Pipedream MCP Server allows you to run your own Model Context Protocol server for over 2,700 apps and APIs, powered by Pipedream Connect. With this implementation, you can host MCP servers for yourself or your users, making it easy to connect accounts, configure parameters, and make API requests through tools.
Before installing the MCP server, you'll need:
PIPEDREAM_CLIENT_ID=your_client_id
PIPEDREAM_CLIENT_SECRET=your_client_secret
PIPEDREAM_PROJECT_ID=your_project_id
PIPEDREAM_PROJECT_ENVIRONMENT=development
If you have Docker installed locally, you can build and run the container:
docker build -t pipedream-connect .
docker run -d --name pd-mcp -p 3010:3010 --env-file .env pipedream-connect:latest
This exposes a generic MCP server at http://localhost:3010/:external_user_id/:app
The MCP server can be used in two different ways:
Access pattern: /{external_user_id}/{app}
This approach provides an endpoint for each specific app. All tools available for that app will be accessible at that endpoint.
Access pattern: /{external_user_id}
This is an experimental version that relies on tools being able to update dynamically.
When running MCP servers for your application, you'll likely want to use the SSE interface. The SSE server accepts two route parameters:
external_user_id
- Your user's unique identifier in your systemapp
- The app's "name slug" (unique identifier for the app)For example, if user "123" wants to connect to the Slack MCP server, your MCP client would make a request to the /123/slack
route.
After starting your server, you can test it using the MCP Inspector:
npx @modelcontextprotocol/inspector
Use one of these URLs in the inspector:
http://localhost:3010/v1/{external_user_id}/{app}
for Streamable HTTP Transporthttp://localhost:3010/{external_user_id}/{app}
for SSE TransportYou can enable debug mode to see all requests and responses going to the Connect API:
PD_SDK_DEBUG=true pnpm dev:http
For development purposes, you can start the server with:
pnpm dev:http
Stdio transport has only been tested with the MCP Inspector:
npx @modelcontextprotocol/inspector bun src/stdio.ts
After connecting in the inspector, press "List Tools" to fetch the list of available MCP tools.
To add this MCP server to Claude Code, run this command in your terminal:
claude mcp add-json "pipedream" '{"command":"npx","args":["@pipedream/mcp"]}'
See the official Claude Code MCP documentation for more details.
There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json
file so that it is available in all of your projects.
If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json
file.
To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".
When you click that button the ~/.cursor/mcp.json
file will be opened and you can add your server like this:
{
"mcpServers": {
"pipedream": {
"command": "npx",
"args": [
"@pipedream/mcp"
]
}
}
}
To add an MCP server to a project you can create a new .cursor/mcp.json
file or add it to the existing one. This will look exactly the same as the global MCP server example above.
Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.
The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.
You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.
To add this MCP server to Claude Desktop:
1. Find your configuration file:
~/Library/Application Support/Claude/claude_desktop_config.json
%APPDATA%\Claude\claude_desktop_config.json
~/.config/Claude/claude_desktop_config.json
2. Add this to your configuration file:
{
"mcpServers": {
"pipedream": {
"command": "npx",
"args": [
"@pipedream/mcp"
]
}
}
}
3. Restart Claude Desktop for the changes to take effect