Scrape over 300 websites including Amazon, LinkedIn, and Google as structured JSON using an AI client.
Also known as piloterr/piloterr-mcp, piloterr-mcp, @piloterr/mcp
- Stars
- 0
- Tools
- 4
- Downloads, 30 days
- —
- Latest version
- 0.1.0
- Last commit
- Nov 11, 2026
- License
- MIT
What is Piloterr MCP?
Piloterr is an MCP server. Scrape over 300 websites including Amazon, LinkedIn, and Google as structured JSON using an AI client. It exposes 4 tools, such as search_endpoints, get_endpoint, call_endpoint.
Summary generated from the project's README
About Piloterr MCP server
Piloterr provides a way for AI clients to scrape data from over 300 websites like Amazon, LinkedIn, and Google. It converts web content into structured JSON format, making it easy for models to process information from sites such as Zillow or Crunchbase. Developers can use this server with Claude, Cursor, VS Code, or Windsurf by setting up a local connection via stdio or using the hosted Streamable HTTP service.
To use the server, you need a Piloterr API key. The implementation includes specific tools to manage the large number of available endpoints. Instead of loading all 391 endpoints at once, the server uses search_endpoints, get_endpoint, and call_endpoint to allow the model to find and execute the correct scraping tasks. You can also use the usage tool to monitor your remaining API credits. The server supports various deployment methods including Docker, local npx execution, or self-hosting via Node.js 20 or newer.
What you can do with it
- 1Extract structured web dataAsk your AI client to scrape specific product or profile information from major websites as JSON.
- 2Discover specific scraping endpointsHave the AI search through the extensive list of available API functions to find the right tool for a task.
- 3Monitor API consumptionCheck how many credits you have left to ensure your scraping tasks continue without interruption.
- 4Retrieve embedded media filesRequest images or documents from websites and receive them as inline or embedded resources.
Written from the project's README. Every use case is checked against a quote from it.
How to install Piloterr MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Piloterr MCP in Claude Code
$ claude mcp add --env 'PILOTERR_API_KEY=<YOUR_PILOTERR_API_KEY>' piloterr-mcp -- npx -y @piloterr/mcpInstall Piloterr MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"piloterr-mcp": {
"command": "npx",
"args": [
"-y",
"@piloterr/mcp"
],
"env": {
"PILOTERR_API_KEY": "<YOUR_PILOTERR_API_KEY>"
}
}
}
}Install Piloterr MCP in VS Code
.vscode/mcp.json
{
"servers": {
"piloterr-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@piloterr/mcp"
],
"env": {
"PILOTERR_API_KEY": "<YOUR_PILOTERR_API_KEY>"
}
}
}
}Install Piloterr MCP in VS Code CLI
$ code --add-mcp '{"name":"piloterr-mcp","type":"stdio","command":"npx","args":["-y","@piloterr/mcp"],"env":{"PILOTERR_API_KEY":"<YOUR_PILOTERR_API_KEY>"}}'Install Piloterr MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"piloterr-mcp": {
"command": "npx",
"args": [
"-y",
"@piloterr/mcp"
],
"env": {
"PILOTERR_API_KEY": "<YOUR_PILOTERR_API_KEY>"
}
}
}
}Install Piloterr MCP in Codex
$ codex mcp add piloterr-mcp --env 'PILOTERR_API_KEY=<YOUR_PILOTERR_API_KEY>' -- npx -y @piloterr/mcpInstall Piloterr MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.piloterr-mcp] command = "npx" args = ["-y", "@piloterr/mcp"] [mcp_servers.piloterr-mcp.env] PILOTERR_API_KEY = "<YOUR_PILOTERR_API_KEY>"
Install Piloterr MCP in Gemini CLI
$ gemini mcp add -s user -e 'PILOTERR_API_KEY=<YOUR_PILOTERR_API_KEY>' piloterr-mcp npx -- -y @piloterr/mcpInstall Piloterr MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"piloterr-mcp": {
"command": "npx",
"args": [
"-y",
"@piloterr/mcp"
],
"env": {
"PILOTERR_API_KEY": "<YOUR_PILOTERR_API_KEY>"
}
}
}
}Needs a key before it starts
Started on 16 Nov 2026 with no keys, it stopped and asked for one, so a client sees no tools until you set the variables above.
Piloterr MCP tools 4
Detected from the READMEsearch_endpointsget_endpointcall_endpointusage
Configuration
PILOTERR_API_KEYRequiredSecretPiloterr API key.
Automated checks
Ran Nov 12, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachablePass
- Open source license (OSI)Pass
- Commit or release in the last yearPass
- Package name not close to a popular packagePass
- Remote endpoint uses HTTPSPass
- Destructive tools are labelledPass
- No hidden instructions to the modelPass
- No critical advisory in the package or its dependenciesPass
README
View on GitHubPiloterr 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
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.
| Tool | Description |
|---|---|
search_endpoints |
Search the 391 Piloterr endpoints. |
get_endpoint |
Describe the parameters of one endpoint. |
call_endpoint |
Call one Piloterr endpoint and return the result. |
usage |
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 3000
The 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.js
Built on the SDK
The server uses the official Node.js SDK (@piloterr/sdk).
All Piloterr SDKs
| SDK | Package | Install |
|---|---|---|
| Node.js | @piloterr/sdk |
npm install @piloterr/sdk |
| Python | piloterr |
pip install piloterr |
| Go | piloterr-go |
go get github.com/piloterr/piloterr-go |
| .NET | Piloterr |
dotnet add package Piloterr |
| Ruby | piloterr |
gem install piloterr |
| PHP | piloterr/sdk |
composer require piloterr/sdk |
| Java | piloterr-java |
build from source, see its README |
| CLI | @piloterr/cli |
npm install -g @piloterr/cli |
| MCP server | @piloterr/mcp |
npx -y @piloterr/mcp |
License
MIT — see LICENSE.
Piloterr MCP questions
How do I add Piloterr MCP to Claude Code?
Run claude mcp add --env 'PILOTERR_API_KEY=<YOUR_PILOTERR_API_KEY>' piloterr-mcp -- npx -y @piloterr/mcp in your terminal. Add --scope user to make it available in every project.
How do I add Piloterr MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What tools does Piloterr MCP provide?
It exposes 4 tools, including search_endpoints, get_endpoint, call_endpoint, usage.
What websites can I scrape with Piloterr?
You can scrape over 300 websites, including major platforms like Amazon, LinkedIn, Google, Zillow, and Crunchbase.
How does the server handle the large number of available endpoints?
Instead of loading all 391 endpoints as separate tools, the server provides a small catalog that allows the model to search, describe, and call endpoints as needed.
What formats are returned when scraping?
JSON results are returned as text, images are returned inline, and other files like PDFs are returned as embedded resources up to 4 MB.
Can I run this server without installing anything?
Yes, you can use the hosted server at mcp.piloterr.com via Streamable HTTP by providing your API key in the header.