Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Recao

REMOTE · RECAO.APP · SCANNED SEP 21

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

Available components

0 this week 86 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security80
Transport & Reachability100
Schema Quality & AI Usability72
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 2444 tokens (~143/item across 17 items; 17 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage93
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 78% of tool parameters carry a description.Partial
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 17 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 18 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the Recao MCP server?

Recao is a hosted endpoint at https://recao.app/api/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · recao.app

# add to Claude Code
claude mcp add --transport http app-recao-recao-mcp 'https://recao.app/api/mcp'
// .cursor/mcp.json
{
  "mcpServers": {
    "app-recao-recao-mcp": {
      "url": "https://recao.app/api/mcp"
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "app-recao-recao-mcp": {
      "type": "http",
      "url": "https://recao.app/api/mcp"
    }
  }
}
# ~/.codex/config.toml
[mcp_servers.app-recao-recao-mcp]
url = "https://recao.app/api/mcp"
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "app-recao-recao-mcp": {
      "type": "remote",
      "url": "https://recao.app/api/mcp",
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add app-recao-recao-mcp --url 'https://recao.app/api/mcp' --transport streamable-http
# ~/.hermes/config.yaml
mcp_servers:
  app-recao-recao-mcp:
    url: "https://recao.app/api/mcp"
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "app-recao-recao-mcp": {
      "Transport": "http",
      "Url": "https://recao.app/api/mcp"
    }
  }
}
# add to Vellum
assistant mcp add app-recao-recao-mcp -t streamable-http -u 'https://recao.app/api/mcp'
// mcp.json
{
  "mcpServers": {
    "app-recao-recao-mcp": {
      "type": "http",
      "url": "https://recao.app/api/mcp"
    }
  }
}

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 26 Aug 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 25 Aug 26 +1
    • Stability: 0.97 → pass security
  • 11 Aug 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 31 Jul 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 30 Jul 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 27 Jul 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 26 Jul 26 0

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Sept 2026 · Probed https://recao.app/api/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=recao.app CN=YR2,O=Let's Encrypt,C=US 15 Aug 2026 13 Nov 2026 RSA 2048 SHA256-RSA 5bc999c376c7bcdf0ff0834af09155a88d3
SANs: recao.app
CN=YR2,O=Let's Encrypt,C=US (CA) CN=Root YR,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 RSA 2048 SHA256-RSA 4ebd24947e24d394802d84a52fd5b319
CN=Root YR,O=ISRG,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 RSA 4096 SHA256-RSA f24b6d17f9d9ad7cb1c9fea78782699f

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of recao.app. Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
app. present 23684 8 Verified
recao.app. absent Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
strict-transport-security max-age=63072000

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://recao.app/api/mcp Verified 200
http (plaintext) http://recao.app/api/mcp HTTPS enforced 308 https://recao.app/api/mcp
MCP tools · 17 exposed · ~2,323 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
assemble_status ~88

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.

NameTypeReqDescription
job_idstringyesThe job_id returned by assemble_video

No output schema declared.

No examples provided.

assemble_video ~356

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.

NameTypeReqDescription
aspectstringOutput aspect ratio: 9:16 (default, 1080x1920), 1:1 (1080x1080), or 16:9 (1920x1080).
clipsarrayyes1 to 6 clips in playback order
introobjectOptional intro title card shown before the clips.
outroobjectOptional outro title card shown after the clips (e.g. a call to action).

No output schema declared.

No examples provided.

clips_status ~88

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.

NameTypeReqDescription
job_idstringyesThe job_id returned by generate_clips with confirm=true

No output schema declared.

No examples provided.

generate_avatar ~196

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.

NameTypeReqDescription
countintegerHow many stills to request (2 to 3). The default model returns 1 regardless; imagen and flux honor this.
modelstringImage model. Default seedream-4.0 (lowest cost).
persona_briefstringyesPhysical description plus vibe of the invented UGC creator. One person (age, look, styling, setting, energy).

No output schema declared.

No examples provided.

generate_clips ~554

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.

NameTypeReqDescription
aspectstringOutput aspect ratio
avatar_idstringAvatar id from generate_avatar (starts with av_). Its persona brief describes the recurring character in text; identity holds within a take only, not across takes.
confirmbooleanSet true to start the metered render. Returns a job_id to poll with clips_status.
modelstringseedance-2.0 (default, highest quality) or seedance-2.0-fast (same generation, faster and cheaper).
personastringAlternative to avatar_id: describe the recurring character or the full ensemble (several characters) in words. Same limits: identity holds within a take, not across takes. Ignored when avatar_id is p…
reference_image_urlsarrayUp to 9 https image URLs of products or props to keep on-model in every take. No people in these images.
scenesarrayyes3 to 6 scenes in order. Adjacent scenes sharing a character land in the same take when their combined length allows it.

No output schema declared.

No examples provided.

get_ad_details ~73

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.

NameTypeReqDescription
adIdstringyes
datePresetstring

No output schema declared.

No examples provided.

get_competitor_ads ~182

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).

NameTypeReqDescription
countriesarrayEU country codes to filter (default: all 25). Available: AT,BE,BG,HR,CY,CZ,DK,EE,FI,FR,DE,GR,HU,IE,IT,LV,LU,NL,PL,PT,RO,SK,SI,ES,SE
datePresetstring
idnumberyesappId or developerId from search_app_advertiser
typestring

No output schema declared.

No examples provided.

get_playbook ~83

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.

NameTypeReqDescription
slugstring

No output schema declared.

No examples provided.

memory_index ~64

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.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

memory_note ~111

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.

NameTypeReqDescription
bodystringyesFull content (markdown fine)
descriptionstringyesOne-line summary for the index
namestringyesShort kebab-case slug, e.g. 'campaign-tiktok-hooks-june'

No output schema declared.

No examples provided.

memory_recall ~42

Read one memory entry's full body by name (get names from memory_index).

NameTypeReqDescription
namestringyesMemory name (kebab-case slug from memory_index)

No output schema declared.

No examples provided.

roadmap_status ~89

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.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

search_app_advertiser ~68

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.

NameTypeReqDescription
namestringyesApp or developer name to search for
typesstring

No output schema declared.

No examples provided.

sign_up ~182

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>`.

NameTypeReqDescription
app_namestringThe user's own app (App Store name), so reports and memory attach to it
emailstringyesThe account owner's email (the human founder's)

No output schema declared.

No examples provided.

upgrade ~71

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.

NameTypeReqDescription
planstringyes

No output schema declared.

No examples provided.

usage ~51

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.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

whoami ~25

Show the authenticated account (plan, email, verification state), or confirm you're anonymous.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

Common questions

What is the Recao MCP server?

Recao is an MCP server listed in the public MCP registry as app.recao/recao-mcp. Rank a competitor's EU App Store ads by longevity. From Apple's official Ad Repository. This page covers its hosted endpoint (https://recao.app/api/mcp).

Is the Recao MCP server safe to use?

Recao scores 86 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Recao MCP server expose?

Recao exposes 17 tools: search_app_advertiser, get_competitor_ads, get_ad_details, get_playbook, sign_up, and 12 more. Their descriptions and schemas cost roughly 2,323 tokens of context every time the server is loaded.

Does the Recao MCP server require authentication?

No. We connected to Recao without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the Recao MCP server still maintained?

Recao is still listed as active in the MCP registry. We last reached this channel on 21 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.