Skip to content
ToolsThatRank logo

ToolsThatRank MCP server

Which servers in the official MCP registry are ToolsThatRank's own, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-25

← Back to ToolsThatRank

Whose server it is
  • Registry namecom.toolsthatrank/serp-metricsverified in the MCP registry

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

When we asked itchecked 2026-10-25
  • Stateanswerschecked 2026-10-25
  • Tools3
  • Server calls itselfcom.toolsthatrank/serp-metrics
  • Server version1.0.0
  • Protocol version2025-06-18

On 2026-10-25 the server answered initialize and tools/list without a sign-in. First answer in 108 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 2 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: 2, the first on 2026-10-25
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 2 so far
  • Answeredmeasuring2 of the 7 daily checks it takes to print a share
  • Median first answer170 ms
  • Space in an agent's context≈ 1,016 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 (30%), doing the product's job (25%), definitions (20%), context (10%) and use (15%). 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 2026-10-25
  • impression_weighted_position

    Compute the impression-weighted average SERP position for a set of query rows, alongside the plain arithmetic mean and the gap between them. The arithmetic mean lets a 3-impression query count as much as a 30,000-impression one; the…

  • project_clicks_from_ctr_curve

    Project how many clicks a set of query rows would earn at a target position instead of their current position, using a CTR curve THAT YOU SUPPLY. This server deliberately ships no built-in CTR table: every published…

  • share_of_voice

    Compute share of voice across competing entities over a keyword set. Reports impression share always, and, if you supply a CTR curve, a weighted visibility share that accounts for the fact that an impression at position 1 is not worth an…

How to connect

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

{
  "mcpServers": {
    "serp-metrics": {
      "type": "http",
      "url": "https://toolsthatrank-mcp.lipmichal.workers.dev"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http toolsthatrank https://toolsthatrank-mcp.lipmichal.workers.dev

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://toolsthatrank-mcp.lipmichal.workers.dev 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.