Skip to content

DECA Labs MCP server

ai.decalabs/decadecalabs.aistreamable-httpv1.4.0Scanned

Demand signals, product ideas and real-ad demand tests for AI agents. Free to read.

8 tools: 1 can delete or cancel things, 1 do something that can't be undone, 1 change things and 5 only read.

Tools: 1 delete, 1 irreversible, 1 write, 5 read.
  • Reads private data · 0
  • Reads text others write · 4
  • Can send data out · 1
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here can delete or cancel things and 1 does something that can't be undone. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the DECA Labs MCP server can do

The DECA Labs MCP server is published by decalabs.ai, a domain the MCP Registry verified. It has 8 tools. It can delete or cancel things (1 tool: cancel_test), do things that cannot be undone, such as sending, paying or publishing (start_test) and create or change data (1 tool: quote_test). 5 tools only read.

4 tools bring in text other people can write (get_signals, get_ideas, start_test and 1 more); 1 tool can send data out of your system (start_test).

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 20, 2026, version 1.4.0.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

8 tools

Deletes or cancels 1Claude Code: deny
  • cancel_testCancel a test that is still in review, before its ads run.No findings

    Why it is in this group

    • The name "cancel_test" says "cancel": a word for removing or ending something.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Cancel a test that is still in review, before its ads run. The whole budget is refunded to the paying wallet.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: true
    • openWorldHint: false
Can't be undone 1Claude Code: ask
  • start_testPay for one option of a quote and open the test.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "start_test" says "start": a word for a change.
    • The description's first verb is "pay": a word that usually means money moves, which cannot be taken back.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe input takes a URL (input.webhook_url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    Pay for one option of a quote and open the test. The price is the option's ad budget in USDC on Base, paid over x402. Call it first without `payment`: the answer is an x402 payment request for the exact amount. Pay it with an x402 client and call again with the payment as `payment` (the base64 PAYMENT-SIGNATURE value). A person reviews every test before its ads run; a declined test is refunded in full. Use sandbox: true to try the whole flow on Base Sepolia with test USDC; a sandbox test runs no ads and moves through its states in minutes.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
Changes things 1Claude Code: ask
  • quote_testThe price of testing an idea with ten days of real ads, before anything is paid.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    The price of testing an idea with ten days of real ads, before anything is paid. You pay only the ad budget, at cost, in USDC on Base; there is no fee. The budget is sized to the idea: several options (signal, clear read, market comparison, or your own budget), each with its expected visits, the number of confirmed sign-ups it must reach to pass, and what it can and cannot tell. Use an idea_id from get_ideas or describe your own idea. The quote is valid for 30 minutes. Free; nothing is charged.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
Only reads 5Show 5 read-only tools
  • get_ideasConsumer product ideas DECA's engine wrote from the demand signals and judged worth testing, best first, each with the apps and posts it rests on and its expected sign-up rate.Reads text others writeNo findings

    Why it is in this group

    • The name "get_ideas" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "post": it reads posts, which other people can write.
    Description, as the server wrote it
    Consumer product ideas DECA's engine wrote from the demand signals and judged worth testing, best first, each with the apps and posts it rests on and its expected sign-up rate. Ideas another founder is testing are not shown. Pass id to read one idea. Free.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • get_my_ideasThe ideas DECA's engine wrote for your own workspace from what it knows about you (set in the dashboard under Settings → Your radar), each with why it is yours, and the day's publi…No findings

    Why it is in this group

    • The name "get_my_ideas" says "get": a word for reading.
    Description, as the server wrote it
    The ideas DECA's engine wrote for your own workspace from what it knows about you (set in the dashboard under Settings → Your radar), each with why it is yours, and the day's public ideas it picked for you. Needs an API key; a key sees only its own workspace. Read only: it never asks the engine to write more. Free.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • get_signalsToday's demand patterns from DECA's radar: groups of apps climbing the App Store and Google Play charts, with what people say and want about them and the public posts behind it.Reads text others writeNo findings

    Why it is in this group

    • The name "get_signals" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "post": it reads posts, which other people can write.
    Description, as the server wrote it
    Today's demand patterns from DECA's radar: groups of apps climbing the App Store and Google Play charts, with what people say and want about them and the public posts behind it. Every chart fact names its store category and country. Free. Updated daily.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • get_testA paid test's state and everything in it: payment, review, the pass line, progress and the result.Reads text others writeNo findings

    Why it is in this group

    • The name "get_test" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "review": it reads comments, which other people can write.
    Description, as the server wrote it
    A paid test's state and everything in it: payment, review, the pass line, progress and the result. Readable with the key it was paid with, or its access_token.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • list_my_testsEvery test paid with this API key's workspace, newest first.No findings

    Why it is in this group

    • The name "list_my_tests" says "list": a word for reading.
    Description, as the server wrote it
    Every test paid with this API key's workspace, newest first. Needs a key.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write4
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out1
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 20, 2026, 18:18 UTC, unchanged since Nov 20, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
3
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 3 tools that change things (1 destructive, 1 irreversible, 1 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://app.decalabs.ai/mcp: tools/list returned 8 tools to an anonymous client, including cancel_test (destructive), start_test (irreversible), quote_test (write)

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

Changes to its tool definitions and to its remote endpoint, newest first.

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

Install

Pinned to version 1.4.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http deca https://app.decalabs.ai/mcp
claude mcp add --transport http deca https://app.decalabs.ai/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__deca__get_signals",
      "mcp__deca__get_ideas",
      "mcp__deca__get_my_ideas",
      "mcp__deca__get_test",
      "mcp__deca__list_my_tests"
    ],
    "ask": [
      "mcp__deca__quote_test",
      "mcp__deca__start_test"
    ],
    "deny": [
      "mcp__deca__cancel_test"
    ]
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as deca. Review it before you use it.

Capability tags behind 4 rules
  • mcp__deca__get_signals untrusted-input
  • mcp__deca__get_ideas untrusted-input
  • mcp__deca__start_test untrusted-input, outbound
  • mcp__deca__get_test untrusted-input

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/ai.decalabs/deca/verify?hash=d7f676090f5f35704847f879e1bfa2ac84972b6666a7f0c07d2096830aa0e6b7" | jq -e '.changed == false'

Pinned hash d7f676090f5f, from Nov 20, 2026, 13:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/ai.decalabs/deca/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for ai.decalabs/deca
[![Anlyon Radar](https://radar.anlyon.com/badge/ai.decalabs/deca.svg)](https://radar.anlyon.com/servers/ai.decalabs/deca)

Source: MCP Registry. Synced Nov 20, 2026, 13:17 UTC.

DECA Labs MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the DECA Labs MCP server safe?

No scan can promise that. What its definitions show: 8 tools, 3 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the DECA Labs MCP server delete data?

Yes. 1 tool can delete, cancel or revoke something: cancel_test.

Can the DECA Labs MCP server do things that cannot be undone?

Yes. 1 tool can send, pay, publish or merge: start_test.

What tools does the DECA Labs MCP server have?

8 tools: 1 destructive, 1 irreversible, 1 write, 5 read. cancel_test, start_test, quote_test, get_signals, get_ideas, get_my_ideas, get_test and list_my_tests.

Does the DECA Labs MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the DECA Labs MCP server send data to outside services?

1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): start_test.

Has the DECA Labs MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 20, 2026.