Skip to content
Citizen of Nowhere logo

Citizen of Nowhere MCP server

Which MCP servers are Citizen of Nowhere'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 2026-10-26

← Back to Citizen of Nowhere

Whose server it is
  • Registry nameorg.citizenofnowhere.rankings/global-metro-power-rankingsverified in the MCP registry

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

When we asked itchecked 2026-10-26
  • Stateanswerschecked 2026-10-26
  • Tools5
  • Server calls itselfglobal-metro-power-rankings
  • Server version1.0.0
  • Protocol version2025-06-18

On 2026-10-26 the server answered initialize and tools/list without a sign-in. First answer in 298 ms.

Should an agent connect itNot proven either way yet
  • Its tools do compare global metros on sixteen weighted dimensions, but not rank sports teams by monthly fan attention; explore a martech reference implementation for fan data.
  • Checked on 2 of the 7 days it takes to judge reliability.

Once connected

  • For "compare global metros on sixteen weighted dimensions", the likely first call is compare_metros.

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 2026-10-26
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 2 so far
  • What an agent can do with it1 of 3 use cases
  • Answeredmeasuring2 of the 7 daily checks it takes to print a share
  • Median first answer258 ms
  • Space in an agent's context≈ 624 tokensthe definitions of all its tools (5), which an agent carries on every turn
  • Tool definitionsB · 80 of 100
  • Typed results0 of 5 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 1 of 5
  • Not saying whether it only reads or can destroy: 5 of 5

What an agent can do with it

  • cannot · rank sports teams by monthly fan attention
  • can do · compare global metros on sixteen weighted dimensions
  • cannot · explore a martech reference implementation for fan data

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 offers5 tools · read 2026-10-26
  • get_metro

    Full profile for one metro in the Global Metro Power Rankings: rank, score, all sixteen dimension values and ranks, teams, universities, culture, luxury hospitality, events, market cap, and more. Use search_metros first if you don't know…

  • list_top_metros

    Ranked list of metros from the Global Metro Power Rankings composite (4,300+ metros total), optionally filtered by region or country. Returns lightweight summary rows (rank, slug, name, country, region, score, population). Call get_metro…

  • search_metros

    Case-insensitive search over metro name, primary city, and country. Use this to find a metro's exact slug before calling get_metro or compare_metros.

  • compare_metros

    Side-by-side comparison of two to 4 metros across all sixteen scoring dimensions, with the leader in each dimension flagged.

  • get_methodology

    The sixteen weighted dimensions behind the Global Metro Power Rankings composite score: what each measures, its weight/shape in the formula, and its upstream data source.

How to connect

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

{
  "mcpServers": {
    "global-metro-power-rankings": {
      "type": "http",
      "url": "https://rankings.citizenofnowhere.org/api/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http citizenofnowhere https://rankings.citizenofnowhere.org/api/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://rankings.citizenofnowhere.org/api/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.