Skip to content
Trakis logo

Trakis MCP server

Which MCP servers are Trakis'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 Trakis

Whose server it is
  • Registry nameio.trakis/seo-checksverified in the MCP registry

The registry name sits under trakis.io. 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
  • Tools3
  • Server calls itselftrakis
  • Server version1.0.0
  • Protocol version2025-06-18

On 2026-10-27 the server answered initialize and tools/list without a sign-in. First answer in 244 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
  • Answeredmeasuring1 of the 7 daily checks it takes to print a share
  • Median first answer242 ms
  • Space in an agent's context≈ 388 tokensthe definitions of all its tools (3), which an agent carries on every turn
  • Tool definitionsA · 100 of 100
  • Typed results0 of 3 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 offers3 tools · read 2026-10-27
  • search_checks

    Find Trakis checks by a word or a problem, when you do not know the check's code. Searches titles, what each check looks at, why it matters and where the problem usually comes from. Returns up to 10 checks, best matches first.

  • explain_check

    The full explanation of one Trakis check: what it looks at, why it matters, where the problem usually comes from, how to fix it (with a worked example when there is one), how to verify it without Trakis, and how an audit counts it.

  • list_checks

    Every check a Trakis audit runs, optionally only one category or one severity, with its code, title and a link to its explanation.

How to connect

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

{
  "mcpServers": {
    "seo-checks": {
      "type": "http",
      "url": "https://trakis.io/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http trakis https://trakis.io/mcp

Add to CursorAdd to VS Code

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

Other servers listed as Trakis's
  • io.trakis/site-auditsanswers, requires sign-inverified in the MCP registry

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.