Ip Location Mcp

MCP server for IPv4 geolocation with Chinese output: country/region/city, ISP and ASN.

LLM Mart 9 views 140 listing impressions

IPv4 geolocation lookup with Chinese output — country/region/city, coordinates, timezone and ISP/ASN info, with automatic fallback between two free providers.

  • Try it in 30 seconds: a free public MCP endpoint is already running — just paste the URL into your MCP client (no install, no API key).
  • Or self-host: a single Python file, stdlib HTTP + FastMCP, zero paid dependencies.

⚡ Use the hosted endpoint (no setup)

https://mcp.pianam.cn/ip-mcp/mcp

Transport: Streamable HTTP (MCP 2025-03-26 compatible). No authentication required.

🔌 Client configuration

Add this to your MCP client's mcpServers configuration (Claude Desktop claude_desktop_config.json, Cursor mcp.json, Cline, Cherry Studio, etc.):

{
  "mcpServers": {
    "ip-location": {
      "type": "http",
      "url": "https://mcp.pianam.cn/ip-mcp/mcp"
    }
  }
}

Clients that do not accept "type": "http" (some Cherry Studio / older Cline versions) accept the same entry with just "url".

🧰 Tools

Tool Parameters Returns
query_ip_location(ip="", ctx=None) ip: IPv4 address, e.g. "8.8.8.8". Empty: attempts the caller's own public IP (via X-Forwarded-For). 归属地 (country/region/city), coordinates, timezone, ISP, organization and AS number — in Chinese. Error message for invalid/non-IPv4 input.

📡 Data sources, caching & limits

  • Primary source: ip-api.com — free endpoint with direct Chinese-language output.
  • Automatic fallback: ipwho.is (free, 10k requests/month) with built-in English→Chinese country/province mapping (all Chinese provinces + US/AU/JP/KR common regions).
  • Results cached for 24 hours (geolocation barely changes); hosted endpoint rate-limited to 200 requests / minute / IP.
  • No API key, no login; read-only lookups.

🐢 Self-hosting

git clone https://github.com/boy-373/ip-location-mcp.git
cd ip-location-mcp
pip install -r requirements.txt
python ip_lookup_mcp_server.py
# the server listens on 127.0.0.1:8006 by default; override with:
#   MCP_HOST=0.0.0.0 MCP_PORT=9000 python ip_lookup_mcp_server.py
#   MCP_ALLOWED_HOSTS="your-domain.com,127.0.0.1:*"
#   MCP_ALLOWED_ORIGINS="https://your-domain.com"

Then point your MCP client at http://127.0.0.1:8006/mcp. No API keys or accounts are ever required.

🐳 Self-host with Docker

Option A — pull the pre-built image (fastest, no build):

docker run -d -p 8000:8000 --name ip-location-mcp ghcr.io/boy-373/ip-location-mcp:latest

Option B — build from source:

git clone https://github.com/boy-373/ip-location-mcp.git
cd ip-location-mcp
docker build -t ip-location-mcp .
docker run -d -p 8000:8000 --name ip-location-mcp ip-location-mcp

Then point your MCP client at http://127.0.0.1:8000/mcp. The container listens on 0.0.0.0:8000 by default (override with -e MCP_PORT=9000 and adjust -p accordingly). No API keys or accounts required.

🗂️ Files

  • ip_lookup_mcp_server.py — the MCP server (FastMCP, Streamable HTTP transport).
  • rate_limit.py — lightweight per-IP sliding-window rate-limit middleware (200 req/min default).
  • requirements.txt — mcp, uvicorn, starlette.
  • server.json — official MCP Registry manifest (remote server entry, ready to publish with mcp-publisher).
  • smithery.yaml / glama.json — directory listing metadata.

🇨🇳 中文使用说明

一句话:IP 归属地查询,国家/省份/城市/运营商/ASN 全中文输出,主备双通道高可用。

在线直连地址(免费、无需 Key、开箱即用):https://mcp.pianam.cn/ip-mcp/mcp

在 MCP 客户端(Claude Desktop / Cursor / Cherry Studio / Cline 等)的配置里加入:

{
  "mcpServers": {
    "ip-location": {
      "type": "http",
      "url": "https://mcp.pianam.cn/ip-mcp/mcp"
    }
  }
}

工具:

  • query_ip_location(ip):查 IPv4 归属地。传 IP 地址(如 8.8.8.8);留空时尝试查询调用方自己的公网 IP。
  • 返回国家/省份/城市、经纬度、时区、运营商、组织、AS 编号,中文输出。
  • 主数据源 ip-api.com(免费、中文直出),故障自动切换 ipwho.is(含中国省份拼音中文化映射)。

From the project's README.

Related servers

Read and write RAGE Package Format archives

23 views

MCP server for Geargrafx PC Engine / TurboGrafx-16 emulator

19 views

See how ChatGPT, Claude, Gemini and Perplexity read any website. Scored out of 100.

19 views

Read-only on-chain intel for AI agents on Base: balances, tokens, gas, tx status. No API keys.

15 views