Piloterr MCP Server
OfficialEnables scraping Amazon pages through the Piloterr API and returning structured JSON data.
Enables scraping Crunchbase pages through the Piloterr API and returning structured JSON data.
Enables scraping Google pages through the Piloterr API and returning structured JSON data.
Enables scraping Zillow pages through the Piloterr API and returning structured JSON data.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Piloterr MCP Server scrape the Amazon product at amazon.com/dp/B08N5WRWNW"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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
Related MCP server: Foundry API MCP Server
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/mcpClaude 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-mcpTools
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.
Tool | Description |
| Search the 391 Piloterr endpoints. |
| Describe the parameters of one endpoint. |
| Call one Piloterr endpoint and return the result. |
| Show API usage and remaining credits. |
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 3000The endpoint is POST /mcp (stateless, JSON responses). Each client sends its own key in the x-api-key header (or Authorization: Bearer <key>); 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.jsBuilt on the SDK
The server uses the official Node.js SDK (@piloterr/sdk).
All Piloterr SDKs
SDK | Package | Install |
Node.js |
| |
Python |
| |
Go |
| |
.NET |
| |
Ruby |
| |
PHP |
| |
Java | build from source, see its README | |
CLI |
| |
MCP server |
|
License
MIT — see LICENSE.
Available Tools
4 toolscall_endpointCall a Piloterr endpointARead-onlyInspect
Calls one Piloterr endpoint with its parameters and returns the result. Each call consumes credits. Use get_endpoint first to learn the parameters.
Inputs: name (required), params.
get_endpointDescribe a Piloterr endpointARead-onlyInspect
Returns the description and parameters (names, types, required, allowed values) of one endpoint.
Inputs: name (required).
search_endpointsSearch Piloterr endpointsARead-onlyInspect
Search the 391 Piloterr endpoints by website, keyword or path (for example "amazon", "linkedin job", "zillow"). Returns endpoint names to use with get_endpoint and call_endpoint.
Inputs: limit, query.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool has a clearly distinct role in the discovery-to-execution workflow: search_endpoints finds endpoints, get_endpoint inspects schema, call_endpoint executes, and usage reports account credits. The descriptions explicitly explain how they relate and when to use each, leaving no meaningful overlap.
The three action tools follow a consistent verb_noun pattern (search_endpoints, get_endpoint, call_endpoint), and usage is a minor deviation as a bare noun. The convention remains predictable and readable.
Four tools are exactly right for a facade over a large API: discovery, schema inspection, execution, and account usage. Each tool earns its place without redundant operations.
The core lifecycle for using Piloterr endpoints is covered: search, inspect, call, and check credits. Minor gaps exist around batch operations, endpoint listing without search, or account management, but agents can work around them.
Maintenance
Related MCP Connectors
Query SEC EDGAR filings, XBRL financials, and company data via MCP. STDIO or Streamable HTTP.
One MCP server for 180+ live web-data APIs returning clean JSON from sites that block scrapers.
ScrapeCreators MCP — wraps the ScrapeCreators social-media + ad-library scraping API…
Remote MCP for 1,500+ APIs. Vault-managed credentials; OAuth or API key. Search, load, and execute.
Related MCP Servers
AlicenseCqualityBmaintenanceHosted MCP server for 3926 structured public web-data tools across 488 platform groups, returning clean JSON for search, maps, commerce, social, and finance.14500308 npm1MIT- AlicenseNot gradedqualityCmaintenanceProvides bounded API tools for web page rendering, document extraction, B2B enrichment, local business search, and more via MCP protocol.MIT
- AlicenseNot gradedqualityDmaintenanceProvides a single MCP endpoint for 90+ tools across 42 backend servers (search, legal, domain, etc.) with per-call credit billing and a single API key.1MIT
- FlicenseNot gradedqualityAmaintenanceEnables MCP clients to scrape web pages, extract structured data, search, crawl sites, generate schemas, schedule monitors, and inspect credits/history through hosted or local integrations.-