Piloterr

Piloterr MCP Server

Official Model Context Protocol server for the Piloterr web scraping API.

Scrape 300+ websites (Amazon, LinkedIn, Google, Zillow, Crunchbase…) as structured JSON with one API.

It lets Claude, Cursor, VS Code, Windsurf and any MCP client call the API as tools. Runs over stdio (local) or Streamable HTTP (self-hosted).

Requirements

• Node.js 20 or newer
• a Piloterr API key — sign up, then copy it from the dashboard

Hosted server (recommended)

Piloterr runs this server for you at `https://mcp.piloterr.com/` (Streamable HTTP). Send your API key in the x-api-key header; nothing to install.

claude mcp add --transport http piloterr https://mcp.piloterr.com/ --header "x-api-key: YOUR_API_KEY"

{

"mcpServers": { "piloterr": { "url": "https://mcp.piloterr.com/", "headers": { "x-api-key": "YOUR_API_KEY" } } } }

The hosted server and this package expose the same API; run the package locally when you want stdio, your own network egress, or to self-host it.

Run it locally

Claude Code

claude mcp add piloterr --env PILOTERR_API_KEY=YOUR_API_KEY -- npx -y @piloterr/mcp

Claude Desktop, Cursor, Windsurf and other clients

Add the server to the client's MCP configuration (claude_desktop_config.json, .cursor/mcp.json…):

{

"mcpServers": { "piloterr": { "command": "npx", "args": ["-y", "@piloterr/mcp"], "env": { "PILOTERR_API_KEY": "YOUR_API_KEY" } } } }

VS Code

{

"servers": { "piloterr": { "type": "stdio", "command": "npx", "args": ["-y", "@piloterr/mcp"], "env": { "PILOTERR_API_KEY": "${input:piloterr-api-key}" } } }, "inputs": [ { "type": "promptString", "id": "piloterr-api-key", "description": "Piloterr API key", "password": true } ] }

Claude Desktop extension

Download the .mcpb bundle from the releases page and open it; Claude Desktop asks for your API key.

Docker

docker build -t piloterr-mcp .

docker run -i --rm -e PILOTERR_API_KEY=YOUR_API_KEY piloterr-mcp

Tools

Piloterr has 391 endpoints, more than a client should load as separate tools. The server exposes a small catalog instead: the model searches it, reads an endpoint's parameters, then calls it.

Every tool that calls the API consumes credits. JSON results are returned as text; images are returned inline and other files (PDF…) as embedded resources, up to 4 MB.

Streamable HTTP

npx @piloterr/mcp --http --port 3000

The endpoint is POST /mcp (stateless, JSON responses). Each client sends its own key in the x-api-key header (or Authorization: Bearer ); the server never uses a key of its own. It binds to 127.0.0.1 by default and rejects browser origins unless you allow them — put it behind TLS before exposing it.

createHttpHandler() is exported for Fetch-compatible runtimes (Cloudflare Workers, Deno, Bun):

import { createHttpHandler } from "@piloterr/mcp";

export default { fetch: createHttpHandler({ allowedOrigins: [] }) };

Security

• The API key is read from PILOTERR_API_KEY (stdio) or the request headers (HTTP) and removed from error messages.
• Content fetched from websites is untrusted: the server instructions tell the model to treat it as data, not instructions.
• See SECURITY.md to report a vulnerability.

Development

npm install

npm test npm run build npx @modelcontextprotocol/inspector node dist/stdio.js

Built on the SDK

The server uses the official Node.js SDK (@piloterr/sdk).

All Piloterr SDKs

License

MIT — see LICENSE.