Skip to content
holdmark logo

holdmark MCP server

Which MCP servers are holdmark'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 holdmark

Whose server it is
  • Registry nameorg.holdmark/registryverified in the MCP registry

The registry name sits under holdmark.org. 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 itselfholdmark
  • Server version1.0.0
  • Protocol version2025-06-18

On 2026-10-28 the server answered initialize and tools/list without a sign-in. First answer in 467 ms.

Should an agent connect itNot proven either way yet
  • Whether its tools do the product's job has not been judged yet.
  • Checked on 1 of the 7 days it takes to judge reliability.

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: 1, the first on 2026-10-28
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 1 so far
  • Answeredmeasuring1 of the 7 daily checks it takes to print a share
  • Median first answer481 ms
  • Space in an agent's context≈ 584 tokensthe definitions of all its tools (3), which an agent carries on every turn
  • Tool definitionsB · 83 of 100
  • Typed results0 of 3 toolsdeclared outputSchema: results come typed, read once
  • Not saying whether it only reads or can destroy: 3 of 3

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
  • find_stores

    List the online stores in the holdmark registry, with a summary of their published facts. Each store publishes the same facts under the same rules: whether it delivers its orders (checked with the carrier) and whether it refunds money…

  • get_store

    Read the full holdmark record for one store, by its domain. Figures are rounded against the merchant, order volume is published in bands rather than exact numbers, and every figure carries the period it covers and the source it came from…

  • how_holdmark_works

    How every figure in the registry is calculated, what the words mean, and above all what holdmark does NOT measure. Read this before drawing a conclusion from any record: it is what stops a figure being read as something it is not.

How to connect

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

{
  "mcpServers": {
    "registry": {
      "type": "http",
      "url": "https://holdmark.org/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http holdmark https://holdmark.org/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://holdmark.org/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.