Vendo AI MCP Server

How many SDR sender email addresses the account has (included + purchased extras) and the estimated daily email throughput. Read-only.

Set status=active and fire-start all enabled hunters. Reversible via `sdr_pause_search`.

Recent discovery + outreach events for one SDR search, newest first — the same ticker the dashboard shows. Read-only, free.

Removes up to 500 contacts of one search. No restore. Only after sdr_preview_bulk_delete_people was approved.

Read-only. One company of a search: company card (website, size, location, links), decision-makers found with fit, other known people at the company and its live signals. part=card returns only the card and people pool (slower source, up to 20 s).

Read-only. Companies ranked by live signal heat, with ICP fit, signal types and contact status. One search (search_id, pages via offset up to any depth) or all searches merged (first 500 rows, offset + limit ≤ 500).

Turns one hunter on/off and/or sets the search fields it reads (only those listed in its inputs): competitor_pages (Competitor Engagement/Switching), target_cities (local business hunters, email discovery), decision_roles (Decision-maker matching, Website profile), linkedin_search_queries (LinkedIn hiring), industry_keywords / exclude_keywords / relevant_topics. Settings are search-wide.

Creates an SDR search like the wizard's "Create & Start". Preferred: research_job_id from a finished sdr_get_research — every field defaults to the research profile, regions to its regions (or HQ country), all 24 hunters on, competitor pages saved, then the search is activated and the research's first buyers are copied in. Legacy: agent_id + name + target_regions (profile generated from the company profile if offer/ICP omitted). start=false creates a draft without hunting. Hunting is not billed per run; each buying signal that fits the ICP costs 1 credit and each usable contact 5 credits (2 and 10 from hunters on paid data). Errors with 409 if an identical search was just created.

Read-only. Station sparklines: signals per day for every hunter of a search (days 2–60, default 14).

Delete the SDR outreach campaign. The Signal Search and its hunters CONTINUE running. Only call after `sdr_preview_delete_outreach`.

Removes one contact from the search: hidden from lists, counts, exports and outreach. No restore, no refund. Only after sdr_preview_delete_person was approved.

Deletes the SDR process and ALL its data: hunters stop, the outreach campaign is stopped and deleted, signals, contacts, hunter state, QA runs and learning weights are removed. Not reversible, no refund. Only after the user approved sdr_preview_delete_search.

Read-only. What the hunters are doing right now (queries, companies resolved, signals saved, contacts found). Pass since = next_since of the previous call to get only new events. Best effort: last 150 events per search, lost on restart.

Read-only. CSV of every company the search found: Company, Domain, Heat, ICP fit, Signal count, Signal types, Contact status, Contacts found.

Export the contacts of an SDR search as CSV text (name, title, email, LinkedIn, location, company). Contacts ONLY — deliberately carries no scores or signal reasoning, because this file leaves the platform. Returns the raw CSV; can be large. Read-only, free.

Creates a custom audience from a search's contacts with an email (segment fit by default, optional roles or explicit ids). No credits. The audience can then be used in any campaign.

Read-only. Main cities of the given countries (no q), or a name search (q ≥ 2 Latin letters). Use the returned objects as target_cities in sdr_create_search / sdr_update_search.

Run Claude on the agent's knowledge to (re)generate its signal profile. Persists onto the agent so later Signal Searches reuse it.

Read the agent's current signal profile (ICP, offer summary, hunter weights). Returns { exists: false } when nothing's generated yet.

Read the SDR outreach campaign — channels enabled, ready/queued/sent counts, current content config.

Read the configured email subject/body templates and LinkedIn invite template for SDR outreach.

Read-only. Provenance of one contact: hunter, query, triggering signal, scores and the reasoning chain. Needs the search_id the contact belongs to.

Read-only. Pass job_id (from sdr_start_research / a previous poll) or agent_id (while the company profile is still being built, or to get the latest research of a company). Returns status (queued/running/done/error), stages, events and, when done, the result: company dossier and the editable profile (search name, offer, ICP, decision roles, regions, keywords, LinkedIn queries, competitor pages, hunter plan). Poll every 5–10 s.

Read-only. The instant audience of a finished research: up to ~20 matching people from the Vendo database with company, position, country, LinkedIn, email and why they fit — the wizard's "buyers already found" cards. refresh=true rebuilds it (slower).

Fetch one Signal Search by id, including its profile, hunters, and contact counts.

Operator-level health view: states, signals/contacts produced, credits spent, recent events, learning insights for a single search.

Read-only. The hunter page chart: signals and contacts per day for one hunter (days 2–60, default 14).

Read-only. One hunter of a search: run state, signals in 30 days, signals & contacts per day (days 2–60, default 14), the contacts it found (incl. pending/phone-only), and its settings.

Lets the ICP check rewrite the search's industry keywords automatically (default off).

Read-only. Past ICP-QA runs (checked, fits, uncertain, unfit, quality %, keyword changes) and whether keyword auto-correction is on.

Restores the search's industry_keywords to the snapshot taken before the given ICP-QA run (undo an auto-correction).

People page "Check now": classifies unchecked contacts of a search as Fit / Uncertain / Not a fit (AI, not billed) and may suggest keyword changes. Returns the run, or null when nothing is unchecked.

Read-only. Uncertain contacts waiting for re-check, last run results, totals and next scheduled run.

ICP Review "Re-check now": re-judges this search's Uncertain contacts (bounded per run, one run at a time). Contacts moved to Fit become billable (5 credits, 10 from hunters on paid data) when used.

Launches outreach: real emails and/or LinkedIn invites start in the working window and new contacts keep being picked up. Each newly queued contact costs 5 credits (10 from hunters on paid data). Managed senders need a paid plan; client_owned needs a connected mailbox. Only after the user approved sdr_preview_launch_outreach.

Read-only. Learned weight per signal type and conversion from real outreach outcomes, for one search or per search across the workspace.

Recalculate per-signal-type weights from outreach outcomes (replies/meetings vs sends) for one search. Safe, no cost; use when the user asks to refresh/recalculate Signal Learning.

Returns a hosted link where the user connects a LinkedIn account for this SDR's outreach. A human must open it; then pick the account in selected_linkedin_account_ids.

Read-only. The 24 hunter sources a search can run, with UI name, what each looks at, opt-in/paid-engine/LinkedIn-budget flags, whether it can be run by hand, and which search fields it reads. Use to map a hunter the user names ("Competitor Switching") to its id (g2_reviews) before sdr_set_hunters / sdr_configure_hunter / sdr_run_now. Hunters are not billed per run; each buying signal that fits the ICP costs 1 credit and each usable contact 5 credits (2 and 10 from hunters on paid data).

Read-only. SDR outreach processes of the workspace as listed on the Sales Process page (status, channels, counters).

Read-only. Contacts of a search, newest first. Filters: group (fits/uncertain/unfit/unchecked), source (contacts of one hunter, incl. pending/phone-only), company, role, min_relevance; paging up to 200.

List active Signal Searches in this workspace. Optionally filter by agent.

Copies the instant audience of a finished research into a search as contacts (background, idempotent, filtered by the search's regions/cities). sdr_create_search with research_job_id already does this after activation; use this only to repeat it. Contacts are billed (5 credits each, 10 from hunters on paid data) like any other contact when used.

Per-channel sent and queued counts for one SDR search. Read-only, free.

Read-only. Every SDR search of the workspace with signals (7/30 days), contacts, hot companies, hunter health (running/cooling/paused) and outreach, plus workspace totals and a daily series — the /vendo-sdr list page.

Pauses one hunter of a search; the others keep running. Reversible with sdr_resume_hunter.

Stop sending new messages on this SDR campaign. Reversible.

Pauses the whole SDR process: every hunter AND all outreach sending (email and LinkedIn). Data is kept. Reversible with sdr_resume_search.

Read-only. How many contacts are Fit, Uncertain, Not a fit and unchecked. only_with_email=false counts email-or-LinkedIn reachable contacts (what outreach "Who to contact" uses). Use before choosing icp_segment.

Read-only. Contact totals, by role, top companies, daily series (7, 14 or 28 days), credits spent.

Dry run of multi-select delete: checks every id belongs to the search and counts them by group.

Show what would happen. The Signal Search ITSELF is NOT deleted, only the outreach campaign.

Dry run. Shows the contact that would be removed. Nothing changes.

Dry run. Shows the process, how many contacts and signals would be lost and the outreach campaign status. Nothing is deleted. Call before sdr_delete_search.

Dry run of "Save and Launch". Shows the effective settings (request + saved + defaults), contacts in the chosen segment, ready email/LinkedIn contacts, predicted blockers (no LinkedIn account, no own mailbox), the paid-plan rule for managed senders and the delivery window. Nothing is sent. Always call first and show it to the user.

Render an example personalized email/LinkedIn message for a specific contact. Costs ~1 Claude call.

Dry run of the hunter "Run" button. Lists which hunters would run (one source, or every enabled runnable hunter when omitted), flags paid engines and LinkedIn-budget hunters. Nothing runs.

Run Claude on the agent's script and return the auto-generated ICP profile (offer summary, ideal customer profile, relevant topics, LinkedIn queries) WITHOUT persisting anything. Use to review/edit before calling `sdr_create_search`.

Dry run. Shows the move and whether it costs credits: moving a contact the ICP check left free to Fit charges 5 credits (10 from hunters on paid data).

Dry run of the New SDR wizard's first steps. Tells whether a company profile for this website already exists (reused, 0 credits) or must be built (deep website scan 15 + outreach playbook 1 = 16 credits), and whether a recent ICP research (< 24 h) would be reused. Nothing is created. Always call before sdr_start_research and show the cost.

Read-only. Latest signals of one search (search_id) or merged across all searches of the workspace.

Re-run Claude on the agent's current knowledge to regenerate the entire ICP profile and hunter configuration. Useful after the agent's script changed significantly.

Resumes one paused hunter of a search.

Resume a paused SDR outreach campaign.

Resumes a paused SDR process: hunters restart and outreach that was paused together with the search resumes (outreach you paused separately stays paused).

Starts (or wakes, if already running) one hunter or every enabled runnable hunter of a search. Paid engines use Vendo's provider budget, LinkedIn hunters the LinkedIn budget; signals that fit cost 1 credit and contacts found 5 credits each (2 and 10 from hunters on paid data). Call after sdr_preview_run_now.

Read-only. Overall run state of a search (running / paused / idle) with the current action.

Per-source map of run state (running / paused / idle) for a Signal Search.

Outreach window 1 "Save": Who to contact (icp_segment), channels, email sender mode/provider, LinkedIn accounts, time zone, working hours, weekends, daily limits, CRM branch. Partial: missing fields keep their saved values. Never launches: a new process stays a draft; a running one keeps its status and applies the change at once (widening Who to contact on a running process queues more contacts at 5 credits each, 10 from hunters on paid data). Set dry_run=true to preview.

Read-only. Every hunter for a search: enabled or not, live run state, signals in 30 days, 7-day sparkline, and the current values of the settings it reads. The search page's hunter stations.

Enables/disables hunters (the wizard's Hunters step). Pass enable/disable lists, or enabled_sources as the full list. On an active search new hunters start within ~10 min (budget-throttled ones ~30); disabled ones stop at their next cycle. To stop one immediately without disabling it use sdr_pause_hunter.

Overrides the ICP verdict for one contact. Moving a free (precheck-skipped) contact to Fit charges 5 credits, 10 from hunters on paid data (402 if the balance is too low). Call sdr_preview_set_person_group first when moving to fits.

Read-only. KPI cards: fresh signals, signals and contacts by source over the last N days (1–90, default 30).

Starts the New SDR wizard for a company + website, exactly like the web app: reuses the company profile for the same domain or builds a hidden one (website deep scan, playbook; 16 credits), then runs the ICP research (1–3 min, not billed). Returns agent_id and either the research job or a setup state. Poll sdr_get_research until the job status is done, then call sdr_create_search with research_job_id. Only call after the user approved sdr_preview_start_research.

Outreach windows 2–3: email (mode ai/fixed/html, prompt, tone, ≤5 fixed variants with {{placeholders}}, per-step follow-ups, own-HTML steps, signature, auto-reply) and LinkedIn (invite on/off, ai/exact texts, follow-up, delay after accept, conversation rules, auto-reply delays, signature, Calendly). Partial; takes effect on new sends. Follow-up changes are blocked while an email sequence is already sending.

The wizard's Edit → "Save changes": name, hunters, regions, cities, offer, ICP, decision-makers, company size, keywords, exclusions, LinkedIn queries, competitor pages, hot threshold. Partial updates; status is not touched (an active search keeps hunting with the new profile). Status changes only via sdr_activate_search / sdr_pause_search / sdr_resume_search.

Internal team note on the lead card (not visible to the lead). Mentioned users (ids from crm_list_workspace_members) get a CRM notification.

Place the lead in another pipeline too (entry stage); it stays in its current ones. Reversible via crm_move_lead_to_branch.

One card per campaign and per SDR search, with outbound counters. This is the FULL outbound stream — everyone contacted, whether or not they replied (CRM leads only contains people who answered). Contact emails/phones are masked for members without the "crm-contact-details" permission. Read-only, free.

Every outbound touch for one campaign or SDR search, filterable by channel, reply status and date. Use `crm_communication_cards` first to get the id. Read-only, free.

The complete message thread with one contact inside a card. `key` comes from a `crm_communication_history` row (an email address or LinkedIn chat id). Read-only, free.

Create an isolated pipeline (team / direction / client) with its own default stages. member_user_ids = who can see it (General stays open to all). Workspace admins/owner only. No credits.

Add a custom event to the CRM planner. Write operation, no credit cost. Does NOT send invites to anyone — it only records the event on the internal calendar.

Add a lead card to the entry stage of the chosen pipeline(s). ALL fields optional — provide whatever is known (at least one of name/company/title/email/linkedin/phone). Not deduplicated (use crm_import_leads or crm_promote_contact_to_lead for dedup). Side-effect: a card appears on the customer board.

Add a custom kanban column to a pipeline (name, optional hex color, is_terminal for Won/Lost-like end stages). Inserted before the terminal stages. branch = "general" (default) or a branch id.

Remove a custom calendar event. Unlike deleting a lead or a stage this destroys no history and needs no preview step, but it cannot be undone.

Fetch name / title / current employer / avatar / location for a linkedin.com/in/... URL (same lookup the SDR hunters use). May also suggest an email as an UNVERIFIED pattern guess (email_confidence=pattern_guess). Costs one profile view from the workspace's shared daily LinkedIn budget — do not loop over big lists.

One pipeline by id (id, name, is_default). Read-only.

The full message thread with this lead on their source channel (LinkedIn / email / widget / telegram / phone transcript). Read-only.

Full lead card: identity, source ("why is this person here"), company enrichment, activities, comments, assignments. Read-only.

Every pipeline a lead currently sits in, with its stage and owner per pipeline. Read-only.

Returns the file as base64 with its name and mime type (files up to 5 MB; larger ones only via REST). Read-only.

Read CRM settings, including the notify_* toggles that control which events send an email/notification. Read-only, free.

Import up to 1000 parsed rows as leads into the chosen pipelines (entry stage). Dedup by email/phone: an existing lead only gets its blank fields filled (never overwritten) and is added to the pipelines. Returns created / updated / skipped (+ reasons). No credits.

Every pipeline of the workspace (id, name, is_default) — wider than crm_list_branches for members; use it to pick a destination for crm_add_lead_to_branch / crm_move_lead_to_branch. Read-only.

Branches are isolated pipelines inside one workspace (teams / directions / clients). Returns id, name, is_default ("General"), member_user_ids. Read-only. Call before crm_stats / crm_list_leads when the user has more than one branch, then pass branch=<id> (or "general").

List custom calendar events (meetings, reminders) in the CRM planner for a date range. Note: SDR sending windows also appear in the UI calendar but are derived from the search schedule — read those via `sdr_get_search`. Read-only, free.

Files attached to a lead card (id, name, type, size, uploader, date). Read-only.

List leads in the CRM pipeline. Filters: branch ("general" or a branch id from crm_list_branches; omitted = all branches visible to the user), stage (stage id), owner (user id from crm_list_workspace_members), source, q (name/company/email search), range or from/to, limit/offset. Read-only. Great first call for "who replied to me?".

List the LinkedIn accounts connected to this workspace, as shown in the CRM. Useful to see which account owns a conversation. Read-only, free.

Latest 50 CRM notifications of the caller (types: assigned, reassigned, mentioned, new_lead, stage_change) plus total and unread counts. unread_only=true returns only unread ones. For the app bell (billing, meetings, invitations) use list_app_notifications. Read-only, free.

Ordered kanban columns of ONE pipeline (id, name, color, is_terminal). Every branch has its own stages: pass branch ("general" = default, or a branch id from crm_list_branches). Read-only. Call before moving leads.

List the AI agents in this workspace that CRM leads can be attributed to. Read-only, free.

List the people in this workspace who can own a CRM lead. Use before `reassign_crm_lead` to get valid owner ids. Read-only, free.

Clear the CRM notification badge by marking everything read.

Mark a single CRM notification as read. Write operation, no credit cost.

Drag-and-drop equivalent: move a lead to a different pipeline stage by stage_id (get ids from crm_list_stages). Reversible.

Move the lead out of one pipeline into another (entry stage, or to_stage_id of the destination). Reversible.

Dry-run of crm_send_email_to_lead: shows recipient, subject and body exactly as they would be sent. Sends nothing. ALWAYS call first and show the draft to the human.

Turn a person from the Communications stream (crm_communication_history row) into a CRM lead in the New stage. Deduplicated: returns { lead_id, already_existed }. Needs at least one of email / linkedin_url / phone. No credits.

Set the full left-to-right order of one pipeline's stages (every stage id exactly once — get them from crm_list_stages with the same branch). Applies to the whole workspace. Reversible.

Sends a REAL LinkedIn message or email reply to the lead on their source channel, from the customer's own account. Also moves the lead to the "Manager Dialog" stage. ALWAYS show the drafted text to the human and get approval BEFORE calling this.

Sends a REAL email from the CRM card ("<your name> via Vendo AI", replies go to your own address) and logs it on the card. Members need the crm-contact-details permission. Only call after the user approved the exact draft from crm_preview_email_to_lead.

Counts per stage, new today/this week, stale leads. Read-only. Optional branch ("general" or a branch id from crm_list_branches) — omitted = all branches visible to the user. If the workspace has more than one branch, call crm_list_branches first and report per branch or ask which one.

Rename a pipeline and/or replace its member list. The General pipeline cannot be changed. Admins/owner only.

Edit an existing custom calendar event (title, times, all-day, description, colour, linked lead — lead_id null unlinks). Write operation, no credit cost.

Patch lead attributes (name, company, title, email, LinkedIn, phone, notes, tags, deal value + currency). Stage and owner have their own tools (crm_move_lead, reassign_crm_lead). Reversible.

Change workspace CRM settings: which notifications fire (new lead, reassigned, mention; by email and/or in-app), the stale-lead alert, the default date range, and which agents / sources / LinkedIn accounts never create leads. Write operation, no credit cost. Turning notifications off or excluding sources means the human stops being alerted / leads stop appearing, so confirm with the user first. (Personal email preferences: update_notification_preferences.)

Rename, recolor or toggle is_terminal of a stage. System stages (New, Manager Dialog) cannot be renamed. To change the column order use crm_reorder_stages.

Attach one file to a lead card (base64 or https URL). Allowed: pdf, doc(x), xls(x), csv, txt, rtf, odt, ods, ppt(x), png, jpg, gif, webp, heic, zip. Stored privately; adds an activity entry. No credits.

Delete a non-default pipeline; its leads are not deleted but return to General. NOT reversible. Admins/owner only. Only call after the user approved preview_delete_crm_branch.

Soft-delete a lead — it disappears from the pipeline (restorable by support only). Only call after the user reviewed `preview_delete_crm_lead` output and explicitly approved.

Permanently delete a file from a lead card. NOT reversible. Only call after the user approved preview_delete_crm_lead_document.

Delete an EMPTY, non-system pipeline stage. Only call after the user reviewed `preview_delete_crm_stage` and explicitly approved.

Status and settings of the Kommo or HubSpot connection ({connected:false} if none). Use it to poll after connect_crm_integration. Read-only.

Recent sync events (contact/lead created, errors) of the caller's own Kommo/HubSpot connection. Read-only.

External CRM connections of the workspace (Kommo, HubSpot): status, account, sync settings and counters. Tokens are never returned. Read-only.

What to sync and where: sync_conversations, sync_contacts, create_leads, auto_sync, pipeline_config (Kommo pipeline_id / stage_id / responsible_user_id from list_kommo_pipelines / list_kommo_users), field_mapping. Affects what is written into the external CRM — confirm with the user.

Dry-run: which accounts would get the campaign audience queued, how many contacts and what is already queued. Nothing changes. Call before activate_campaign_linkedin.

Dry-run of activating the phone channel with numbers the account already owns: numbers, objective, calls/day, window and estimated credits per call/day. Nothing is scheduled. Numbers cannot be bought through the API.

Render a sample outreach email from an agent — no sending, no credits. Optional mode/prompt/tone/customInstructions/variant/followUp{index,delayDays,previous}/sample make it render exactly like a campaign would (same as preview_campaign_email).

Show what archiving would do — NOTHING CHANGES: current status and channels, what stops (an active campaign stops ALL outreach at once and releases its mailboxes / LinkedIn accounts), what is kept (history, threads, stats, CRM leads). Archiving cannot be undone (duplicate_campaign to run the same setup again). ALWAYS call first and show the user before archive_campaign.

Dry-run of purchasing an audience set — returns the set, contact count, price per contact, estimated credits, current balance and can_afford, WITHOUT spending credits. ALWAYS call this first and show the cost to the human.

Render the exact email a campaign would send — first email or follow-up #k — with the writing rules, tone, Communication Rules or fixed text. Pass campaign_id to use its saved settings (any field you pass overrides them), or agent_id + rules for an unsaved draft. No sending, no credits.

Render the first LinkedIn message sent after an invite is accepted (AI from the agent, or the fixed text with placeholders filled). Pass campaign_id to use saved settings. No sending, no credits.

Render the LinkedIn connection note a campaign would send (AI from rules/tone, or fixed text with placeholders), with its length vs the 200-char limit. Pass campaign_id to use saved settings. No sending, no credits.

Show which meeting the agent would skip. Nothing changes. Call first and show the user.

Explain what connecting a WhatsApp number does and list the accounts already connected. No link is created. Call first, then connect_whatsapp_account after the user approves.

Step 1 of an upload: send a CSV/XLSX/XLS/TSV/TXT file (base64 or https URL) and get the detected headers, a suggested column mapping, sample rows, total rows and the list of target fields. Creates nothing, no credits. Then call `upload_custom_audience` (optionally with a corrected column_mapping).

Show what deep_scan_agent would do: cost (15 credits), duration (60-180 s) and what gets saved. Nothing runs. ALWAYS call first and get the user's approval.

Show what would happen if you delete an agent. The agent is NOT deleted. ALWAYS call this first and surface the result to the user before calling `delete_agent`.

Show what removing a channel would do. Nothing is removed. ALWAYS call first and show the user before delete_agent_connection.

Show what would happen if you delete a campaign. The campaign is NOT deleted.

Dry-run: shows the pipeline and how many leads would fall back to General. Changes nothing. ALWAYS call before delete_crm_branch.

Dry-run of deleting a CRM lead — shows who would be removed from the board. ALWAYS call this first and show the result to the human.

Dry-run: shows which file would be deleted. Changes nothing.

Dry-run of deleting a pipeline stage. Deletion is refused downstream if the stage still holds leads or is a system stage.

Dry-run: shows the audience name and how many contacts would be deleted. Changes nothing. ALWAYS call before `delete_custom_audience` and show the result.

Dry-run of removing one contact from a custom audience. Changes nothing. Show the result to the human before `delete_custom_audience_contact`.

Show the lead that would be deleted. Nothing is deleted. Call first and show the user before delete_narrator_lead.

Dry-run: which client_owned campaigns are affected and how many usable mailboxes remain. Nothing changes.

Dry-run of removing a publishing account. Nothing changes.

Dry-run: shows which connection would be removed. Changes nothing.

Show what disconnecting Google Meet would do. Nothing changes. Call first and show the user.

Dry-run of removing a LinkedIn account, showing the capacity that would be lost. ALWAYS call this first.

Show which Telegram bot would be detached from the agent (username, chats, messages). Nothing changes. Call first.

Show the WhatsApp account that would be disconnected. Nothing changes. Call first.

Dry-run of enrichment: how many contacts still need enrichment, the maximum credits (1 per contact), estimated minutes, the current balance and whether it can start. Spends nothing. ALWAYS call first and show the cost to the human.

Dry-run: checks whether the email can be invited (caller is admin, not already a member, no pending invite). Sends nothing.

Dry-run of `launch_audience_set`: shows the set, contact count, credits it would cost (signals sets: price per contact for a fresh snapshot; people sets: free) and the balance. Nothing is bought or sent. ALWAYS call this first and show the cost.

Readiness report for launch/resume — NOTHING IS SENT: ready flag, blockers (AGENT_REQUIRED, AUDIENCE_REQUIRED, AUDIENCE_EMPTY (0 contacts), CLIENT_MAILBOX_NOT_CONNECTED, PAID_PLAN_REQUIRED for Vendo managed senders, INVALID_STATUS), warnings, real recipient count, channels, daily email/LinkedIn limits, sender mode, email steps, schedule and the LinkedIn accounts that will be activated. ALWAYS call this first and show the result to the user before launch_campaign.

Sample invite, follow-up and auto-reply plus suggested pitch/signature for an account in a campaign (built from the campaign's agent). No sending, no credits.

Render a sample first follow-up (after the connection is accepted). No sending, no cost.

Render a sample LinkedIn connection request from this agent. No sending, no cost.

Show which number would be called from which, and the cost (25 credits/min, max 2 min). Nothing is dialled. ALWAYS call first.

Dry-run of re-authenticating a LinkedIn account. Explains the side-effects without doing anything. ALWAYS call this first — reconnecting changes the account id upstream and can orphan existing outreach history.

Show whether the agent is in this live meeting and what removing it does. Nothing changes.

Dry-run: shows who would lose access. Changes nothing. ALWAYS call before remove_workspace_member.

Dry-run: recipient, subject (defaults to Re: last subject) and the exact text. Nothing is sent. Call before reply_in_campaign_thread and show the text to the user.

Dry-run of replying to a lead's email reply: shows recipient, subject and the exact text. Nothing is sent. Call before reply_to_campaign_email and show the text to the user.

Dry-run: how many ready prepared emails would be scheduled into the campaign working hours. Nothing changes. Call before schedule_campaign_delivery.

Dry-run: how many prepared emails would be sent immediately (outside the schedule). Nothing is sent.

Dry-run: recipient, exact text, cost (3 credits) and whether the balance suffices. Nothing is sent. Call before send_linkedin_message and show the text to the user.

Show the recipient and exact text of an operator message. Nothing is sent. ALWAYS call first and show the user the text.

Dry-run of set_workspace_member_role. Changes nothing.

Show what setup_phone_agent would do with the same arguments: which channel is created or updated, which of YOUR numbers is attached, objective, voice, inbound on/off. Nothing is attached or created. ALWAYS call first and show the user, then call setup_phone_agent with the same arguments after approval.

Dry-run of enabling/changing automatic lead discovery: source, daily credit budget, leads/day. Nothing changes. Call before update_campaign_discovery whenever discovery is (or stays) enabled.

Add a connected account to a running campaign; pending contacts are rebalanced across accounts and backfilled. It starts sending invites in the next cycles. No credits.

Create a classic campaign in DRAFT — nobody is contacted until launch_campaign. Needs an audience (audienceId from save_audience/list_audiences, OR customAudienceId of a READY uploaded/CRM list) and should get an agentId (a campaign cannot be launched without an agent: AGENT_REQUIRED). branchId = CRM branch for replies (crm_list_branches; null = General). Settings (all optional): channels, dailyLimit, dailyEmailLimit, dailyLinkedinLimit, timezone, workingHours, excludeWeekends, campaignDurationDays, customInstructions (Communication Rules incl. form of address), emailSignature, notifyEmails, ccEmail, autoResponseEnabled, autoResponseDelayMinutes, followUpInterval, maxFollowUps, trackOpens, emailSenderMode (managed needs a paid plan), senderEmailIds, emailContent {mode, prompt, tone, variants, htmlSteps, followUps[{delayDays, prompt|subject+body}]}, linkedinContent {mode, invite_prompt, invite_tone, invite_exact_text, followup_delay_minutes, followup_exact_text}, selectedLinkedinAccountIds, linkedinAutoReplyDisabled. Ids are checked against the workspace. Free, no sending.

Permanently delete a campaign. NOT reversible. Only call after the user has reviewed `preview_delete_campaign` output and explicitly approved.

Full campaign: status, settings (all wizard fields), sequence, channel paused flags, channelStatuses, today's sends, stats.totalContacts. Read-only.

Paged activity events of a campaign (discovery, outreach, engagement, system, billing). Poll it instead of a live stream. Read-only.

Sales Process KPIs for the workspace: totals (campaigns, emails sent, opens, clicks, replies, contacts, rates) and per-campaign performance, optionally for a date range. Read-only. For SDR + campaigns combined use the SDR analytics tool.

AI lead discovery settings of a campaign (null when never configured). Read-only.

One sent email by email id (from list_campaign_emails / list_campaign_replies): content, recipient, related open/click/reply events, the reply and the conversation. Read-only.

Email funnel: sent, delivered, opened, clicked, replied (real / auto-reply / bounce), bounced; delivery block (delivered vs not delivered: bounced, rejected as spam, unsubscribed; sender inbox-placement test — real inbox vs spam folder is not reported by providers) and unique opened/clicked/replied. Read-only.

LinkedIn counters (total, pending, invites sent, connected, messaged, replied, failed), invites sent today, effective daily limit and active accounts; optionally for one account. Read-only.

Email channel progress: audience size, processed, % complete, event counts, queue depth and provider status / sent today. Read-only.

Monitor page data: AI lead discovery config + stats, audience growth by day, the last 100 activity events, event counts and credits (balance, spent today/total, daily budget). Read-only.

Call counters: total, completed, active, pending, no answer, voicemail, failed, interested, meetings booked, not interested, average/total duration. Read-only.

What the campaign is doing now (sending / idle / outside_hours / paused / queue_empty / done), today vs daily limits, 7–28-day email + LinkedIn series and the latest events. Read-only.

One conversation with all messages (AI, human and contact). Read-only.

Leads found by AI lead discovery for a campaign, filterable by status (discovered, enriching, enriched, added_to_audience, rejected, duplicate, enrichment_failed). Read-only.

Recipients with their open/click/reply counts, read live from the sending provider (throttled: once per 15 s per campaign). Read-only.

state=sent: emails already sent (filter by status, search by address); state=queued: scheduled/queued emails waiting to go out; state=prepared: pre-generated emails pipeline with status counts and preparation progress. Read-only.

Accounts working this campaign with per-account counters (pending, invites sent, connected, messaged, replied). Read-only.

Contacts in the campaign's LinkedIn queue with their status (pending, invite_sent, connected, message_sent, replied, failed, skipped), optionally for one account. Read-only.

Calls with contact, status, outcome, duration, sentiment, summary and recording URL. Read-only.

Email replies received by a campaign with body and classification: real (a person answered), auto_reply (out of office), bounce. Read-only.

Conversations the AI is handling for a campaign (filter by status ai_handling|human_takeover|closed and sentiment positive|objection|referral|unsubscribe|neutral), plus counters by status and sentiment. Only threads of the API key's user. Read-only.

Stop using an account for this campaign; its pending contacts move to the remaining accounts. Already-sent invites stay.

Change a campaign's name, description or any wizard setting (partial: send only what changes; settings are merged). agentId and branchId can be changed only while the campaign is a draft. Settings (all optional): channels, dailyLimit, dailyEmailLimit, dailyLinkedinLimit, timezone, workingHours, excludeWeekends, campaignDurationDays, customInstructions (Communication Rules incl. form of address), emailSignature, notifyEmails, ccEmail, autoResponseEnabled, autoResponseDelayMinutes, followUpInterval, maxFollowUps, trackOpens, emailSenderMode (managed needs a paid plan), senderEmailIds, emailContent {mode, prompt, tone, variants, htmlSteps, followUps[{delayDays, prompt|subject+body}]}, linkedinContent {mode, invite_prompt, invite_tone, invite_exact_text, followup_delay_minutes, followup_exact_text}, selectedLinkedinAccountIds, linkedinAutoReplyDisabled. On a running campaign, changed email steps/delays are not applied once anything was sent (settings.smartleadSequencePending). No sending, no credits.

Turn on or adjust automatic lead discovery: it runs daily, SPENDS CREDITS up to daily_discovery_budget_credits and adds new leads to the campaign audience. Same args as preview_update_campaign_discovery; only after the user approved that preview. Disabling (enabled=false) needs no preview.

Upload a material the agent learns from (PDF, DOC, DOCX, TXT, XLS, XLSX, CSV, PPT, PPTX, KEY; ≤10 MB) from a public URL or base64. Used the next time the script is generated (generate_agent_script). Free.

Create an AI agent like step 1 of the app's builder. Choose its direction: purpose "sales" (default), "support" or "info". The agent starts in DRAFT and contacts nobody. Needs at least 1 credit on the balance (checked, not charged). Fails with a plan-limit error when all agent slots are used (see get_agent_plan_limits). Next: set_agent_company → generate_agent_script → channels.

Add a channel. WEBSITE_WIDGET needs website_url; new widgets get the app defaults (Modern design) plus your widget_config — then get_widget_embed_code. WEBSITE_BUTTON: just creates the channel (style it in get_widget_embed_code). PRESENTATION_WIDGET = publish the Slide Presenter (optional website_url). GOOGLE_MEET: prefer connect_google_meet. PHONE_CALL: prefer setup_phone_agent. Telegram → connect_telegram_bot; WhatsApp → connect_whatsapp_account. A second widget for the same URL updates the existing one. Free. Interactive cards in chat need design "modern"; in voice they need set_agent_voice screen_cards=true.

Permanently delete an agent. NOT reversible. Only call after the user has reviewed `preview_delete_agent` output and explicitly approved.

Remove a channel from the agent (the embed code stops working). No undo. Only after preview_delete_agent_connection and explicit user approval.

Fetch the full details of a single agent by id.

Full settings of one channel (website widget, button, presentation, Google Meet, phone, Telegram). Read-only.

Conversations, messages, unique visitors, last activity of one channel. For widgets prefer get_connection_analytics (fresher). Read-only.

Status and result of a deep scan or script generation job started by deep_scan_agent / generate_agent_script (kept 1 hour). Poll every 10-20 s while status is "running". Read-only.

How many agents can the user create (base plan + purchased extra slots) vs how many they have. Read-only.

See every channel attached to this agent: widgets, telegram, phone, presentations, etc.

Deep scans and script generations of this agent in the last hour (status only) — use when a job_id was lost. Read-only.

Alias of get_presentation kept for older clients: returns the agent's current Slide Presenter deck (PDF name, slides with text and presenter script, look, call-to-action, voice, published channels, direct link) — slides_count 0 when no deck is uploaded. Prefer get_presentation. Read-only.

Remove an uploaded material from the agent (see get_agent → documents[].url). Free.

The agent leaves the live Google Meet call right now. Only works while the meeting is in progress. Only after preview_remove_agent_from_meeting and user approval.

Upload a custom avatar photo (JPG, PNG or GIF, ≤5 MB) from a public image URL or base64. Replaces the preset face. Free.

Required before `generate_agent_script` will work. Set the company the agent represents — its name, website, and what it sells.

Set the meeting link, presentation link, email, phone, WhatsApp, Telegram and up to 10 custom links that the agent gives to visitors (also shown as screen cards). MERGE: only the channels you pass change; pass "" (or null for custom_links) to clear one. Write, free.

Legacy flags on the agent (zoom_enabled, google_meet_enabled, website_embed_enabled). Channels are managed with the connection tools; this does not connect anything. Free.

Change agent status. Allowed values: ACTIVE, PAUSED, ARCHIVED, DRAFT.

Configure the voice of the agent's website widget exactly like the app's widget settings page and create/update the voice agent at the voice provider, so voice calls in the widget really work. Only the settings you pass change (the rest keep their saved values or the app defaults). voice_id is required the first time (list_voice_catalog). Takes up to ~1 min. Free to configure; widget voice calls cost 15 credits/min.

Change an agent's name, description, direction (purpose), voice gender or preset face. Only the fields you pass change. Company name/website/description → set_agent_company; contacts → set_agent_contact_channels. Free.

Change a channel: website widget look and behaviour (design, colours, button picture, invitation/auto-open, sounds, contact form and its wording, greetings, page navigation, voice view), name, website_url, Google Meet settings or phone texts. Only what you pass changes; widget texts and theme are merged. Free.

Replace the script stages (rename, reorder, edit, add or remove stages) and optionally the tone, like the builder's script editor. Send the FULL list of stages you want; the full text is rebuilt from them. Get the current stages from get_agent (script_sections). Free.

Append up to 5000 contacts to a custom audience. Deduplicated inside the audience by email, LinkedIn URL or phone (duplicates and contacts with no email/LinkedIn/phone are skipped). Returns added / skipped / total_contacts. No credits.

Create an empty, named custom audience (status ready) — then fill it with `add_custom_audience_contacts`. To create one from a file use `upload_custom_audience`. No credits.

Permanently delete a custom audience with all its contacts and source file. NOT reversible. Only call after the user approved `preview_delete_custom_audience`.

Permanently remove one contact from a custom audience (not reversible). Optional reason (UI choices: Not relevant, Wrong contact, Already a customer, Bad data, Other) is logged to improve automatic selection. Only call after the user approved `preview_delete_custom_audience_contact`.

One custom audience: status, counts (with email/phone/LinkedIn), enrichment progress, column mapping and the first 20 contacts. Page through all contacts with `get_custom_audience_contacts`. Read-only, free.

Paged contacts of a custom audience (max 100 per page). Contacts added by Vendo SDR carry signal_context (why they were picked: reasoning, relevance score, ICP group). Read-only, free.

Status and progress of a running (or finished) enrichment: status, enrichment_total, enrichment_done, enrichment_progress (%), done flag. Poll every 10–30 s. Read-only.

List the workspace's custom audiences — uploaded CSV/XLSX lists, purchased audience sets, CRM selections — with status (processing|ready|enriching|error), contact counts and enrichment progress. These are different from campaign audiences (`list_audiences`). Read-only, free.

Edit one contact of a custom audience (only the fields you pass change). No credits.

AI-write "what the agent knows" about the company from its website (no full scan). Costs 1 credit. NOT saved — pass the text to set_agent_company (company_description).

Write AI descriptions + keywords for website pages (output of scan_agent_website). Costs 1 credit per 5 pages. Not saved.

Generate the agent's script (stages + full text + email/LinkedIn script) in the chosen tone for its direction (sales / support / info), using the company description and uploaded files. Saves it on the agent (overwrites). Costs 1 credit, takes 60-90 s. Needs company_name and company_description (set_agent_company). If it is still running after ~200 s you get a job_id → get_agent_job.

Read a public web page and return a knowledge text block about it. Costs 1 credit. NOT saved — append the result to company_description with set_agent_company if you want the agent to know it.

Draft a call script and greeting from the agent's sales script for a call objective, in the agent's language. Free. Not saved — pass it to setup_phone_agent (or let setup_phone_agent generate it).

AI-write what the presenter says on one slide, in the presentation's language. 1 credit (2 with image_url — the AI looks at the slide). NOT saved — put it into narrator_script with set_presentation_slides.

Legacy support-script generator of the old text-widget creators. Prefer generate_agent_script with purpose "support". Needs company name + description. Costs 1 credit.

Generate the phrases the Slide Presenter uses to move between slides, in the presentation's language, and save them on the agent. Needs saved slides (set_presentation_slides).

Connect the user's OWN mailbox for sending. Requires SMTP/IMAP hosts+ports and an APP PASSWORD, which passes through this conversation: prefer asking the user to connect it in the app (Settings → Email Sending) unless they explicitly give you the password. WARM-UP STARTS IMMEDIATELY: the real mailbox sends and receives warm-up mail. The password is never returned. Gmail: smtp.gmail.com:465 / imap.gmail.com:993; Outlook: smtp.office365.com:587 / outlook.office365.com:993.

Returns a hosted URL a HUMAN must open in a browser to authorise a LinkedIn or Instagram publishing account. Give the link to the user; nothing is connected until they finish.

Returns an authorization URL a HUMAN must open in a browser (logged in to Kommo/HubSpot) and approve within 20 minutes; the connection completes server-side. Give the URL to the user, then poll get_crm_integration. Kommo needs save_kommo_credentials first.

Turn on the Google Meet channel the way the app does: returns the agent's own invite address ([email protected]). Invite that address to any Google Calendar event with a Meet link and the agent joins automatically. No Google login needed. Also saves the meeting settings. Free to connect; meeting minutes are billed.

Returns a hosted URL that a HUMAN must open in a browser to authorise a LinkedIn account. This tool cannot complete the connection itself — give the link to the user. No account exists until they finish the flow.

The user creates a bot with @BotFather, gets the HTTP API token, and passes it here. After that, all messages to the bot are answered by the agent.

Returns a hosted link; the user opens it and scans the QR code with WhatsApp (Linked devices) — that links a REAL phone number to the workspace. Poll list_whatsapp_accounts until status is "ok". Free. Only after preview_connect_whatsapp_account and the user's approval.

Stop using the mailbox as a sender. If none remain, client_owned campaigns cannot send or launch. Only after the user approved preview_disconnect_client_mailbox.

Remove the publishing account; it can no longer publish posts. Only after the user approved preview_disconnect_content_account.

Remove the Kommo/HubSpot connection: syncing stops, tokens and settings are deleted; reconnecting needs OAuth again. Only call after the user approved preview_disconnect_crm_integration.

Remove the Google Meet channel from the agent and turn auto-join off. Already scheduled meetings are not cancelled (use cancel_meeting). Only after preview_disconnect_google_meet and user approval.

Remove a LinkedIn account from the workspace. Any campaign or SDR search sending from it stops immediately and daily capacity drops. Only call after the user reviewed `preview_disconnect_linkedin_account` and explicitly approved.

Detach the bot from this agent: the webhook is removed and the bot stops answering (it keeps existing in Telegram; chat history is kept; reconnect with connect_telegram_bot). Only after preview_disconnect_telegram_bot and the user's approval.

Disconnect and delete the WhatsApp account; auto-replies stop and reconnecting needs a new QR scan. Only after preview_disconnect_whatsapp_account and user approval.

Read one saved audience with its filters and contact count. Read-only, free.

Details of one marketplace set by slug: size, description, freshness. Use the contact count here to work out the purchase cost (2 credits per contact). Read-only, free.

Full card of one contact in a marketplace set: person, company, buying signal, channels. Contact details stay masked until the set is bought. Contact ids come from `get_audience_set_contacts`. Read-only, free.

Paginated preview of the contacts inside a marketplace set. Contact details stay masked until the set is purchased. Read-only, free.

Browse pre-built, ready-to-use audiences available for purchase, plus their categories. Browsing is free; buying costs credits. Read-only.

Search the people graph for prospects matching include AND exclude filters (countries, cities, industries, positions, company sizes, tags, company keywords, language, freshness, must-have-email/LinkedIn/phone/booking link). PREVIEW only — returns aggregate counts and a small sample. Does not save anything, does not contact anyone, does not spend credits. Next: `save_audience` with the same filters.

Credit deductions + grants of the workspace, newest first. Optional filters: type, date range (from/to, a date-only `to` is inclusive), pagination. With filters the gateway scans the newest 5000 rows; `has_more`/`total_matched` tell you if there is more. Read-only.

Total credit spend per agent in the workspace. Identifies the most expensive agents.

Per-session credit spend (newest first) with connectionType (email_outreach, linkedin_invite, linkedin_message, phone_call, widget, voice, sdr_contact, ...). With from/to it also returns totals_by_type for that range. Read-only.

Total credits spent by one specific agent.

Per-channel credit spend (widget, telegram, phone, etc.) for one agent. Identifies the costliest channels.

Calendar-month breakdown of credit spend across all categories.

The agent's presentation: PDF name, slides (text + presenter script; images with include_images), look, call-to-action, presenter voice, published channels and direct link. Read-only. (list_agent_presentations shows only the legacy creator.)

Direct link (narrator page) and the HTML snippet with the saved look. Publish it as a channel first (create_agent_connection type PRESENTATION_WIDGET). Read-only.

The button viewers see: a lead form (fields) or a link. Only what you pass changes (fields replaces the whole field list). Leads land in list_narrator_leads. Free.

Theme, colours, corner radius, controls, autoplay, voice on/off, chat on/off, Modern look (background, glass, font, panel side, presenter bubble, voice visual), slide transition and button texts. Only what you pass changes. Free.

Save the slide deck — REPLACES all slides (add, remove, reorder, edit). Each slide: image (public URL or base64; JPG/PNG/WebP/GIF ≤5 MB; omit to keep the stored image of an existing slide id), extracted text and presenter script. PDF upload is not supported by the API: render the PDF pages to images first. Then write scripts with generate_slide_script and set_presentation_voice. Free.

The Slide Presenter's own voice and model (the website widget voice is not touched). Same settings as the app; only what you pass changes. Needs saved slides. Takes up to ~1 min. Free to configure; presentation voice costs 17 credits/min.

Chats, messages, voice calls, text messages, unique users and credits (text/voice) of the agent's Telegram bot for a date range. Read-only.

See the connected bot username + settings.

All messages of one Telegram chat, incl. voice-call turns with recording URL and duration. Read-only.

People/groups talking to the agent's Telegram bot: name, username, type, message count, last message time. Paged. Read-only.

Show or hide the VOICE button of the agent's Telegram bot (voice calls in the mini app). Needs a connected bot. Free.

Voice and behaviour of the Telegram bot's voice calls (separate from the website widget): the same settings as set_agent_voice plus the mini app look (visual). Only what you pass changes. Needs a connected bot. Takes up to ~1 min. Free to configure; calls are billed per minute.

Meetings, minutes, completed, missed and credits used for a date range. Read-only.

Whether Google Meet is connected for this agent, its invite address, settings and totals. Read-only.

All meetings of this agent (newest first) with status, times, duration, whether a transcript exists. Paged. Read-only.

Read-only list of meetings the agent has scheduled. Requires Google Meet connected first.

Auto-join, minutes before start, greeting, language, meeting mode (voice only / presentation — needs slides). Only what you pass changes. Free.

Per-account LinkedIn settings shared by every campaign and SDR process using the account: AI auto-replies (on/off, tone, instructions, pitch, booking link, reply delays, daily limit, working hours, agent, contact info), invites (on/off, tone, pitch, instructions, CTA), follow-ups (on/off, pitch, instructions, CTA) and signature (text, first_message|every_message). The first read creates defaults (pre-filled from campaign_id's agent).

All messages of one LinkedIn chat (chat_id from list_linkedin_conversations). Read-only.

LinkedIn accounts of the workspace and their status (ok = can send; ~70–80 invites/day each). Returns { role, accounts } (role is filled only with detailed=true). detailed=true adds owner/role, campaigns and SDR searches using each account, 7-day activity, prospecting caps, warm-up stage, premium tier and proxy country. Read-only.

LinkedIn chats of the workspace (optionally of one campaign and/or account): contact, last message, pending AI reply, human takeover flag, outreach status. Read-only.

Change AI auto-replies, invite / follow-up pitch, CTA, signature, reply delays/limits for ONE LinkedIn account (applies to all campaigns and SDR processes using it). Send only changed fields. To switch AI replies off for a single campaign use update_campaign settings.linkedinAutoReplyDisabled. No credits.

Permanently delete a presentation lead. Only after preview_delete_narrator_lead and explicit user approval.

Slide Presenter analytics. view "summary" (default): views, presentations started, watch time, unique viewers, average duration, completion rate, recent sessions, per channel. view "period" with date_from/date_to: widget loads, starts, watch minutes, unique viewers, credits used. Read-only. (No per-slide drop-off.)

Leads from the presentation call-to-action form (form data, page, status, notes). Filter by status, page with limit/offset. Read-only.

Set a presentation lead's status (new / contacted / converted / spam) and notes. Free.

Calls attempted/completed/successful, minutes and credits of one Voice Call channel. Read-only.

Phone calls of this agent (incl. test and inbound) with transcript, recording URL, summary, outcome, sentiment, duration and credits, plus totals by outcome/sentiment. Read-only.

Phone numbers already on your account (number, country, type, monthly cost, per-minute rate). Buying numbers is done in the app. Read-only.

DIALS A REAL PHONE: the agent calls to_number from the channel's number (max 2 min, 25 credits/min). Only call the user's own number, only after preview_phone_test_call and explicit approval.

Create a new tracked referral link (max 20 active). Returns code and url.

Commission %, minimum payout, totals (visits, signups, paying customers, revenue, earned, paid out, available), every referral link with its stats, and payout request statuses. Payout requests themselves can only be made in the app. Read-only.

Everything needed to render the share card / QR for a link: url (QR payload), short url, headline and description texts. Render the QR image yourself. Read-only.

Change a link label or archive it (archived links stop attributing new signups; archived=false restores).

Workspace name/owner, members (user_id, email, name, role, feature permissions), pending invitations, and whether the caller is admin/owner. Read-only.

Remove a member: they immediately lose access to this workspace (their account gets its own empty workspace). Re-adding needs a new invitation. Admins only. Only call after the user approved preview_remove_workspace_member.

Restrict what a (non-admin) member sees: an allow-list of features, or null for full access. "crm-contact-details" controls whether they see lead emails/phones. Admins only; the owner and admins cannot be restricted.

admin=true makes the member an admin (full access, can manage team and pipelines); false demotes to member. Owner only. Only call after the user approved preview_set_workspace_member_role.

Older overview numbers of all agents (superseded by get_analytics_agents). Read-only.

List all AI agents in the account. Read-only.

Same as `list_agents` but includes per-agent stats (connections, credits spent, status).

Remove one in-app notification from the caller's list.

Number of unread in-app notifications (the bell badge). Read-only.

The caller's in-app notifications, newest first (type, subject, preview, isRead, createdAt), with unreadCount and paging. Types include MEETING_TRANSCRIPT, MEETING_NOTIFICATION, SUBSCRIPTION_*, PAYMENT_RECEIPT, LOW_CREDITS, CREDITS_ADDED, INVITATION, CUSTOM. CRM lead notifications are separate (crm_list_notifications). Read-only.

One meeting with transcript, summary, action items, join/leave time and duration. Read-only.

Transcript messages, summary and action items of a meeting (from the database or the recording service). Read-only.

Agents that have Google Meet connected (the calendar's agent filter). Read-only.

The API key owner's profile: name, email, company, position, avatar. Read-only.

Upload a JPG/PNG/GIF (≤5 MB) as the profile photo, from an https URL or base64.

Change first_name, last_name, company_name, position of the API key owner. (Email, password and 2FA are UI-only.)

Save a campaign audience from the same filter set as `search_audience` (call that first to check the counts). Returns the audience id to pass to `create_campaign`. No outreach happens here, no credits.

Kommo private integration step 1: store the Integration ID (UUID) and Secret key of the Vendo app the client created in their Kommo account. The secret is never echoed back. Returns the redirect_uri to paste into Kommo. Then connect_crm_integration provider=kommo.

Save company facts (team, contacts, social links, pricing, employee count, auto re-scan) onto the agent — what the app does after a scan. Side effects: stores them in the agent, creates/updates the company and people records, fills BLANK contact channels (never overwrites manual ones). Not needed after deep_scan_agent with persist=true. Free.

Send up to `limit` prepared emails immediately, ignoring the schedule. REAL emails to real people. Only after the user approved preview_send_campaign_emails_now.

Send a REAL LinkedIn message in the chat; costs 3 credits, the AI stops messaging this contact (human takeover) and the CRM lead moves to Manager Dialog. Only after the user approved preview_send_linkedin_message.

Sends a REAL Telegram message from the bot to this person (human takeover). Only after preview_send_telegram_message and the user approved the exact text.

Queue the campaign audience for LinkedIn on the given (or selected/all connected) accounts and add linkedin to the channels. On an active campaign REAL connection invites start within the next cycles. Only after the user approved preview_activate_campaign_linkedin.

Schedule REAL outbound AI calls to every audience contact with a phone number; credits are charged per call minute. Same args as preview_activate_campaign_phone; only after the user approved that preview. Pause with pause_channel channel=phone_call.

All metrics of the workspace's agents for a UTC date range (default: the page default), optionally one agent: totals, rates, daily series, funnel (widget loads → opens → conversations → contacts → leads), by agent / channel, leads by source, recent leads, credits by type, languages, pages, traffic sources, hours, durations, previous-period comparison. Read-only.

Outreach analytics for a UTC date range across Vendo SDR and classic campaigns, or narrowed to one SDR search (search_id) or one campaign (campaign_id) — never both: totals, rates, daily series, delivery (sent/delivered/bounced/inbox placement), by product / source / type, contacts by source, enrichment, funnel, per-process rows. Read-only.

Get the current shared credit balance of the workspace (credits belong to the workspace owner; member keys see the same number). Read-only, no side-effects, no cost.

Richer than `get_balance` — returns balance, total subscription credits, total purchased, total spent, free-trial credits, email/workspace info.

The agent will NOT join this scheduled meeting (the calendar event itself stays). Only scheduled, not yet started meetings. No undo. Only after preview_cancel_meeting and user approval.

Cancel a pending invitation (its link stops working). Admins only. Invitation ids come from get_workspace.pendingInvitations.

For a website widget/button/presentation channel: widget loaded, activated, chats started, voice calls started, plus estimated credits (text messages, voice minutes) for a date range. Read-only.

Conversations of a widget/presentation channel with messages, mode (chat/voice), visitor name/email/phone and page. Paged (limit ≤500). Read-only.

Create a copy of an existing agent (new id, same config). Counts toward agent capacity.

Copy a campaign (settings + audience) into a new DRAFT named '<name> (Copy)'. Nothing is sent. Note: the copy re-uses company-based audiences only and has no CRM branch; check get_campaign of the copy before launching.

Pipelines and their statuses (stages) in the connected Kommo account — values for pipeline_config. Read-only.

Users of the connected Kommo account — values for pipeline_config.responsible_user_id. Read-only.

Creates a campaign-ready audience from a marketplace set and returns its audienceId. Signals sets SPEND CREDITS (a fresh snapshot is bought, price per contact; it also appears in My Audiences); people sets are free. Does NOT contact anyone. Next: `create_campaign` with the audienceId, then `preview_launch_campaign`. Only call after the user approved `preview_launch_audience_set`.

Start (or resume a paused) campaign exactly like the app: starts email sending and queues LinkedIn on the selected (or all connected) accounts. Contacts receive REAL outreach in the working hours; credits are spent as messages go out. Only call AFTER the user reviewed preview_launch_campaign and approved it. Returns the campaign plus linkedin_activation.

Mark every in-app notification of the caller as read (clears the badge).

Mark one in-app notification as read.

Personal email/in-app preferences: email_notifications, in_app_notifications, meeting_reminders, credit_alerts, analytics_emails_enabled. Read-only.

Turn personal notifications on/off. Turning them off means the human stops being alerted (e.g. low credits, meetings) — confirm with the user first.

Pause a running campaign across every channel. Reversible — call `launch_campaign` to resume.

Pause a single channel (email, linkedin, phone_call, voice_call) on a running campaign. Other channels keep going.

Turn a READY custom audience into a campaign audience and return its id ({ id, name, stats }) — pass it as audienceId to `create_campaign`. Sends nothing, no credits. The "Launch campaign" button of My Audiences.

Generate emails for every contact ahead of sending (legacy company-based audiences only; people/custom-audience campaigns prepare automatically after launch). Can take minutes. Nothing is sent. No credits.

Retry the SMTP/IMAP connection of a mailbox in status error and refresh its status. No credits.

Re-authenticate a LinkedIn account whose session died. Creates a NEW account id upstream: past outreach stays attached to the old id, so per-account history can look empty afterwards and running campaigns may need re-pointing. Only call after the user reviewed `preview_reconnect_linkedin_account` and approved.

Send the email to the contact now. REAL email. Only after the user approved preview_reply_in_campaign_thread. Consider takeover_campaign_thread first so the AI stops answering.

Send the reply immediately in the lead's thread (bypasses daily limits). REAL email. Only after the user approved the exact text from preview_reply_to_campaign_email.

List the pages of a website (path, title, description, keywords) for this agent — used by the page-navigation feature. Costs 2 credits. Read-only for the agent (nothing saved).

Crawl a website's structure (sitemap, top pages) BEFORE creating an agent. Useful when deciding which company to set on the agent. Costs ~2 credits.

Plan, status (ACTIVE/CANCELLED/PAST_DUE/EXPIRED/TRIALING), period dates, currency, amount, Stripe IDs.

Base + purchased extra agent slots. Useful to check "can I create another agent?" before calling `create_agent`.

Stop the AI from replying in this conversation; a human continues (reply_in_campaign_thread). Nothing is sent.

Stop the AI from messaging this LinkedIn contact (outreach id from list_campaign_linkedin_outreach or list_linkedin_conversations); pending auto-replies are cancelled. Nothing is sent.

Create (or return the existing) private, unlisted test page with this website widget installed, to try it before adding it to a real site. Only the agent's creator can do this. Free.

HTML to paste on a site for a channel: website widget (settings load from the server), website button (style it here: text, colours, radius, size — not stored server-side) or Slide Presenter (also the direct link). Read-only.

Archive the campaign: status becomes completed, all its outreach stops and it is hidden from the default lists (history stays readable with include_archived). Not reversible. Only call after preview_archive_campaign and the user's explicit approval.

List the CAMPAIGN audiences (filter-based, attachable to campaigns) of this workspace. Uploaded / purchased / CRM-built lists ("My Audiences") are listed by `list_custom_audiences`. Read-only, free.

SPENDS CREDITS (2 per contact). Purchases the set and snapshots its contacts into the workspace. Only call after the user reviewed `preview_buy_audience_set` output and explicitly approved the cost.

List classic Sales Process campaigns with status and live stats. Archived campaigns are hidden unless include_archived=true. Read-only.

The workspace's own connected mailboxes (status connecting|warming|ready|error|disconnected, warm-up reputation, last error). Capacity ≈ 50 emails/day per READY box. Used when settings.emailSenderMode=client_owned (classic campaigns and SDR). Read-only.

Mark the conversation closed (no more AI replies). Nothing is sent.

LinkedIn / Instagram accounts connected for publishing posts (Settings → Social), with status. Read-only.

Recording URLs (WAV), duration and start time of the voice calls in one widget conversation (up to 10 calls). Read-only.

Read the company website + LinkedIn and extract description, team, employee count, contacts, social links and pricing. Costs 15 credits, takes 60-180 s. With persist=true (default) the result is SAVED like in the app: company_description replaced, team/contacts/social/pricing stored (creates company + people records, fills blank contact channels). Waits up to ~200 s; if still running it returns a job_id — then call get_agent_job. Only call after preview_deep_scan and the user's approval.

SPENDS CREDITS: starts background enrichment (email, phone, LinkedIn, WhatsApp lookups) of the not-yet-enriched contacts — 1 credit per contact actually enriched, charged as it runs. Only call after the user approved `preview_enrich_custom_audience`. Then poll `get_custom_audience_enrichment`; stop with `stop_custom_audience_enrichment`.

Download every contact of a custom audience as CSV text (filename, total_rows, csv). Can be large. Read-only, free.

Sends a REAL invitation email (link valid 7 days). Admins only. Only call after the user approved preview_invite_workspace_member.

List of Stripe invoices (paid + open). Optional year/month scope.

Google Meet meetings of all your agents in a date range (default: next 7 days, max 62 days) — title, time, link, organizer, attendees, status, agent, has transcript. Read-only.

The planner layer of the calendar page: campaign and SDR sending windows per day and channel (paused flag, planned today, sent today) with campaign/search info, for an ISO date range (wide ranges are capped; `range` says what was materialised). CRM events: crm_list_calendar_events. Read-only.

List of public plans + add-ons (Extra Agent Slot, SDR sender pair, etc.) with prices. Optional currency filter (USD/GBP/EUR); omitted = every currency. Read-only.

Change who owns a lead (the new owner gets a CRM notification). Call `crm_list_workspace_members` first to get a valid user id — passing an unknown id fails. Write operation, no credit cost.

Re-apply the bot's commands and menu button (for private and group chats) — use when the bot menu looks wrong. Free.

People who signed up through the caller's referral links (masked email, link, signup date, free/paying, revenue and commission). Read-only.

Fetch the latest reply text for an email from the sending provider (when a reply shows as empty). No credits, nothing sent.

Rename a custom audience. Reversible, no credits.

Resume a paused channel on a campaign.

Catalogue of voices that can be assigned via `set_agent_voice`. Read-only.

Put prepared emails that failed validation/generation back in the queue (max 3 attempts each). Nothing is sent.

Spread all ready prepared emails over the campaign's working-hour slots; they are then SENT for real automatically. Only after the user approved preview_schedule_campaign_delivery.

Sending addresses available to this workspace (Vendo managed pool + own mailboxes) with warm-up level, daily limit and status; summary.emails_per_day_ready = capacity in managed mode. Managed senders require a paid plan to launch (summary.paid_plan). Use ids in settings.senderEmailIds. Read-only.

Create/update the agent's Voice Call channel like the app: attach one of YOUR numbers (list_phone_numbers), objective, script (generated if omitted), greeting, voice, pace, emotion, language, rules, inbound calls on/off, background sound, silence/reminder timings. Creates the phone voice agent at the provider and links the number (with accept_incoming the number starts answering real calls). Takes up to ~1 min. Free to set up; calls cost 25 credits/min. Only call after preview_setup_phone_agent and the user's approval.

Stop an in-progress enrichment after the current contact (stops further spending). Already-enriched contacts stay enriched and charged.

Currencies Vendo bills in (code, symbol, name) and the account's own billing currency. Read-only.

Pull the latest sent/opened/clicked/replied/bounced counters from the sending provider and store them. Max once per minute per campaign. No credits.

Send a message to the agent and get its reply using its current script — a text test, nobody is contacted. Needs a generated script. Use history for a multi-turn test.

Create a custom audience from a CSV/XLSX/XLS/TSV/TXT file given as base64 or an https URL. Parsing runs in the background: poll `get_custom_audience` until status is "ready". No credits (enrichment is a separate, paid step).

All voices for the website widget, Slide Presenter and Telegram voice: engine, gender, accent, expressive support, Ukrainian support, recommended flag, preview audio. Read-only. Use a voice_id from here in set_agent_voice / set_presentation_voice / set_telegram_voice_settings.

WhatsApp accounts connected to your user (phone, name, status: connecting / ok / error / credentials / stopped). Account-level: auto-replies use your latest campaign's agent. Read-only.