Skip to content
MCP server

IP for AI

Check whether your exit IP works for ChatGPT, Claude and Gemini from your AI client

Runs locallyStatus and history
Install
Pricing
Open source
Platforms
CLI, Linux, macOS
Runs
Locally
Version
0.1.0
Listing updated
2 days ago

About IP for AI

IP for AI is an open-source MCP server for ai models and llm tooling. It runs locally on your machine and is started by your AI client.

The server answers one practical question for people behind proxies or VPNs: what does the network exit look like to AI services? It calls the ipforai.cc service and returns a profile of an IP address, so an assistant can report on connectivity problems without leaving the chat.

The README says each profile covers location, ASN, network type (residential, ISP, datacenter, proxy or Tor), access and routing type, risk level, an environment score and AI service availability, plus a link to the full report. Results describe the network only and are not verdicts on any account, login or subscription.

It runs locally over stdio with Node.js 20.18.1 or later and needs no API key. It honours HTTPS_PROXY, HTTP_PROXY and NO_PROXY so the check goes out through the same path as your AI traffic. The only host it contacts is ipforai.cc.

Install

Run in a terminal

claude mcp add ipforai -- npx -y ipforai-mcp

Add to claude_desktop_config.json

{
  "mcpServers": {
    "ipforai": {
      "command": "npx",
      "args": [
        "-y",
        "ipforai-mcp"
      ]
    }
  }
}
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "ipforai": {
      "command": "npx",
      "args": [
        "-y",
        "ipforai-mcp"
      ]
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "ipforai": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "ipforai-mcp"
      ]
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "ipforai": {
      "command": "npx",
      "args": [
        "-y",
        "ipforai-mcp"
      ]
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "ipforai": {
      "command": "npx",
      "args": [
        "-y",
        "ipforai-mcp"
      ]
    }
  }
}

Tools this server provides (2)

Taken from the project documentation; the running server may differ.

check_my_ip
Profile of this machine's IPv4 / IPv6 exit
lookup_ip
Profile of a given IPv4 or IPv6 address

What it does

Check own exit IP
Profiles the IPv4 and IPv6 exit of the current machine.
Look up any IP
Returns the same profile for an address you supply.
Network type detail
Separates residential, ISP, datacenter, proxy and Tor.
Proxy support
Reads standard proxy environment variables.
No API key
Runs through npx without credentials.

Good for

  • Diagnose why an AI service reports a region error
  • Compare IPv4 and IPv6 exits on a dual-stack connection
  • Check the risk level of a proxy address before using it
  • Confirm a proxy setup routes AI traffic as intended

Pricing

Open source

MIT licence; no API key

Prices change. Check ipforai.cc before you buy.

IP for AI FAQ

Which tools does it expose?

check_my_ip, which takes no input, and lookup_ip, which takes an IPv4 or IPv6 address.

Does it need an API key?

No.

Does it read my machine?

The README says it reads only the proxy environment variables and calls ipforai.cc.

Does a good score guarantee account access?

No. The results describe the network environment only.

Is IP for AI free?

Yes. IP for AI is open source, so you can use and self-host it for free.

How do I add IP for AI to Claude Code?

Run this command in your terminal: claude mcp add ipforai -- npx -y ipforai-mcp

What are the best alternatives to IP for AI?

The closest alternatives to IP for AI are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

Alternatives to IP for AI

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  3. GitHub

    MCP server

    Official MCP server connecting AI assistants to GitHub repos, issues and workflows

    Not checked yet
    • Remote
    • Open source
    • 34.5K GitHub stars
    • Developer tools
  4. MCP toolkit giving coding agents symbol-level code retrieval and editing

    Runs locally
    • Open source
    • 31.5K GitHub stars
    • Developer tools
  5. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  6. Ouroboros

    MCP server

    Spec-first layer that pins requirements and verifies results of AI coding agent work

    Runs locally
    • Open source
    • 6.4K GitHub stars
    • Developer tools