@pipedream/mcp
This is a reference implementation of the Pipedream MCP server. You can run **your own MCP server** for [over 2,700 apps and APIs](https://pipedream.com/apps) and is powered by [Pipedream Connect](https://pipedream.com/docs/connect/).
Markdown Content: Pipedream MCP Server
This is a reference implementation of the Pipedream MCP server. You can run your own MCP server for over 2,700 apps and APIs and is powered by Pipedream Connect.
[Note] These docs discuss how you can host Pipedream's MCP server in your own app or run it locally. To use Pipedream's remote MCP server (most common), refer to our docs to get started.
This reference implementation shows how you can:
- Run the servers locally with
npx @pipedream/mcp - Host the servers yourself to use them within your app or company
See the consumer-facing MCP server in action at mcp.pipedream.com and check out a demo of the developer-facing product at chat.pipedream.com.
We published this code as a reference, so you can better understand how to use Pipedream Connect for such an application. This is a reference implementation specifically for self-hosting the server and may not be fully documented. Please reach out to us if you have any questions.
⭐ Features
- Run your own MCP server for over 2,700 apps and APIs
- Manage servers for your users, in your own app.
- Connect accounts, configure params, and make API requests, all via tools
- Fully-managed OAuth and credential storage (see security docs)
🚀 Getting Started
Pipedream's MCP servers use the Pipedream Connect API to manage auth and make API requests. To run an MCP server, you'll need a Pipedream project and Pipedream API credentials.
- Sign up for Pipedream
- Create a project. Any accounts connected via MCP will be stored here.
- Create a Pipedream OAuth client
- Set the environment variables (See
.env.example) (directly in your shell session, dot files, etc.):
PIPEDREAM_CLIENT_ID=your_client_id PIPEDREAM_CLIENT_SECRET=your_client_secret PIPEDREAM_PROJECT_ID=your_project_id PIPEDREAM_PROJECT_ENVIRONMENT=development
Pipedream concepts to understand
If you're running MCP servers for your app, you'll likely want to use the SSE interface. The SSE server accepts two route params:
external_user_id—This is your user’s ID, in your system — whatever you use to uniquely identify them. Any requests made to that route are coupled to that end user, and would use the auth Pipedream stores for that user. See the docs for more detail.app—The app's "name slug" (the unique identifier for the app), found in the Authentication section of any Pipedream app. For example, the app slug for Slack isslack.
If your user 123 wants to connect to the slack MCP server, your MCP client would make a request to the /123/slack route. See the SSE docs below for more detail.
Server overview
There are two ways to use this MCP server.
1 - App specific /{external_user_id}/{app} This is currently available at mcp.pipedream.com. You can use an endpoint for each app. All the tools available for that app will be available at that endpoint.
2 - Dynamic /{external_user_id} This is an experimental version, since it relies on tools being able to update dynamically. We use this server to power the tools on chat.pipedream.com.
[!NOTE] >Check out the docs to learn more about enabling app discovery with the MCP server.
Hosting your own server
Using the Dockerfile
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.
Development
cp .env.example .env and fill in the details of your dev project.
pnpm install
Start the server with Streamable HTTP Transport
pnpm dev:http
You can use the optional env var PD_SDK_DEBUG to print out all the requests and responses going to the Connect API
PD_SDK_DEBUG=true pnpm dev:http
Then run the inspector:
npx @modelcontextprotocol/inspector
Use http://localhost:3010/v1/{external_user_id}/{app} for Streamable HTTP Transport or http://localhost:3010/{external_user_id}/{app} for SSE Transport.
These URLs can also be used by other clients (e.g. Cursor).
Stdio Transport setup
Stdio has only been tested with the MCP Inspector.
npx @modelcontextprotocol/inspector bun src/stdio.ts
See the logs for the inspector URL.
Ensure the left side of the inspector matches this:
Then press "List Tools" to fetch the list of MCP tools.
License
Pipedream Source Available License Version 1.0 - See https://github.com/PipedreamHQ/pipedream/blob/master/LICENSE
Recommend MCP Servers 💡
@neondatabase/mcp-server-neon
Neon MCP Server is an open-source tool that lets you interact with your Neon Postgres databases in natural language.
server-sharepoint
An MCP server for Claude Desktop that enables seamless interaction with SharePoint Online through the SharePoint REST API.
mcp-konnect
A Model Context Protocol (MCP) server enabling AI assistants to interact with Kong Konnect APIs for querying and analyzing gateway configurations, traffic, and analytics.
attio-mcp-server
This is an MCP server for [Attio](https://attio.com/), the AI-native CRM. It allows mcp clients (like Claude) to connect to the Attio API.

reza-gholizade/k8s-mcp-server
Manage Your Kubernetes Cluster with k8s mcp-server
metoro-mcp-server
Metoro MCP Server allows you to interact with your Kubernetes cluster via the Claude Desktop App!