Skip to content
Agent Request Desk logo

Agent Request Desk MCP server

Which MCP servers are Agent Request Desk's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-28

← Back to Agent Request Desk

Whose server it is
  • Registry namedev.agentrequest/request-deskverified in the MCP registry

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

When we asked itchecked 2026-10-28
  • Stateanswerschecked 2026-10-28
  • Tools3
  • Server calls itselfagent-request-desk
  • Server version0.3.0
  • Protocol version2025-06-18

On 2026-10-28 the server answered initialize and tools/list without a sign-in. First answer in 232 ms.

Should an agent connect itNot proven either way yet
  • Its tools do every use case we checked: get official API or dataset pointers for missing data; log agent dead ends into a private report.
  • Checked on 5 of the 7 days it takes to judge reliability.

Once connected

  • For "get official API or dataset pointers for missing data", the likely first call is request_data.
  • For "log agent dead ends into a private report", the likely first call is report_failure.
  • Parameters are untyped or undescribed in 2 of 3 tools: check arguments before calling.

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: 5, the first on 2026-10-28
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 5 so far
  • What an agent can do with it2 of 2 use cases
  • Answeredmeasuring5 of the 7 daily checks it takes to print a share
  • Median first answer295 ms
  • Space in an agent's context≈ 1,021 tokensthe definitions of all its tools (3), which an agent carries on every turn
  • Tool definitionsC · 72 of 100
  • Typed results0 of 3 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 2 of 3
  • Not saying whether it only reads or can destroy: 3 of 3

What an agent can do with it

  • not sure · find which sites block your agent
  • can do · get official API or dataset pointers for missing data
  • can do · log agent dead ends into a private report

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 (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). 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 offers3 tools · read 2026-10-28
  • request_data

    Call this when you need specific data for a task and cannot get it: the site returned 403 or 429, showed a CAPTCHA or Cloudflare challenge, sits behind a login wall, has no API, renders only with JavaScript, publishes only as PDF, or the…

  • request_action

    Call this when you tried to do something for your user and could not finish it: there is no API for the action, a CAPTCHA or bot check stopped you, it needs a login or account, it is phone-only or in person only, or a booking or…

  • report_failure

    Call this right after a fetch, scrape or API call fails and stops your task: HTTP 403, HTTP 429, CAPTCHA, Cloudflare challenge, login wall, an empty page that needs JavaScript, PDF-only content, or a page that has gone. Returns an…

How to connect

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

{
  "mcpServers": {
    "request-desk": {
      "type": "http",
      "url": "https://agentrequest.dev/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http agentrequest https://agentrequest.dev/mcp

Add to CursorAdd to VS Code

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

OpenAPI spec

4 paths, read 2026-10-28. 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.