Skip to content

Open Quality MCP server

Which MCP servers are Open Quality'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 2026-10-27

← Back to Open Quality

Whose server it is
  • Registry nameus.openquality/mcpverified in the MCP registry

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

When we asked itchecked 2026-10-27
  • Stateanswerschecked 2026-10-27
  • Tools5
  • Server calls itselfopenquality
  • Server version0.2.0
  • Protocol version2025-06-18

On 2026-10-27 the server answered initialize and tools/list without a sign-in. First answer in 117 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 2026-10-27
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 1 so far
  • Use1 GitHub stars
  • Answeredmeasuring1 of the 7 daily checks it takes to print a share
  • Median first answer220 ms
  • Space in an agent's context≈ 788 tokensthe definitions of all its tools (5), which an agent carries on every turn
  • Tool definitionsA · 100 of 100
  • Typed results0 of 5 toolsdeclared outputSchema: results come typed, read once
  • Every tool passes all six checks.

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 offers5 tools · read 2026-10-27
  • search_measures

    Find measure packages by CMS id, title words, steward or package id. Every word must match. Shared CQL libraries are packages too; pass kind "library" to search them.

  • get_measure

    A package: title, steward, license, provenance (upstream commit, unmodified or derived, and exactly what changed), value set references, file list and known issue summaries.

  • get_artifact

    The raw text of one file a package lists: CQL, SQL, a ViewDefinition, or a FHIR Measure.

  • get_bundle

    The package as a CRMI artifact Bundle, the shape CRMI's $package returns: an asset-collection Library, then the Measure, its Library and every shared library it depends on.

  • known_issues

    Interpretation issues, defects, test cases and implementation notes, with their full text. Read these before writing or reviewing measure logic.

How to connect

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

{
  "mcpServers": {
    "openquality": {
      "type": "http",
      "url": "https://openquality.us/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http openquality https://openquality.us/mcp

Add to CursorAdd to VS Code

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

Also shipped through: npm

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.