Panda Video MCP Server

by pandavideo Your server? Claim it

answering

Panda Video is answering right now. Last checked 7 min ago. It exposes 216 tools. Last commit 5 Oct 2026.

Video hosting: upload, organize and configure videos, analytics, AI subtitles and Shorts.

Uptime history 33 days of history

33 days agonow

100.0%

Uptime 24h

91 of 91 checks

216

Tools

read from the server

527 ms

Response time

average over 24h

Stars

last commit 5 Oct 2026

What changed 123

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 23 October 2026. No other catalogue keeps this.

4 Nov 2 tool descriptions were rewritten panda_action_dub_folder_videos, panda_create_ai_dubbing

4 Nov 2 tools changed the parameters they ask for panda_action_dub_folder_videos, panda_create_ai_dubbing

3 Nov 4 tool descriptions were rewritten panda_add_videos_to_funnel, panda_delete_funnel, panda_get_business_rules and 1 more

29 Oct 11 tools appeared panda_confirm_ai_ebook_pdf, panda_create_ai_resource, panda_delete_ai_resource and 8 more

29 Oct 5 tool descriptions were rewritten panda_action_credit_preflight, panda_action_enable_ai_package_for_folder, panda_delete_ai_workflow and 2 more

29 Oct 2 tools changed the parameters they ask for panda_action_credit_preflight, panda_action_enable_ai_package_for_folder

28 Oct 9 tools appeared panda_encrypt_videos, panda_get_exclusive_playback, panda_get_hls_encryption_batches and 6 more

28 Oct 6 tool descriptions were rewritten panda_action_reencode_folder_videos, panda_action_set_allowed_domains, panda_action_set_anti_download and 3 more

28 Oct 4 tools changed the parameters they ask for panda_action_reencode_folder_videos, panda_action_set_allowed_domains, panda_reencode_video and 1 more

27 Oct 3 tool descriptions were rewritten panda_action_add_folder_videos_to_tutor, panda_add_tutor_videos, panda_update_ai_assistant_video_bindings

and 75 more, back to 23 October 2026

Nothing serious here today

Today is the operative word: we check Panda Video every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 7 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add mcp --transport http https://mcp.pandavideo.com/mcp

Settings → Connectors → Add custom connector, then paste this address

https://mcp.pandavideo.com/mcp

~/.codex/config.toml

[mcp_servers.mcp]
url = "https://mcp.pandavideo.com/mcp"

.cursor/mcp.json

{
  "mcpServers": {
    "mcp": {
      "url": "https://mcp.pandavideo.com/mcp"
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "mcp": {
      "type": "http",
      "url": "https://mcp.pandavideo.com/mcp"
    }
  }
}

Available tools 216

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

panda

panda_action_add_folder_videos_to_funnel

Deterministically resolve a funnel (by name or ID) and a folder, then add every CONVERTED folder video to the funnel (POST /funnels/add_videos). dry_run=true (default) previews the additions.

panda_action_add_folder_videos_to_playlist

Deterministically resolve a folder and an existing playlist (by name or ID), then append every CONVERTED folder video to the playlist after its current items. dry_run=true (default) previews the additions.

panda_action_add_folder_videos_to_tutor

Deterministically resolve an existing AI Tutor (by name or ID) and a folder, then bind every CONVERTED folder video to the tutor (PUT /assist-ai/update_assistant_video_bind/{id}). Additive: videos already bound stay as they are and nothing is unbound. Billing: each NEW video without a subtitle in the tutor's language gets a transcription, charged at ceil(minutes/5) credits per video (Gold/Enterprise plans outside trial get free transcriptions up to a daily limit); without enough credits the API refuses before binding anything. dry_run=true (default) previews the additions.

panda_action_apply_profile_to_folder

Deterministically resolve a player profile and a folder and link the profile to ALL videos of the folder in one call (sends folder_id, like the dashboard). Subfolders are not included; videos in any status (not only converted ones) also receive the profile. Videos with their own customized player lose that customization. The work is queued: the result is status 'executed' with api_status 'pending' — confirm later with panda_get_profile (videos_count). api_status 'ok' only means the API found no videos in the folder: nothing was changed. Free action (no credits). dry_run=true (default) returns a preview.

panda_action_apply_video_config_to_folder

Deterministically resolve a folder and apply per-video player config to every CONVERTED video (POST /player?type=video). Supports: default_subtitle (lang code or 'false'), default_audio (dubbing language code or 'false'), on_funnel, and the AI toggles questions/mindmap/abstract. Send only the fields you want to change. dry_run=true (default) previews the affected videos.

panda_action_apply_watermark_group_to_folder

Deterministically resolve a watermark/DRM group (by name or ID) and a folder, then add the folder to the group so all its videos (current and future) inherit the forensic watermark (PUT /drm/videos/{id} folders.increment). dry_run=true (default) previews.

panda_action_configure_folder_profile

Deterministically apply player-profile settings to every CONVERTED video in a folder, without touching videos outside it. Covers everything a profile holds: colors (Cores) incl. caption colors, captionsSize, controls incl. the big play button 'play-large' (Controles / Botão de Play Grande), VSL, save-progress, general (speed, theme, gear menu, offline) and availableQualities — pass any subset. Per video: its own (exclusive) profile is updated; a video on a SHARED or the default profile first gets its own copy of that profile (like the dashboard does), so the other videos of that profile do not change; a video without a profile gets a new one. Colors are merged with the current ones. dry_run=true (default) first VALIDATES each video and previews the plan — including which shared profiles end up with no videos — without changing anything.

panda_action_create_ab_test

Create an A/B comparison from 2+ videos (POST /comparison) and optionally start it immediately (PUT /comparison/{id}?type=start). dry_run=true (default) previews.

panda_action_create_folder_path

Deterministically ensure a nested folder path exists (e.g. 'Courses/2026/Module 1'), creating only the missing segments and returning the leaf folder ID. Idempotent: existing segments are reused. dry_run=true (default) previews which segments would be created.

panda_action_create_playlist_from_folder

Deterministically resolve a folder, create a new playlist, and add every CONVERTED video to it in folder order. dry_run=true (default) previews the playlist and its videos without creating anything.

panda_action_create_review_link_for_folder

Deterministically resolve a folder and create a review link for every CONVERTED video (POST /video-review/{id}?action=link). dry_run=true (default) previews the links that would be created.

panda_action_create_tutor_from_folder

Deterministically resolve a folder, estimate the credit cost via purchase_overview, and create an AI Tutor bound to every CONVERTED video in the folder. dry_run=true (default) returns the cost preview without creating anything.

panda_action_create_watermark_group_for_folder

Deterministically resolve a folder and create a new watermark/DRM group seeded with all its videos (POST /drm/videos). dry_run=true (default) previews the group and its videos.

panda_action_credit_preflight

Estimate the credit cost of running a paid operation (dub / subtitles / ai_package) across every CONVERTED video in a folder and compare it to the current balance — WITHOUT executing anything. ai_package = eBook + mind map + quiz in target_langs (default 1 language), 1 credit/min per resource per language, minus the free daily AI quota of an active Gold/Enterprise plan (1 use per video × resource); resources the videos already have aren't subtracted (panda_action_enable_ai_package_for_folder with dry_run=true gives the exact preview). Read-only; use before the real action to decide whether to proceed.

panda_action_delete_folder_videos

Deterministically resolve a folder and send every video inside it to the trash (30-day recovery). DESTRUCTIVE. dry_run=true (default) returns a preview of what would be deleted; set dry_run=false AND confirm=true to actually delete.

panda_action_dub_folder_videos

Deterministically resolve a folder, list eligible (CONVERTED) videos, estimate the dubbing cost in credits, and optionally create AI dubbing jobs for one or more target languages. dry_run=true (default) returns a preview without creating any job. standard mode (AI dubbing, HeyGen audio only) = 5 credits/min, lipsync = 14 credits/min, per language (minimum 1 min; a partial minute counts only past 1 s). Skips videos that already have the other dubbing technology (standard and lipsync can't be mixed) and, in lipsync, videos over 60 minutes. Each video follows its subtitles like the dashboard: targets already subtitled get audio only (DUBBING), the others TRANSLATION (source subtitled) or TRANSCRIPTION + dubbing. Stops at the first insufficient-credits (402) answer and lists the videos not attempted.

panda_action_duplicate_folder_videos

Deterministically resolve a folder and create a copy of every CONVERTED video inside it. Duplication only works for non-external, non-funnel videos (the API rejects others, surfaced per-video). dry_run=true (default) previews the affected videos.

panda_action_enable_ai_package_for_folder

Deterministically resolve a folder and generate AI package resources — eBook, mind map and/or quiz — for every CONVERTED video, one request per video × resource (POST /aiworkflow ABSTRACT | MINDMAP | QUESTIONS, like the dashboard). Default: the three resources in each video's own language. Resources a video already has in a language (or is still generating) are skipped. PAID: 1 credit per minute of video per resource per language (minimum 1 min; a partial minute counts only past 1 s); on an active Gold/Enterprise plan the free daily AI quota covers the first requests while it lasts (1 use per request). dry_run=true (default) returns the cost preview; execution is refused when the balance doesn't cover the cost.

panda_action_export_folder_analytics

Deterministically resolve a folder and aggregate per-video play analytics over a date range (GET /general/{videoId} on the analytics host). Read-only — returns a per-video breakdown and folder total. No dry_run.

panda_action_folder_ai_status

Deterministically resolve a folder and report the aggregate status of all its AI workflow jobs (subtitles, dubbing, AI package) via GET /aiworkflow?folder_id. Read-only — returns counts by status and by type. No dry_run (nothing is mutated).

panda_action_generate_shorts_from_folder

Deterministically resolve a folder and submit each eligible video (CONVERTED, 5min–5h) for AI Shorts generation (POST /shorts/import-video). Each job consumes Shorts processing. dry_run=true (default) previews eligible videos. DRM-protected videos are rejected by the API and surfaced per-video.

panda_action_generate_subtitles_for_folder

Deterministically resolve a folder, list eligible (CONVERTED) videos, estimate the AI subtitle cost in credits, and optionally generate subtitles in one or more languages. Tiers: essential (only en/pt-BR/es, 1 credit/30min), advanced (34 langs, 1 credit/5min), pro (34 langs, 1 credit/min). dry_run=true (default) returns a preview.

panda_action_move_videos_by_folder

Deterministically resolve a source and target folder and move every video from the source into the target in one call. Pass target_folder_ref='root' to move to the root (no folder). Skips videos already being deleted. Free action (no credits). dry_run=true (default) returns a preview of which videos would move.

panda_action_preview_storage_reduction

How much the invoice will be if the account reduces its ADDITIONAL storage — to a new total (target_total_gb) or by removing an amount (remove_gb), in GB (1 TB = 1024 GB). Without an amount, returns the current storage, what is in use and the smallest possible total. Refuses totals below what is already in use or below what the plan includes (plan storage only changes by changing plans). It never applies the change (that is done in the dashboard). dry_run=true (default) checks the new total against the plan and usage without calling billing; dry_run=false also gets the price from billing (same calculation as the dashboard cart: next invoice, next cycles, savings). Side effect of dry_run=false, same as opening the preview in the dashboard: if the account has a subscription but no default payment method, Panda's billing sets its first saved card as the default payment method.

panda_action_provision_user

Create a team user, resolving the role by name (or original_name/ID) to its role_id (POST /users). dry_run=true (default) previews. Validates the email format up front.

panda_action_reencode_folder_videos

Deterministically resolve a folder and re-encode every CONVERTED video with a given compression mode (no credit cost). Each video is processed again from its original file (backup): videos without the backup are refused and listed in failed. The current qualities are replaced by the re-encoded ones; encryption (HLS) is kept. dry_run=true (default) previews the affected videos.

panda_action_remove_subtitle_language_from_folder

Deterministically resolve a folder and delete a subtitle language from every CONVERTED video that has it (DELETE /subtitles/{id}). DESTRUCTIVE. dry_run=true (default) previews; set dry_run=false AND confirm=true to delete. Videos without that language are simply skipped by the API.

panda_action_rename_folder

Deterministically resolve a folder by name/ID/URL and rename it (PUT /folders/{id}). dry_run=true (default) previews the rename.

panda_action_request_folder_downloads

Deterministically resolve a folder and request an async download for every CONVERTED video (POST /download-async/{externalId}). Without quality, each video is requested at the highest quality it has; with a quality, videos that don't have it are skipped with the reason. Results list each video's status and `url` when it is already ready (temporary signed link); poll the others with panda_check_download_status. dry_run=true (default) previews the requests.

panda_action_schedule_lives

Create one or more scheduled live streams in a single call (POST /lives), optionally recording into a resolved folder. Defaults like the dashboard: region us, quality_package hd, save_vod true. Refuses trial accounts and quality above the plan's maximum. Without stream_key_id the account's default stream key is used. dry_run=true (default) previews the lives that would be created.

panda_action_set_allowed_domains

Add referer domains to the account's allow/block list for playback (POST /library/{id}?action=refer) and optionally turn domain protection on or off (block_none_refer). block_none_refer is applied first and rewrites the status of ALL the library's domains: true activates every domain (including ones turned off on purpose), false deactivates all of them and lets every request play; it is refused while a domain is still pending. With protection off, the new domains are created inactive. Resolves the library ID automatically. dry_run=true (default) previews.

panda_action_set_anti_download

Enable or disable account-wide anti-download protection (GET/PUT /block_download). Reads the current state first and only changes it if needed. Turning it on is only for plans that include it (Gold/Enterprise and others; Silver/Bronze need the "Anti-Download Simples" add-on, contracted in the dashboard; not available on Clipador/Clipper and VSL Only plans). Turning it off also turns Exclusive Playback off; a paid add-on stays billed until it is removed in the dashboard. dry_run=true (default) previews the change.

panda_action_set_custom_field_for_folder

Deterministically resolve a folder and set a custom metadata field (key/value) on every CONVERTED video (POST /videos/{id}?custom_fields). dry_run=true (default) previews the affected videos.

panda_action_set_default_subtitle_for_folder

Deterministically resolve a folder and set the default subtitle language on every CONVERTED video (POST /player?type=video). Pass language 'false' to clear the default. dry_run=true (default) previews the affected videos. Note: videos lacking that subtitle simply won't show it.

panda_action_set_folder_player_control

Enable or disable a single player control on every CONVERTED video in a folder, via player profiles, PRESERVING all other controls and without touching videos outside the folder. The big play button (dashboard 'Botão de Play Grande') is the 'play-large' control — disable it with control='play-large', enabled=false. Each video's controls are read-modify-written; when a profile has no explicit control list it inherits the global player controls, so the action materializes that global list minus/plus the control. A video on a SHARED or the default profile first gets its own copy of that profile (like the dashboard does); videos without a profile get one created and assigned. dry_run=true (default) validates + previews per-video changes, including which shared profiles end up with no videos.

panda_action_set_folder_videos_offline

Deterministically resolve a folder and enable or disable offline (mobile app) playback for every CONVERTED video inside it, in one batch call (POST /app). dry_run=true (default) previews the affected videos.

panda_action_set_forms_integration

Create or update a forms/CRM integration by service name. Reads existing integrations (GET /forms-integration/get); updates in place if the service already exists (PUT /forms-integration/update), otherwise creates it (POST /forms-integration/save). dry_run=true (default) previews.

panda_action_set_webhook

Idempotently set the account webhook URL. Reads the current webhook (GET /user/webhook); if a different one exists it is removed (DELETE /user/webhook/{id}) before creating the new one (POST /user/webhook). dry_run=true (default) previews the change.

panda_action_transfer_credits_to_subaccount

Resolve a subaccount by name or ID and transfer credits to it (POST /user/limit/transfer_credits). Checks the parent balance first. dry_run=true (default) previews the transfer.

panda_add_cta

Add a CTA (Call-to-Action) button to a video. Placement 'inside' = overlay on the video, 'outside' = below the video. Builds the same payload the dashboard's button editor sends.

panda_add_end_thumbnail

Upload an end thumbnail — an image shown after the video finishes. Provide `image_url` pointing to a publicly reachable JPG, PNG or GIF up to 5 MB. The upload also creates the end CTA, so the image shows in the player right away. A video has one end thumbnail: a new upload replaces the previous one. Returns {response: {endThumbnail: <name>}}.

panda_add_pause_thumbnail

Upload a pause thumbnail — an image shown when the viewer pauses the video. Provide `image_url` pointing to a publicly reachable JPG, PNG or GIF up to 5 MB. The upload also creates the pause CTA, so the image shows in the player right away, for the whole video. A video can have several pause thumbnails. Returns {response: {pauseThumbnail: [<thumb_name>]}} — keep that name: panda_delete_thumbnail needs it to remove this image. Time window and button overlay are edited in the dashboard pause-thumbnail editor.

panda_add_thumbnail

Upload the video cover (start thumbnail) — the image shown before the user presses play. Provide `image_url` pointing to a publicly reachable image (PNG/JPG/GIF); the tool downloads it and uploads as multipart to the Panda API. Replaces any existing start thumbnail. After this returns, the cover is active immediately for the player.

panda_add_tutor_videos

Add videos to a Tutor AI assistant. Additive: only videos not yet bound are added; videos already bound stay as they are and nothing is unbound (use panda_remove_tutor_video to remove one). Only CONVERTED videos: if any ID doesn't exist or isn't CONVERTED, the whole request is refused. Billing: each NEW video without a subtitle in the tutor's language gets a transcription, charged at ceil(minutes/5) credits per video (Gold/Enterprise plans outside trial get free transcriptions up to a daily limit); without enough credits the API refuses before binding anything.

panda_add_videos_to_funnel

Add one or more videos to a funnel with optional coordinates. Every call must mark exactly one video with is_first: true — it becomes the entry video. To add a video without changing the entry, also send the current entry video (from panda_get_funnel) with is_first: true.

panda_add_videos_to_playlist

Add videos to a playlist with order. Returns the updated playlist video entries [{video_id, playlist_id, order}].

panda_apply_profile_to_videos

Link a player profile to videos — pass video_ids OR folder_id (every video in that folder, any status; subfolders are not included). A video that had its own customized player (exclusive profile) loses that customization. Up to 5 video_ids are applied immediately; more videos, or any folder_id, are queued and return status 'pending' — confirm later with panda_get_profile (videos_count). Returns {status, message}.

panda_cancel_partial_deletion

Undo a partial deletion of ONE video before it is executed: the qualities/backup come back. Without qualities and backup, everything pending for the video is restored. Refused once the final deletion has started. Does not recover videos in the trash.

panda_check_download_status

Check the status of an async download request (same format/quality/language used in panda_request_download). Returns {status, url?} — `url` (a temporary signed link) is present when status is 'ready'.

panda_confirm_ai_ebook_pdf

Finish the PDF upload started with panda_get_ai_ebook_upload_url (kind=pdf): the PDF is checked (exists, not empty, up to 15 MB, valid PDF) and becomes the eBook of that language. With upload_success=false the uploaded file is discarded instead.

panda_confirm_tutor_file_upload

Confirm that a file was successfully uploaded to a Tutor AI assistant (call after uploading to the presigned URL)

panda_create_ai_assistant

Purchase credits and create a new AI assistant for a video. Returns the created {id, name, status, video_id}.

panda_create_ai_dubbing

Create an AI dubbing of a video into one target language. The path follows the video's subtitles, like the dashboard: target already subtitled → audio only (DUBBING, reuses that subtitle); source subtitled → TRANSLATION + dubbing; otherwise TRANSCRIPTION + dubbing (also creates the source subtitle). Costs 5 credits/min (standard AI dubbing, HeyGen audio only) or 14 credits/min (lipsync) per language; minimum 1 min, a partial minute counts only past 1 s. Refuses lipsync on a video that already has standard dubbing (and the inverse), lipsync over 60 min, and a balance below the cost. Returns {video_id, path, from_lang, to_lang, cost_credits, response} — response is the queued work (for TRANSCRIPTION, the transcription work; the dubbing work is created when it finishes).

panda_create_ai_resource

Create a quiz or mind map WITH CONTENT YOU PROVIDE (no AI, free) in a language that doesn't have one yet — the dashboard's "Add → Create New". Quiz: `questions` (1 to 10, 2 to 5 options each, correct ones marked) and optional `quiz_settings`. Mind map: `topics` (with optional subtopics), `mindmap_theme` (center; default the video title) and optional `mindmap_settings`. The eBook has no manual creation: generate it or upload a PDF (panda_get_ai_ebook_upload_url).

panda_create_comparison

Create a new A/B test. Needs at least 2 videos to start. Returns the created {id, name, status, video_ids}.

panda_create_custom_field

Create a custom metadata key-value field for a video (for tagging/categorization). Do NOT use this for chapters, subtitles, CTAs, or player settings — use the specific tools for those. Max 50 fields per video.

panda_create_folder

Create a new folder. Returns the created {id, name, parent_folder_id}.

panda_create_folder_refer

Add a domain referrer scoped to a single folder. type is ALLOW|BLOCK. The new row starts in 'pending'. A folder cannot have the same hostname twice. library_id is resolved automatically when omitted. On error the API returns { errCode, errMsg }.

panda_create_funnel

Create a new video funnel

panda_create_live

Create a new live stream event. Trial accounts cannot create lives. A quality_package above the plan's maximum is silently lowered to the plan's maximum. Without stream_key_id the account's default stream key is used; a key held by another live (online, provisioning, expired, waiting to start or scheduled within 24h) returns 400. Omitted fields use the API defaults (region us, save_vod true).

panda_create_playlist

Create a new playlist. Videos are REFERENCES — removing from playlist does NOT delete the video. Returns the created {id, name, description, access_type}.

panda_create_profile

Create a player profile (POST /profile) already configured — colors, controls, caption appearance (colors.captionsColor / captionsBackgroundColor + captionsSize), VSL, save progress, general (speed, theme, gear menu, offline) and availableQualities, all in one call. Send only what you want to set; the rest uses the player defaults. `name` is any label (3–100 chars). The new profile has no videos: link them with panda_apply_profile_to_videos. To make it the account default use panda_set_default_profile. Returns {id, name, isDefault}.

panda_create_refer

Add one or more library-level domain referrers. Each entry has a hostname and a type (ALLOW|BLOCK, default ALLOW). The same hostname cannot coexist as both ALLOW and BLOCK at the library scope (duplicate check is type-agnostic). New rows start in 'pending' (when domain protection is active) or 'inactive'. library_id is resolved automatically when omitted. On error the API returns { errCode, errMsg }.

panda_create_stream_key

Create a new stream key for OBS or other streaming software. The account's first key becomes the default.

panda_create_user

Create a new user in the organization. Returns the created {id, name, email, role_id}.

panda_create_watermark_group

Create a new watermark group

panda_delete_ai_assistant

Delete an AI assistant

panda_delete_ai_resource

Delete ONE AI package resource of a video in one language (eBook, mind map or quiz) — cannot be undone: its content, PDF, images and the published file are removed, also for legacy resources. Same as the dashboard's Remove. Refused while it is still generating (checked before deleting; if that check fails nothing is deleted). Other languages and resources stay. To remove a failed generation card use panda_delete_ai_workflow.

panda_delete_ai_workflow

Delete an AI work record (e.g. a failed or queued transcription/dubbing card; a queued one is refunded). It doesn't remove what a finished work produced: to remove an eBook, mind map or quiz use panda_delete_ai_resource.

panda_delete_comparisons

Delete one or more A/B tests

panda_delete_cta

Delete a CTA from a video

panda_delete_dubbing_audio

Delete a dubbed audio track from a video

panda_delete_folder

Delete a folder by ID. WARNING: All videos and subfolders inside are also deleted (cascade). Goes to trash for 30 days.

panda_delete_folder_refer

Delete one or more folder-level referrers by id (batch). Duplicate ids are de-duplicated; if any id is missing the API returns 404, and if any referrer is library-level it returns 400 ({ errCode, errMsg }). Rows transition to 'deleting' and are removed asynchronously.

panda_delete_funnel

Delete a funnel by ID. WARNING: this is destructive. The funnel is removed and the videos inside it go to the trash for 30 days (restoring the funnel's folder brings them back; the funnel does not come back).

panda_delete_lives

Delete one or more live streams

panda_delete_playlist

Delete a playlist. Videos are NOT deleted — only the collection is removed.

panda_delete_profile

Delete a player profile. The default profile ('Padrão') cannot be deleted. A profile with no videos is deleted directly. A profile WITH videos needs `strategy` — ask the user which one: 'keep' = each video keeps its current look (gets its own copy of the profile's settings); 'migrate' = the videos move to `target_profile_id`. Up to 5 videos are processed immediately; more are queued (status 'pending') and the profile disappears once all videos are moved. If any video fails, the profile is NOT deleted.

panda_delete_refer

Delete one or more library-level referrers by id (batch). Each referrer must be library-level (folder_id=null) and belong to the library; otherwise the API returns 400 ({ errCode, errMsg }). Rows transition to 'deleting' and are removed asynchronously.

panda_delete_short

Delete a Shorts job/project

panda_delete_subaccount

Delete a subaccount

panda_delete_subtitle

Remove a subtitle from a video by language

panda_delete_thumbnail

Delete a thumbnail from a video (image and its player CTA). Type: 'start' (default, the cover), 'pause', 'end'. For 'pause', thumb_name is required and must be the exact file name — returned by panda_add_pause_thumbnail, or metadata.thumbId of the 'pause' CTA in panda_get_video_player_config. The tool checks the name against the video's pause thumbnails first and refuses (listing the existing names) when it does not match exactly.

panda_delete_tutor_file

Delete a file from a Tutor AI assistant

panda_delete_user

Remove a user from the organization

panda_delete_videos

Delete one or more videos by ID. Sends to trash for 30 days.

panda_delete_watermark_group

Delete a watermark group

panda_disable_auto_recharge

Disable auto-recharge for credits

panda_disable_watermark

Disable watermark protection for the account

panda_download_subtitle

Download a subtitle file for a specific language

panda_duplicate_profile

Copy a player profile's settings into a new profile named '<name> (2)', '(3)'… The copy has no videos and is never the default. Exclusive profiles (a single video's own player) cannot be duplicated. Returns {id, name}.

panda_duplicate_video

Create a copy of a video. Only works for CONVERTED, non-external, non-funnel videos.

panda_enable_auto_recharge

Enable auto-recharge for credits. When balance drops below trigger, recharges action_value.

panda_enable_watermark

Enable watermark protection for the account

panda_encrypt_videos

Turn on Encrypted Anti-Download (HLS encryption) on existing videos, 1–100 per call (one video works too). PAID in credits, per video: ceil(duration in hours × number of current qualities), e.g. a 10-minute video in 3 qualities = 1 credit; charged when the video is queued. Cannot be undone: there is no way to decrypt a video. Only for Gold/Enterprise plans or accounts with the 'Anti-Download Criptografado' add-on (checked before sending; otherwise refused). Videos already encrypted are left out (checked before sending) and listed in skipped as already_encrypted. Videos are also skipped without charge when still processing, with a pending partial deletion, without duration/qualities, not found, or when the credit balance doesn't cover them (insufficient_funds). Returns {idempotency_key, total, queued, skipped: [{video_id, reason}]}; follow the progress with panda_get_hls_encryption_batches. To encrypt future uploads automatically use panda_set_new_uploads_encryption.

panda_finish_comparison

Finish an A/B test and declare a winner. PERMANENT — cannot be reversed.

panda_finish_live

End a live broadcast

panda_generate_ai_resource

Generate ONE AI package resource of a video — eBook, mind map or quiz — in one or more languages, with its settings and extra instructions (same as the dashboard: Video Settings → Panda AI). PAID: 1 credit per minute of video per language (minimum 1 min; a partial minute counts only past 1 s), e.g. a 10-minute video in 2 languages = 20 credits. On an active Gold/Enterprise plan the free daily AI quota covers the whole request while it lasts (1 use per request, checked before sending). Languages that already have this resource, or are still generating, are skipped (listed in skipped); the balance is checked before sending. The resource is ready in a few minutes; follow it with panda_get_ai_workflows. Returns {video_id, resource, from_lang, to_langs, skipped, gross_cost_credits, cost_credits, free_by_daily_quota, response}; response is the queued request (its id isn't a work id: the works show up in panda_get_ai_workflows once processed). To redo an existing one use panda_regenerate_ai_resource.

panda_generate_ai_subtitles

Generate subtitles for a video using Panda AI. Creates a transcription in the specified language. Costs credits based on video duration and tier.

panda_generate_tutor_file_upload_url

Generate a presigned URL to upload a PDF/file to a Tutor AI assistant. Returns upload_url and file_id. After uploading, call panda_confirm_tutor_file_upload.

panda_get_account_analytics

Get general analytics metrics for the whole account. Returns {views, unique_viewers, watch_time_seconds, avg_watch_percentage, plays}.

panda_get_ai_assistant

Get an AI assistant's details. Returns {id, name, status, videos: [{id, title}], files: [{id, file_name}], answers_count}.

panda_get_ai_assistant_purchase_overview

Get credit cost overview before creating an AI assistant. Returns {credit_cost, current_balance, sufficient_credits}.

panda_get_ai_ebook_images

Images generated with AI in the dashboard's eBook editor for one eBook × language, with their status (QUEUED, PROCESSING, SUCCESS, ERROR), and how many free images that eBook still has (5 free per eBook × language, then 1 credit each). Generating images is done in the dashboard editor. Read-only.

panda_get_ai_ebook_upload_url

Get a temporary upload URL (valid 1 hour) to send a file of the eBook: kind=pdf — your own PDF as the eBook of a language that has no eBook yet (up to 15 MB); kind=logo — a PNG/JPEG logo for the eBook (up to 5 MB). The URL is a credential: don't show or share it. Send the file with an HTTP PUT to upload_url with the Content-Type header exactly as returned. Then: PDF → panda_confirm_ai_ebook_pdf; logo → pass logo_key in ebook_config of panda_update_ai_resource (existing eBook) or panda_generate_ai_resource. Your client must be able to send files over HTTP; otherwise use the dashboard (Video Settings → Panda AI → eBook).

panda_get_ai_resource_content

Read the CONTENT of one AI package resource of a video in one language: the quiz questions and options (correct ones marked) and its options, the mind map topics, or the eBook cover, style and chapters (with `chapter`, that chapter's text; the whole text when short). Also says whether the resource can be edited (legacy = generated by the old package, not editable; uploaded PDF eBook = no content). Read-only. Use before panda_update_ai_resource. To list which resources a video has use panda_get_videos_ai_resources.

panda_get_ai_workflows

Get every AI work of a video (subtitles, translation, dubbing, eBook=ABSTRACT, mind map=MINDMAP, quiz=QUESTIONS) with status (QUEUE, RUNNING, FINISHED, ERROR, SKIPPED). For the whole account or a folder, page by page, use panda_list_ai_works.

panda_get_auto_recharge_settings

Get auto-recharge configuration for credits. Returns {enabled, trigger_value, action_value}.

panda_get_bandwidth_analytics

Get bandwidth/traffic usage by folder, by video, or DRM by video. Returns array of {name, bandwidth_bytes, video_id?} entries.

panda_get_best_times

Which weekday and 2-hour slot the audience of the WHOLE account plays the most (or sees the player the most) in a period — "best time to publish". Weekday × 2-hour slot grid, summed over the period — the same grid as the dashboard heatmap (Analytics → Best times), with the hours exactly as Panda analytics stores them. Returns {start_date, end_date, metric, best_slots: [{weekday, hours, total}] (top 10), by_weekday, by_hours}. For specific videos or a folder use panda_get_best_times_by_videos.

panda_get_best_times_by_videos

Which weekday and 2-hour slot the audience of specific videos (or of every video in a folder) plays the most in a period. Weekday × 2-hour slot grid, summed over the period — the same grid as the dashboard heatmap (Analytics → Best times), with the hours exactly as Panda analytics stores them. An end_date of today counts only up to yesterday (the API clamps it). Returns {scope, start_date, end_date, metric, videos_count, best_slots: [{weekday, hours, total}] (top 10), by_weekday, by_hours, warnings}.

panda_get_business_rules

Returns the platform business rules: the real consequences of actions that modify, delete or move resources (e.g., deleting a folder or a funnel sends the videos inside to the trash for 30 days). Useful before planning such actions, so the advice given to the user matches how the platform actually behaves. Domains: funnels, videos_and_folders, video_upload, embed_and_share, player_settings, cta_interactions, playlists, drm_watermark, comparisons_ab_tests, lives, shorts, anti_download_and_domains, credits, thumbnails_and_subtitles, trash_and_recovery, analytics, tutor_ai_assistant, webhooks, review_timeline, subaccounts, billing_and_plans, member_get_member, organization_and_accounts.

panda_get_credits_balance

Get the current credits balance for the account. 1 credit = R$1.

panda_get_credits_history

Get credits transaction history for a date range. Returns {balance, history: [{id, type, amount, status, description, created_at}]}.

panda_get_custom_fields

Get all custom fields for a video. Returns array of {id, key, value} metadata pairs.

panda_get_exclusive_playback

Whether Exclusive Playback is on (on-demand videos only play in the Panda Player). Returns {status}.

panda_get_folder

Get a folder's details and one page of its videos. Returns {id, name, parent_folder_id, status, videos: [...], pagination: {page, limit, total_count, total_pages, has_next, has_prev}}. Only videos directly in this folder; subfolders are not included (use panda_list_folders). To list every video of a large folder, keep calling with page+1 while pagination.has_next is true. Default 20 videos per page, max 20.

panda_get_funnel

Get a funnel's details and its videos. Returns {data: {id, name, videos: [{id, title, status, is_first}]}}. Funnels are NOT folders.

panda_get_hls_encryption_batches

Progress of encryption batches started with panda_encrypt_videos. With idempotency_key: that batch; without it: every batch not finished yet (including failed videos). Each video: {video_id, status, state, updated_at}; state is pending, in_progress, processed, failed or cancelled. estimated_completion_minutes estimates the whole encryption queue (all accounts), not only your batch, and may be 0 when unknown.

panda_get_library_qualities

The account's quality settings (dashboard: Settings > Qualities). Returns {encoding, playback, compression_mode, compression_label, keep_original_files}: encoding = "Conversão de Novos Uploads" (qualities new uploads are converted to); playback = "Reprodução de Todos Vídeos" (qualities the player offers, on every video, when converted in that quality); compression_mode = "Compressão de Novos Uploads", shown as compression_label (size = Econômica, balanced = Equilibrada, quality = Maior qualidade); keep_original_files = "Backup do Arquivo Original de Novos Uploads".

panda_get_live

Get details of a specific live stream. Returns {id, title, status, scheduled_at, stream_key, rtmp, live_hls, created_at}. Status: provisioning (channel starting), offline (waiting for signal or scheduled), online, finishing, finished, finished_imported (recording became a video), expired (no signal in time; can be regenerated). stream_key is a secret credential: show it only when the user asks for it (e.g. to set up OBS).

panda_get_live_viewers

Get viewer history for a live stream. Returns time-series array of viewer counts.

panda_get_new_uploads_encryption

Whether new uploads are encrypted automatically (Encrypted Anti-Download / HLS encryption for future videos). Returns {library_id, status}.

panda_get_plan_usage

Get the current billing cycle usage and plan limits. Returns {start_period, end_period, plan_name, is_trial, storage, storage_plan, traffic, traffic_plan (all MB), play, play_plan, live, live_plan, live_count}. live = live minutes used this cycle (whole account, all regions); live_plan = free live minutes informed in the plan; live_count = lives in the cycle. Live minutes above live_plan are billed per minute by region and quality: see panda_get_subscription → addons.live. Trial accounts (is_trial) cannot create lives.

panda_get_player_config

Get global player configuration (applies to all videos without a custom profile)

panda_get_playlist

Get details of a specific playlist. Returns {id, name, description, videos_quantity, access_type, creator_name, duration, updated_at}.

panda_get_playlist_videos

List all videos in a playlist. Returns array of {id, video_id, order, video: {id, title, duration}}.

panda_get_profile

Get one player profile with all its settings: controls, colors (incl. caption colors and captionsFontSize), vsl, saveProgress, hideControlsOnStart, general (speed, theme, gear menu, offline, caption size), availableQualities, is_default and feature_tags.

panda_get_ranking_analytics

Get ranking analytics for the account. Returns {most_watched: [{video_id, title, watch_time}], most_played: [{video_id, title, plays}]}.

panda_get_realtime_analytics

Get the real-time snapshot of the account: how many viewers are watching now and on which devices. Returns {total_users, devices: {mobile, desktop, others}, geojson} — geojson (the dashboard map clusters) comes empty in this account-wide snapshot; no per-viewer data (IP, browser) is returned.

panda_get_referrals_summary

Get referral program summary (balance, estimated value)

panda_get_retention_analytics

Get audience retention analytics (account-wide or per video). Returns array of {percentage, viewers} showing drop-off at each point.

panda_get_subscription

Get current subscription/plan details. Returns {subscription_id, subscriptions: {name, status, active}, currency, addons}. addons.live lists live minutes billed above the plan's free minutes, per region and quality (quantity in minutes, unit_amount in cents); the plan's max live quality is subscriptions.metadata.live_max_quality.

panda_get_subtitle_by_language

Get a subtitle file for a specific language

panda_get_subtitles

Get all subtitle information for a video

panda_get_thumbnails

Get the cover (start thumbnail) of a video. Returns {response: {active, default}}: active = the uploaded cover in use (absent when none was uploaded), default = the automatic thumbnails generated from the video. Pause and end thumbnails are NOT listed here — they are CTAs in the video's player config (panda_get_video_player_config → ctas with type 'pause' / 'end').

panda_get_unwatched_videos

List the account's videos that had NO access at all in a period (the inverse of the ranking). Whole account only. Only videos that already existed on start_date are considered. Returns {start_date, end_date, data: [{id, video_external_id, title, created_at}], pagination: {limit, offset, total_unwatched, has_more}, coverage: {partial_coverage, missing_days}} — when partial_coverage is true, a listed video may have had access on the missing days.

panda_get_video

Get full properties of a video by its ID, including video_external_id, config (config.ctas holds the pause/end thumbnail CTAs), profile, status, duration, folder, subtitles, etc.

panda_get_video_analytics

Get analytics metrics for a specific video. Returns {views, unique_viewers, watch_time_seconds, avg_watch_percentage, plays}.

panda_get_video_player_config

Get per-video player configuration (chapters, CTAs, pixels, redirect, AI features, retention markers, subtitle default, offline config)

panda_get_videos_ai_resources

Which AI Package resources (e.g. eBook, quiz, mind map; one entry per type and language) up to 100 videos already have, in one call. Subtitles and dubbing are not included. Each item: {id, ai_resources: [{type, srclang}]} (type: abstract = eBook, mindmap, questions = quiz). A video that only has resources from the old AI package (legacy) comes back with an empty list here; panda_get_ai_resource_content shows them. No titles (use panda_get_video or panda_list_videos). IDs that don't exist or aren't yours come back in not_found. Returns {videos, not_found}.

panda_get_videos_count

Get total video count by status (CONVERTED, CONVERTING, DRAFT, etc.)

panda_get_videos_status

Processing status of up to 100 videos in one call. Each item: {id, status, available_resolutions, pending_resolutions, encoding_resolutions, playable, conversion_percentage, estimated_time, ...}. No titles (use panda_get_video or panda_list_videos). IDs that don't exist or aren't yours come back in not_found. Returns {videos, not_found}.

panda_get_viewers_by_videos

Who watched specific videos (or any video of a folder) in a period: distinct viewers, identified by IP. The IP is returned MASKED (a.b.x.x) — the full list is in the dashboard (Analytics → Users). The selection only chooses WHICH viewers appear: each viewer's metrics (play, view, watch_time) cover the whole account, not only these videos. Returns {scope, start_date, end_date, total_viewers, viewers: [{viewer_ip, play, view, unique_play, unique_view, watch_time_seconds, videos_watched}] (most plays first), warnings}.

panda_get_watermark_group

Get a watermark group's details. Returns {id, name, video_ids: [], folder_ids: [], created_at}.

panda_get_watermark_status

Check whether watermark/DRM is currently active on the account. Returns {active: boolean}.

panda_help_get_article

Get the full content of a specific Panda Video help center article by slug. Use this after searching to read the complete content of an article. The response is the full official documentation.

panda_help_search

Search Panda Video help center articles to answer user questions. Searches through ALL 146 pre-indexed articles from the official help center (https://help.pandavideo.com/pt-br/). Use this tool whenever the user has a QUESTION about how Panda Video works, pricing, features, integrations, configuration, etc. DO NOT use this for API execution commands — only for knowledge/support questions. IMPORTANT: Base your answer EXCLUSIVELY on the article content returned. Do NOT infer, assume, or use external knowledge.

panda_import_video_for_shorts

Import a video for AI shorts generation. Sources: library (video_id), youtube (source_url). Default config: vertical aspect, 30-60s duration, no captions. Video must be CONVERTED, 5min-5hrs, <50GB, no DRM.

panda_list_ai_assistants

List all AI video assistants. Returns array of {id, name, status, videos: [{id, title}], created_at}.

panda_list_ai_works

List the account's AI works (subtitles, translations, dubbing, lipsync, eBook=ABSTRACT, mind map=MINDMAP, quiz=QUESTIONS) page by page, newest first, with status (QUEUE, RUNNING, FINISHED, ERROR, SKIPPED). Only the latest attempt of each video × type × language. Filters: status, updated_since, video_id, folder_id (the API doesn't filter by type). Read-only. Returns {works: [{id, video_id, type, status, from_lang, to_lang, credits_charged, created_at, updated_at}], page, pages, total}.

panda_list_comparisons

List all A/B test comparisons. Status: DRAFT → IN_PROGRESS → COMPLETED. Returns array of {id, name, description, status, videos: [], winner_video_id, created_at}.

panda_list_folder_refer

List the domain referrers set directly on a folder. Returns { refers: [{ id, url, type, status, origin: { type, id } }] }. library_id is resolved automatically when omitted.

panda_list_folder_refer_inherited

List the effective referrers that apply to a folder using override-total semantics: the folder's own referrers if it has any, otherwise the library-level referrers. Use this to know which domains actually gate playback for videos in the folder. Returns { refers: [{ id, url, type, status, origin: { type, id } }] }. library_id is resolved automatically when omitted.

panda_list_folders

List all folders. Returns array of {id, name, parent_folder_id, status, created_at, videos_count}.

panda_list_funnels

List all funnels. Returns {data: [{id, name, videos_count, created_at}]}. A funnel with videos_count=0 has no videos. Funnels are NOT folders.

panda_list_hls_encrypted_videos

List the account's videos that are already encrypted (HLS). Videos still in an encryption batch only show up when it finishes (see panda_get_hls_encryption_batches). Returns {total, page, limit, pages, videos: [{id, title, status, folder_id, encrypted_at, available_resolutions, ...}]}. Default 25 videos per page, max 50; keep calling with page+1 while page < pages.

panda_list_invoices

List all invoices. Returns array of {id, status, amount_due, amount_paid, created, due_date, invoice_pdf, hosted_invoice_url}.

panda_list_lives

List all live streams. Returns array of {id, title, status, scheduled_at, region, quality_package, save_vod, stream_key_id, stream_key, rtmp, live_player, created_at}. Status: provisioning (channel starting), offline (waiting for signal or scheduled), online, finishing, finished, finished_imported (recording became a video), expired (no signal in time; can be regenerated). stream_key is a secret credential: show it only when the user asks for it (e.g. to set up OBS).

panda_list_notices

List the notices the Panda team sent to the account (tips, alerts, news) — the ones shown in the dashboard notice card and Notifications panel. Only the account owner and admins have notices: any other user gets an empty list (not an error). Status: 'sent' = unread, 'read' = dismissed, 'completed' = the user already acted on it (clicked its button). Returns up to 100 [{id, notice_type, title, text, primary_button, secondary_button, status, created_at, read_at, completed_at}].

panda_list_partial_deletions

List pending removals that can still be undone. type 'partial' = qualities/backup removed with panda_request_partial_deletion (cancel with panda_cancel_partial_deletion); 'video' = whole videos in the trash; 'all' (default) = both. Returns {retention_days, partial_deletions, pagination}.

panda_list_plans

List available subscription plans and pricing

panda_list_playlists

List all playlists. Returns array of {id, name, videos_quantity, duration, access_type, updated_at}.

panda_list_profiles

List the account's player profiles (GET /profile). 'Profiles' are player UI configs, not user accounts. Returns an array of {id, name, pullzone_name, is_default, updated_at, videos_count, feature_tags, colors, availableQualities}. The default profile ('Padrão') has is_default=true. Exclusive profiles (a single video's own customized player) are NOT listed. Use panda_get_profile for a profile's full settings. No pagination.

panda_list_refer

List the library-level domain referrers (Domain Protection / allow-block list for playback). Returns { refers: [{ id, url, type, status }] } where type is ALLOW|BLOCK and status is one of active|inactive|pending|deleting|turning_inactive. library_id is resolved automatically when omitted.

panda_list_refer_all

List all of the library's domains consolidated by hostname across library and folder scopes. Returns { refers: [{ hostname, type, status, scope, library_refer_id, folders, type_inconsistency, created_at }] }. scope is library|folder|mixed; status may be 'mixed' when rows differ; library_refer_id is the library-level row id (null if folder-only); folders is an array of { folder_id, name, refer_id, status }; type_inconsistency=true when the same hostname has divergent ALLOW/BLOCK rows. Referrers with status=deleting are ignored. library_id is resolved automatically when omitted.

panda_list_short_segments

List all generated segments (clips) for a Shorts job. Each segment has viralScore, duration, transcription.

panda_list_shorts

List all Shorts jobs. Projects expire after ~30 days. Returns array of {job_id, status, user_context: {video_title, source_type}, completed_segments, created_at}.

panda_list_stream_keys

List all stream keys for live broadcasting. Returns array of {id, title, region, default, stream_key, in_use, in_use_by: {live_id, title, status}, created_at}. A key is held (in_use) by a live that is online, provisioning, expired, waiting to start or scheduled within 24h; an expired live holds it until regenerated or deleted. stream_key is a secret credential: show it only when the user asks for it (e.g. to set up OBS).

panda_list_subaccounts

List all subaccounts and their usage limits. Returns array of {organization_id, name, status, credits_balance, storage_used, limits}.

panda_list_users

List all users in the organization. Returns array of {id, name, email, role_id, role_name, created_at}.

panda_list_videos

List videos. Each video has: id, video_external_id, title, status, created_at, length (seconds), folder_id, config. `id` is what most tools take as video_id; video_external_id is what panda_get_best_times_by_videos / panda_get_viewers_by_videos take. Results are returned newest first by default. There is NO server-side date filter or sorting — to find videos created on a specific date, fetch videos and check created_at in the response.

panda_list_watermark_groups

List all watermark groups. Returns array of {id, name, active, video_ids: [], folder_ids: [], created_at}.

panda_manage_drm_group_items

Add or remove videos and/or folders from a DRM watermark group. Returns the updated group with current video_ids and folder_ids.

panda_move_videos

Move one or more videos to a folder

panda_reencode_video

Re-encode a video with a compression mode (no credit cost). The video is processed again from its original file (backup): without the backup the API refuses. Its current qualities are replaced by the re-encoded ones and it stays in processing until done. Encryption (HLS) is kept. To encrypt videos use panda_encrypt_videos.

panda_regenerate_ai_resource

Generate AGAIN an existing AI package resource of a video in one language — PAID and cannot be undone: the current one is deleted first, including every edit made to it. Cost: 1 credit per minute of video (minimum 1 min; a partial minute counts only past 1 s); free on an active Gold/Enterprise plan while the daily AI quota lasts (checked before sending). Without new settings it reuses the previous ones. Refused while the resource is still generating, for uploaded PDF eBooks, or when the balance doesn't cover it. Also the way to make a legacy (old package) resource editable. Returns {video_id, resource, lang, gross_cost_credits, cost_credits, free_by_daily_quota, response}; response is the queued request, and while it generates the resource is missing from the video.

panda_regenerate_live

Regenerate an expired live so it can be broadcast again. Only works when status is expired (otherwise 400 with the current status). Keeps the same stream key, but the RTMP server may change: update it in OBS. Start broadcasting within 15 minutes or the live expires again. Returns {id, status: provisioning, stream_key, stream_key_id, rtmp, region, started_at}. stream_key is a secret credential: show it only when the user asks for it (e.g. to set up OBS).

panda_remove_tutor_video

Remove ONE video from a Tutor AI assistant: the tutor stops using it and its knowledge is deleted from the tutor. The video stays in the library. Refused when the video isn't bound to the tutor, when it is the tutor's last video (use panda_delete_ai_assistant to delete the tutor), and while the video is still being processed by the tutor (queued/processing — try again when it finishes). Returns {assistant_id, video_id}.

panda_remove_video_from_playlist

Remove a video from a playlist. Does NOT delete the video.

panda_remove_videos_from_funnel

Remove one or more videos from a funnel. The videos leave the funnel and go to the library root — they are not deleted (the dashboard deletes them in a second call; this tool does not).

panda_request_download

Request an async download for a video. Only works for CONVERTED, non-external, non-Hotmart videos. Returns {status, url?}: when status is 'ready' the response already has `url` (a temporary signed link); otherwise poll panda_check_download_status with the same format/quality/language. Lipsync dubbing is a separate video: to download it, pass the video_external_id of that language's entry in config.lipsync_info[] (panda_get_video) and language = that language.

panda_request_partial_deletion

Remove some qualities and/or the original file (backup) of ONE CONVERTED video to free storage, keeping the video. The removed items disappear right away and are deleted for good after retention_days (30); until then panda_cancel_partial_deletion restores them. Videos from an external source are refused. Refused when it would leave the video with no quality: the API would send the whole video to the trash instead — use panda_delete_videos to delete a video. Returns {retention_days, action, remaining_qualities, ignored, partial_deletion}.

panda_restore_profile

Reset a player profile to the account's global player settings (panda_get_player_config): controls, colors, VSL, general, save progress, hideControlsOnStart and availableQualities are all replaced — this also drops the profile's theme, gear menu, caption size and offline settings unless the global has them. Changes every video linked to the profile. Returns the restored profile.

panda_save_segment_to_library

Save a Short segment to the video library as an independent video

panda_set_ai_resource_download

Allow or block viewers from downloading a video's eBook, mind map or quiz (the dashboard's "Allow download"). Applies to every language of that resource. Free.

panda_set_block_none_refer

Turn the library's domain protection on or off (block_none_refer). false = protection OFF for the whole library: every request plays, with or without a referer, and even BLOCK domains are ignored. true = the ACTIVE domains apply: requests without a referer are blocked (native TV/iOS players excepted), with ALLOW domains only matching referers play, with only BLOCK domains the matching referers are blocked; with no active domain nothing is blocked. WARNING: this also rewrites the status of ALL the library's domains (library and folders): true activates every domain, including ones turned off on purpose (to keep one off, deactivate it afterwards with panda_set_refer_status); false deactivates all of them. Refused (400) while any domain is still pending, deleting or turning inactive. The server recalculates the flag afterwards: it is true while at least one domain is active. On error the API returns { errCode, errMsg }. library_id is resolved automatically when omitted.

panda_set_default_profile

Make a profile the account's default player profile ('Padrão'). Exclusive profiles cannot be default. If the current default profile has videos, ASK the user what happens to them and pass unlinked_videos_strategy: 'apply-new' = they follow the new default; 'keep-current' = they stay with the current profile. Without it only the default flag changes and no video is touched. Video changes run in the background (videoMigrationQueued). Returns {message, id, videoMigrationQueued}.

panda_set_exclusive_playback

Turn Exclusive Playback on or off (dashboard: Security > Anti-Download > "Reprodução Exclusiva", Beta). When ON, the on-demand videos of the account are served only to the Panda Player: the Panda Player embedded by iframe keeps working on any site allowed by domain protection (members areas that use the embed included), while custom players, scrapers or extensions that open the HLS (m3u8) link directly get a decoy video. It deters casual capture; it is not DRM. Covers on-demand videos, Libras and the main audio; does not cover live streams, dubbed audio tracks, subtitles or downloads (they keep working). Requires the Simple Anti-Download to be ON (checked before changing; turn it on with panda_action_set_anti_download); turning Simple Anti-Download off turns Exclusive Playback off too. Turning on is only for plans that include Simple Anti-Download (Gold/Enterprise and others; Silver/Bronze need the "Anti-Download Simples" add-on, contracted in the dashboard; not available on Clipador/Clipper and VSL Only plans).

panda_set_new_uploads_encryption

Turn automatic encryption (HLS) of NEW uploads on or off. No credit cost. Turning on is only for Gold/Enterprise plans or accounts with the 'Anti-Download Criptografado' add-on (checked before changing; otherwise refused). Existing videos don't change: to encrypt them use panda_encrypt_videos (paid). Turning off only affects future uploads: videos already encrypted stay encrypted, and a paid add-on stays billed until it is removed in the dashboard.

panda_set_refer_status

Activate (active=true) or deactivate (active=false) a single referrer by refer_id. Activation moves inactive→pending; deactivation moves active→turning_inactive (the async worker finalizes the state). If the referrer is already in an intermediate state (pending|deleting|turning_inactive) the API returns 400 ({ errCode, errMsg }: 'Operation in progress, ...'). Works for both library- and folder-level referrers.

panda_set_video_offline

Configure offline playback for a video (mobile app feature)

panda_start_comparison

Start an A/B test (begin collecting data). Only from DRAFT status. Returns the updated comparison with status IN_PROGRESS.

panda_transfer_credits

Transfer credits to a subaccount

panda_update_ai_assistant

Update AI assistant information (name, status, etc.)

panda_update_ai_assistant_chat_visibility

Show or hide the AI chat widget on the video player

panda_update_ai_assistant_video_bindings

Bind videos to an AI assistant (Tutor). Additive: only videos not yet bound are added; videos already bound stay as they are and nothing is unbound (use panda_remove_tutor_video to remove one). Only CONVERTED videos: if any ID doesn't exist or isn't CONVERTED, the whole request is refused. Billing: each NEW video without a subtitle in the tutor's language gets a transcription, charged at ceil(minutes/5) credits per video (Gold/Enterprise plans outside trial get free transcriptions up to a daily limit); without enough credits the API refuses before binding anything.

panda_update_ai_resource

Edit an existing AI package resource of a video in one language, like the dashboard editor — free. Quiz: send `questions` (the WHOLE new list, 1 to 10 questions, 2 to 5 options each, read it first with panda_get_ai_resource_content) and/or `quiz_settings`. Mind map: `mindmap_edits` (replace an excerpt that exists in one topic only) and/or `mindmap_settings`. eBook: `ebook_edits` (replace an excerpt that exists once in the text), `cover` and/or `ebook_config` (style, logo); the eBook is then recomposed from its text (manual formatting done in the dashboard editor may be lost; images stay) and the new PDF is ready in about 1 minute. Legacy resources (old package) and uploaded PDF eBooks can't be edited. Returns {video_id, resource, lang, saved, changes}; read the result with panda_get_ai_resource_content.

panda_update_auto_recharge

Update auto-recharge settings

panda_update_cta

Update a CTA on a video. Only the fields you pass are changed; everything else keeps its current value. Placement cannot be changed — delete and re-add the CTA instead.

panda_update_folder

Update folder properties (name, parent). Also used to recover deleted folders with status=true.

panda_update_folder_refer

Edit one or more existing referrers (refer_ids) in a single call: rename the hostname, change the type (ALLOW|BLOCK), and/or move them between scopes. scope='library' makes the domain apply to the whole library (omit folder_ids). scope='folder' makes it apply to the listed folder_ids (required and non-empty, the backend computes the add/remove diff). All refer_ids must belong to the same hostname. Moving a folder domain to scope='library' recreates it as a library domain that starts 'pending' until it is active. Returns { message, hostname, type, scope, renamed, folders_added, folders_removed, refers }. On error the API returns { errCode, errMsg }. library_id is resolved automatically when omitted.

panda_update_funnel

Update a funnel's properties (rename)

panda_update_library_qualities

Change the account's quality settings (dashboard: Settings > Qualities); send only what changes. encoding ("Conversão de Novos Uploads"): qualities NEW uploads are converted to, each one using storage. playback ("Reprodução de Todos Vídeos"): qualities the player offers on ALL videos, including the ones already uploaded, when converted in that quality. compression_mode ("Compressão de Novos Uploads", NEW uploads): Econômica (size, smaller files), Equilibrada (balanced) or Maior qualidade (quality, larger files). keep_original_files ("Backup do Arquivo Original de Novos Uploads"): keep the original file of NEW uploads (uses storage; when off, downloads only offer the converted versions). Existing videos are not re-encoded (use panda_reencode_video). Not available on the Clipador/Clipper plan and needs the permission to change account settings (put-general-config); both are checked before changing.

panda_update_notice_status

Mark one notice as 'read' (default — same as dismissing it in the dashboard) or 'completed'. Use 'completed' ONLY when the user explicitly asks for it: in the dashboard it means the user did what the notice asked, and it is final (a completed notice never changes again). Nothing is deleted. Only the account owner and admins can mark notices. Get the id from panda_list_notices.

panda_update_player_config

Update the account's GLOBAL player (dashboard page Player): controls, colors, theme, caption color/background/size, resume from last position, gear-menu items, menu language and time display. Applies to every video WITHOUT a player profile — including videos uploaded later (they are born without a profile). Send only what changes; the rest is kept. Speed, autoplay and VSL options are NOT global: they live in each video's profile (panda_update_profile / panda_action_configure_folder_profile). Panda branding is not changed here (Settings → Panda Partner). Returns the saved config.

panda_update_playlist

Update a playlist's properties

panda_update_profile

Update a player profile's settings. Changes EVERY video linked to the profile. Covers: player colors (colors.primaryColor / controlsColor), enabled controls list, smart autoplay (vsl.smartAutoplay), VSL mode (vsl.disablePause / disableForward / alternativeProgress), playback speed (general.default_speed), save progress, theme and gear menu (general.theme / general.settingsControls), offline (general.video_offline_enabled…), availableQualities, and CAPTION APPEARANCE: text/background colors (colors.captionsColor / captionsBackgroundColor, hex with #, alpha allowed) and size by name (captionsSize: extra_small | small | normal | large | extra_large — use the user's word). Colors are merged with the current ones (only the colors you send change); general is merged too. controls, vsl, saveProgress and availableQualities REPLACE the current value — send the complete object/list. Do NOT use this tool for: chapters (use panda_update_video_config), subtitle generation (use panda_generate_ai_subtitles), thumbnails, or title/description (use panda_update_video).

panda_update_sign_language_display

Change how the sign language interpreter (Libras) window shows on a video's player: start time, size, position, autostart, or a free position/size. Only fields passed are changed. The interpreter clip itself is uploaded and removed on the dashboard (Video → Settings → Libras); this tool does not create or delete it. Choosing a preset size or position drops the free position (custom), like the dashboard. Returns the updated sign language entry.

panda_update_subaccount

Update a subaccount's settings (name, limits, status)

panda_update_subtitle_visibility

Show or hide a subtitle language (hidden subtitles are not visible but still indexable for search)

panda_update_user

Update a user's information or role

panda_update_video

Update basic metadata of a video: title, description text, or move to a different folder. Do NOT use this for player settings, chapters, subtitles, thumbnails, or any playback configuration — use the specific tools for those.

panda_update_video_config

Update per-video config (POST /player?type=video). Send only fields you want to change. Fields: chapters, default_subtitle, default_audio, redirect_video_id, custom_pixels, on_funnel, questions (AI quiz), mindmap (AI), abstract (AI ebook), retention_markers, ai. NOT for: controls, autoplay, Smart Autoplay, colors, speed, big play button, save progress — use panda_update_profile for those.

panda_update_watermark_group

Update a watermark group

panda_upload_video_from_url

Import a video from an external URL (YouTube, Vimeo, S3, generic HTTPS)

Endpoints

URL	Transport	State	Latency	Checked
https://mcp.pandavideo.com/mcp	streamable-http	answering	553 ms	7 min ago

Alternatives to Panda Video

same job, measured the same way

Youtube Creator

by wmarceau

YouTube automation: upload videos, Shorts, manage playlists, get analytics

85 installs/wk local only

QRCodeKIT

by qrcodekit

Branded short links, instant page & file hosting, and dynamic QR codes with unified analytics.

14 tools answering

RankReactor

by flagman5

Hosted RankReactor MCP: SEO articles, UGC video, keywords, analytics, and site audits.

answering

parcelLab

by parcellab

Configure parcelLab journeys, tracking pages and returns portals, and query delivery analytics.

answering

FindMe Photo

by findmephoto

Create wedding galleries, upload photos, and pull analytics on FindMe Photo from any AI assistant.

72 installs/wk local only

Picoli MCP

by amaterous

MCP server for picoli.site - URL shortening and click analytics for AI agents

50 installs/wk local only

Zype

by zype-mcp

Manage videos, playlists, analytics, and monetization for OTT streaming services.

67 installs/wk answering

Shortimize

by shortimize

Track TikTok, Instagram Reels and YouTube Shorts accounts and videos: views, growth and analytics.

32 tools answering

Panda Video — questions

Answers built from our own checks of this server.

What can Panda Video do?

It exposes 216 tools, read directly from the server on our last check. Among them: panda_action_add_folder_videos_to_funnel, panda_action_add_folder_videos_to_playlist, panda_action_add_folder_videos_to_tutor, panda_action_apply_profile_to_folder, panda_action_apply_video_config_to_folder, panda_action_apply_watermark_group_to_folder and 210 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →

Is Panda Video working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 527 ms. The bar chart above shows every period we have measured.

How do I connect Panda Video?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.

Does Panda Video need an API key?

No. Panda Video completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 216 of them are readable on this page. This is what we observed, not what the docs claim.

How fast is Panda Video?

It answers our handshake in 527 ms on average, which is faster than 22% of all working MCP servers we measure. That is on the slow side — worth knowing if the tool sits inside an interactive loop. The comparison comes from our own checks across the whole registry, every 15 minutes.

Is Panda Video open source?

The code is open source: it is published under the MIT licence and 0 stars on GitHub. The licence covers the code in the repository, not the hosted service at mcp.pandavideo.com, which runs on its operator's own terms.