How do I handle private or reserved IP addresses?
The server returns `{ found: false }` for private or reserved IPs, indicating no geolocation data is available.
@racccoinorg
MCP (Model Context Protocol) server that wraps the RockyGeo IP geolocation API hosted on RapidAPI. Lets MCP-compatible clients (Claude Desktop, Claude Code, etc.) perform IPv4/IPv6 geolocation lookups via tool calls
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"rockygeo": {
"command": "node",
"args": [
"/Users/cyborg97/rockygeomcp/dist/index.js"
],
"env": {
"RAPIDAPI_KEY": "<your-key>"
}
}
}
}`{ ip: string }` → geolocation for one IP. Private/reserved IPs return `{ found: false }`.
`{ ips: string[] }` (1–100) → `{ results: { [ip]: ... } }`.
`{}` → `{ status, dataVersion, lastSyncAt, uptime }`.
A Model Context Protocol (MCP) server that wraps the RockyGeo IP geolocation API on RapidAPI. It lets MCP-compatible clients like Claude Desktop or Claude Code perform IPv4/IPv6 geolocation lookups via tool calls.
Install with npm install && npm run build, then configure the RAPIDAPI_KEY environment variable (or pass via --api-key). Add the server to your MCP client config (e.g., claude_desktop_config.json) using the node command pointing at the built dist/index.js file.
lookup_ip toollookup_ips_batchhealth_check) returning status and data version{ found: false }The server returns `{ found: false }` for private or reserved IPs, indicating no geolocation data is available.
The `lookup_ips_batch` tool accepts between 1 and 100 IP addresses per call.
Yes, a RapidAPI key (`RAPIDAPI_KEY`) is required and must be set either as an environment variable or passed with `--api-key`. The free RapidAPI plan allows 1 request per second.
Yes, set the `ROCKYGEO_BASE_URL` environment variable to point at your own instance. The default is `https://rocky-geo.p.rapidapi.com/v1`.
End‑to‑end integration tests are in `tests/integration.test.js` and can be run with `npm test`. They hit the live RockyGeo API, so they consume RapidAPI quota and may be rate‑limited on the free plan.

MCP server for AI Agents — exposes Yocoolab feedback threads and design selections as tools

The tools your AI needs to make your games. Turn prompts into production-ready game assets — animated characters with their weapons attached, seamless textures, terrain, VFX, HUDs — and playable game kits Unity, Godot, U
Query your team's drift, vulnerability, and migration data from any AI assistant. Vibgrate MCP connects Cursor, Claude, ChatGPT, Windsurf, or VS Code to Vibgrate Cloud: 51 tools for DriftScores, CVEs and EOL runtimes, up

The BetterBugs MCP (Model Context Protocol) enables you to load BetterBugs bug reports (via report links) directly to your preferred AI Agents and developer environments with MCP Client capabilities (such as Cursor, VS C

One case file per task — shared by every session, agent and person that touches it. Self-hosted MCP server and live board. MIT.
评论