mcpbeat

Recao MCP Server

app.recao/recao-mcp
answering

Recao is answering right now. Last checked 14 min ago. It exposes 17 tools. Last commit 12 Jul 2026.

Rank a competitor's EU App Store ads by longevity. From Apple's official Ad Repository.

Uptime history 41 hours of history · worst hour 0%
41 hours agonow
75.8%
Uptime 24h
69 of 91 checks
17
Tools
read from the server
338 ms
Response time
average over 24h
0
Stars
last commit 12 Jul 2026

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 14 min ago.

run in your terminal
claude mcp add recao-mcp --transport http https://recao.app/api/mcp
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "recao-mcp": {
      "url": "https://recao.app/api/mcp"
    }
  }
}
~/.codex/config.toml
[mcp_servers.recao-mcp]
url = "https://recao.app/api/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "recao-mcp": {
      "url": "https://recao.app/api/mcp"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "recao-mcp": {
      "url": "https://recao.app/api/mcp"
    }
  }
}

Available tools 17

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

memory
memory_index
List this account's company memory, one line per entry (name + description), newest first. Traverse index-first: scan this, then memory_recall(name) for full bodies. Memory accrues automatically from your competitor scans (exhaust) and from your own memory_note writes.
memory_note
Write (or update) a memory entry on this account: decisions, campaign outcomes, learnings. Use a short kebab-case name and a one-line description (that's the index line); details go in body. Your future sessions and Recao's weekly reports read this.
memory_recall
Read one memory entry's full body by name (get names from memory_index).
assemble
assemble_status
Check an assemble_video job by its job_id. Returns the status (processing, done, or error). When done, returns the final MP4 url, the aspect, clip count, total duration, and the booked cost in EUR. When it errored, returns the reason. Only jobs on your own account are visible.
assemble_video
Stitch rendered scene clips into one ad-ready MP4 with burned-in subtitles and crossfades. Pass 1 to 6 clips in order, each with its mp4 url, its duration in seconds (3 to 12), and an optional subtitle line to burn over that clip. Every clip is scaled and padded to the chosen aspect (9:16 default 1080x1920, 1:1 1080x1080, or 16:9 1920x1080). Optional intro and outro title cards: pass intro/outro as { text, duration_s? } to bookend the ad with a centred title card (1 to 5 seconds, default 2) that crossfades into the video; cards do not count toward the 6-clip limit. Assembly is our compute, so it carries a small flat fee (about 0.12 EUR), booked only when the file is produced, against your trust cap. Runs in the background over up to a couple of minutes and returns a job_id: poll assemble_status with it to get the finished MP4 url. Feed it the clips from clips_status (map each to url, duration_s, subtitle). Paid plans only.
generate
generate_avatar
Generate a UGC persona: your agent passes a persona brief (physical look plus vibe of one invented creator), and we return stills of that invented person plus an avatar_id. The persona brief anchors the same character in generate_clips takes, and the stills are the customer's reference artifact for the creative. Ask for up to 3; the default model returns a single strong base still, imagen and flux return the full set. Metered per generation; the price is shown in the response. Paid plans only.
generate_clips
Render UGC video scenes as ad-ready clips, metered per second of video (the estimate shows the exact price before anything renders). Pass 3 to 6 scenes (5 to 8 seconds each, one action per scene, spoken lines at most 20 words; empty spoken_line for silent characters). Consecutive scenes pack into single TAKES of up to 15 seconds, one generation each. HOW CHARACTER IDENTITY WORKS, read carefully: all characters are described in TEXT (avatar_id resolves to its persona brief; or write the persona field yourself, covering one character or a whole ensemble). The video model rejects every image that contains a person, so no photo can anchor a face. Text keeps a character IDENTICAL only WITHIN a take; ACROSS takes it preserves the look and styling but the exact face can drift, and neither avatar_id nor persona prevents that. Structure your script so scenes where the same character must be recognizably identical sit adjacent and fit one take (15s or less); treat cross-take appearances as different shots of a matching character, and review the result. reference_image_urls (up to 9 https images) keeps real products or props on-model in every take; these images must contain no people. Without confirm, it validates the contract and returns the per-scene price estimate in EUR, and makes nothing. With confirm=true it starts the metered render and returns a job_id: rendering runs in the background over a few minutes, so poll clips_status with that id to get per-scene clip URLs plus the uncut takes. Paid plans only.
app
search_app_advertiser
Search the Apple Ad Repository for apps or developers advertising on the EU App Store. Returns ids to use with get_competitor_ads. Start here with your competitor's app name.
clips
clips_status
Check a generate_clips render job by its job_id. Returns the status (processing, done, or error). When done, returns the finished clip URLs, the model used, and the booked cost in EUR. When it errored, returns the reason. Only jobs on your own account are visible.
competitor
get_competitor_ads
Get all Apple App Store ads a competitor has run (EU storefronts, up to 1 year back), with creative copy, placements, formats, and an inferred winner analysis: ads sorted by how long they've been running (longevity = the advertiser keeps paying = likely converting). Source: official Apple Ad Repository (DSA transparency data).
details
get_ad_details
Get full details and locale/creative variations for one specific ad (use adId from get_competitor_ads). Shows every language variant, creative asset URLs, and icon variations. Useful to see how a competitor localizes a winning ad.
playbook
get_playbook
Get a Recao GTM playbook: the go-to-market moves a solo app founder's agent runs, wired to the competitor data tools. Start with 'the-roadmap' (diagnoses the founder's stage and its binding constraint, then routes you to the right playbook). Call with no slug to list all playbooks.
roadmap
roadmap_status
Where the founder's agent starts its go-to-market work: diagnose which stage of the Recao Roadmap this account is in (S0 pre-launch to S4 scale), the binding constraint, and the playbook to run. Reads your scans and memory. Sharpen it: write a memory_note named 'company-stage' with your MRR band and funnel numbers, and this tool will use it.
sign
sign_up
Request a free Recao account for your human. This does NOT create an active account: it registers a PENDING one and emails your human an activation link; nothing works and no terms are accepted until they click it (the human accepts the terms at activation, not you). The API key in the response stays inert until then. Consent stays with the human, so calling this is a request, not a decision made for them: in an interactive session their approval of this tool call is the go-ahead; if you run autonomously, surface this step to your human instead of calling it. After activation, reconnect with header `Authorization: Bearer <key>`.
upgrade
upgrade
Get the checkout link to upgrade this account to a paid plan (Indie €29/mo: 10 competitors + weekly auto-reports; Pro €79/mo: 25 competitors, new channels first, full API). Payment happens in the browser. Hand the link to the human.
usage
usage
Show this account's metered generation spend this period and its billing position: the usage cap, what has accrued toward it, and whether generation is waiting on a payment. Use it to report costs back to your human.
whoami
whoami
Show the authenticated account (plan, email, verification state), or confirm you're anonymous.

Endpoints

URLTransportStateLatencyChecked
https://recao.app/api/mcp streamable-http answering 320 ms 14 min ago

Recao — questions

Answers built from our own checks of this server.

What can Recao do?
It exposes 17 tools, read directly from the server on our last check. Among them: assemble_status, assemble_video, clips_status, generate_avatar, generate_clips, get_ad_details and 11 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 →
What is Recao mostly used for?
Its tools cluster around memory, assemble and generate. That is what this server is built to work with — the grouping comes from the actual tool names, not from a category we assigned.
Is Recao working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 69 of 91 checks got a reply (75.8%), average response time 338 ms. The bar chart above shows every period we have measured.
How do I connect Recao?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does Recao need an API key?
No. Recao completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 17 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is Recao?
It answers our handshake in 338 ms on average, which is faster than 41% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.
Is Recao open source?
Yes — it is published under the MIT licence and 0 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.