Skip to content
IP 判官 logo

IP 判官 MCP server

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

read 2026-10-21

← Back to IP 判官

Whose server it is
  • Registry nameorg.ipjudge/ipjudgeverified in the MCP registry

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

When we asked itchecked 2026-10-21
  • Stateanswerschecked 2026-10-21
  • Tools4
  • Server calls itselfipjudge
  • Server version1.0
  • Protocol version2025-06-18

On 2026-10-21 the server answered initialize and tools/list without a sign-in. First answer in 134 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.

Once connected

  • Parameters are untyped or undescribed in 3 of 4 tools: check arguments before calling.

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 2026-10-21
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 2 so far
  • Use1 GitHub stars
  • Answeredmeasuring2 of the 7 daily checks it takes to print a share
  • Median first answer7279 ms
  • Space in an agent's context≈ 320 tokensthe definitions of all its tools (4), which an agent carries on every turn
  • Tool definitionsC · 71 of 100
  • Typed results0 of 4 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 3 of 4
  • Not saying whether it only reads or can destroy: 4 of 4

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 offers4 tools · read 2026-10-21
  • check_ip

    Judge an IPv4/IPv6 address: residential vs datacenter, purity score 0-100, risk-list hits, and whether ChatGPT, Claude, Gemini and Muse accept its region/type. Data: ipjudge.org.

  • my_exit

    Judge the public IP this agent/server is calling from (its own network exit) — use it to check whether Claude / ChatGPT will accept the machine the agent runs on.

  • ai_availability

    Whether ChatGPT, Claude, Gemini and Muse officially support a country (ISO 3166-1 alpha-2, e.g. US, HK, CN), from each company's published list.

  • service_status

    Official live status (Statuspage) of Claude, OpenAI, Cursor, GitHub, Cloudflare and more, refreshed every 3 minutes.

How to connect

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

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

Add it

Claude Code, in a terminal

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

Add to CursorAdd to VS Code

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