Skip to content
Corduroy Labs logo

Corduroy Labs MCP server

Which MCP servers are Corduroy Labs'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 2026-10-23

← Back to Corduroy Labs

Whose server it is
  • Registry nameai.corduroy-labs/updatesverified in the MCP registry

The registry name sits under corduroy-labs.ai. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-23
  • Stateanswerschecked 2026-10-23
  • Tools2
  • Server calls itselfcorduroy-labs
  • Server version1.28.1
  • Protocol version2025-06-18

On 2026-10-23 the server answered initialize and tools/list without a sign-in. First answer in 93 ms.

Should an agent connect itSkip it
  • Its tools do none of the product's use cases we checked: route website and email intake to shared role inboxes; add human approval gates to agent-drafted replies; map which workflow steps agents classify, draft, or route.
  • Checked on 4 of the 7 days it takes to judge reliability.

Once connected

  • Parameters are untyped or undescribed in 2 of 2 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: 4, the first on 2026-10-23
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 4 so far
  • What an agent can do with it0 of 3 use cases
  • Answeredmeasuring4 of the 7 daily checks it takes to print a share
  • Median first answer292 ms
  • Space in an agent's context≈ 248 tokensthe definitions of all its tools (2), which an agent carries on every turn
  • Tool definitionsC · 67 of 100
  • Typed results1 of 2 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 2 of 2
  • Not saying whether it only reads or can destroy: 2 of 2

What an agent can do with it

  • cannot · route website and email intake to shared role inboxes
  • cannot · add human approval gates to agent-drafted replies
  • cannot · map which workflow steps agents classify, draft, or route

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 offers2 tools · read 2026-10-23
  • list_updates

    List Corduroy Labs blog updates, newest first. Args: limit: optional maximum number of items to return. Returns: A list of update summaries with: slug, title, url, date_published, summary, and optionally tags, location, image.

  • get_update

    Fetch one Corduroy Labs update in full by its slug. Args: slug: the update's slug (e.g. "the-studio-machine-readable"). Obtain slugs from list_updates(). Returns: A dict with slug, title, url, date_published, summary, content_html, and…

How to connect

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

{
  "mcpServers": {
    "updates": {
      "type": "http",
      "url": "https://corduroy-labs.ai/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http corduroy-labs https://corduroy-labs.ai/mcp

Add to CursorAdd to VS Code

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

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.