Skip to content
Cleat logo

Cleat MCP server

Which servers in the official MCP registry are Cleat's own, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-20

← Back to Cleat

Whose server it is
  • Registry nameso.cleat/cleatverified in the MCP registry

The registry name sits under cleat.so. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-20
  • Stateanswerschecked 2026-10-20
  • Tools4
  • Server calls itselfcleat
  • Server version1
  • Protocol version2025-06-18

On 2026-10-20 the server answered initialize and tools/list without a sign-in. First answer in 92 ms.

Should an agent connect itNot proven either way yet
  • Whether its tools do the product's job has not been judged yet.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 7, the first on 2026-10-20
  • INITE MCP score94 of 100answers 100 · definitions 83 · context 100
  • Answered100% of days7 of 7 daily checks
  • Median first answer122 ms
  • Space in an agent's context≈ 521 tokensthe definitions of all its tools (4), which an agent carries on every turn
  • Tool definitionsB · 83 of 100
  • Typed results0 of 4 toolsdeclared outputSchema: results come typed, read once
  • Not saying whether it only reads or can destroy: 4 of 4

What an agent can do with it

  • not sure · receive bank and payment login codes on a US mobile number
  • not sure · share service verification codes with a team inbox
  • cannot · forward incoming codes to email or a Telegram chat

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (30%), doing the product's job (25%), definitions (20%), context (10%) and use (15%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers4 tools · read 2026-10-20
  • list_lines

    The phone numbers in this workspace that can receive texts, newest first.

  • list_messages

    Texts received by one line, newest first.

  • latest_code

    The most recent verification code sent to a line, or nothing if none has arrived.

  • wait_for_code

    Waits for the next verification code to arrive at a line and returns it. Call this immediately BEFORE triggering the text, so nothing is missed. Returns timedOut: true if none arrives in time.

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "cleat": {
      "type": "http",
      "url": "https://cleat.so/api/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http cleat https://cleat.so/api/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://cleat.so/api/mcp as a custom connector in the settings.

Also shipped through: npm

OpenAPI spec

2 paths, read 2026-10-20. Open the spec ↗

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.