Pipedream MCP Server Details

Pipedream MCP Server is a reference implementation for self-hosting a Model Context Protocol (MCP) server. It showcases how to manage and serve MCP-based apps and tools in your own environment, providing you with a way to run MCP servers locally or within your organization. Note that this MCP server is a reference implementation and is no longer actively maintained; for production workloads, Pipedream recommends using the remote MCP server, which offers hosted reliability and scaling. The server supports two primary modes and integrates with Pipedream Connect for authentication and API management, enabling automatic app discovery and credential storage with enterprise-grade security.

Use Case

This MCP server allows you to run your own MCP server to manage apps and tools within your own app or company. It supports app-specific endpoints and a dynamic mode that powers tools on sites like chat.pipedream.com. Use cases include connecting accounts, configuring parameters, making API requests via MCP tools, and handling OAuth and credential storage. The server can be run locally or hosted yourself and exposes Streamable HTTP Transport and SSE Transport for client interactions. Example usage from the docs includes running the server, starting with environment configuration, and inspecting requests with the MCP Inspector. Example commands:

  • Copy and configure environment:

  • cp .env.example .env
    # Fill in PD client ID/secret, project ID, and environment
  • Start the server with Streamable HTTP Transport:

  • pnpm dev:http
  • Debug requests/responses (optional):

  • PD_SDK_DEBUG=true pnpm dev:http
  • Run the inspector:

  • npx @modelcontextprotocol/inspector
  • Access Streamable HTTP Transport URL:

  • http://localhost:3010/v1/{external_user_id}/{app}
    or for SSE Transport:
    http://localhost:3010/{external_user_id}/{app}
  • Stdio Transport setup (inspector):

  • npx @modelcontextprotocol/inspector bun src/stdio.ts

    These commands illustrate how to configure and run the MCP server, inspect interactions, and use both HTTP and SSE transport modes. The documentation also notes that you can fetch the list of MCP tools via the Stdio transport by clicking "List Tools".

    Examples & Tutorials

    PIPEDREAM_CLIENT_ID=your_client_id
    PIPEDREAM_CLIENT_SECRET=your_client_secret
    PIPEDREAM_PROJECT_ID=your_project_id
    PIPEDREAM_PROJECT_ENVIRONMENT=development

    pnpm install

    pnpm dev:http

    PD_SDK_DEBUG=true pnpm dev:http

    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.

    npx @modelcontextprotocol/inspector bun src/stdio.ts

    See the logs for the inspector URL and use the inspector to verify MCP tool interactions.

    Installation Guide

  • Copy environment configuration: cp .env.example .env and fill in the details.

  • Install dependencies: pnpm install.

  • Start the server with Streamable HTTP Transport: pnpm dev:http. Optional: debug requests with PD_SDK_DEBUG=true pnpm dev:http.

  • Run the MCP Inspector: npx @modelcontextprotocol/inspector.

  • Access the Streamable HTTP Transport URL: http://localhost:3010/v1/{external_user_id}/{app} or the SSE URL: http://localhost:3010/{external_user_id}/{app}.

  • For Stdio Transport, run: npx @modelcontextprotocol/inspector bun src/stdio.ts and check logs for the inspector URL.
  • Frequently Asked Questions

    Is this your MCP?

    Claim ownership and get verified badge

    Repository Stats
    Important Notes

    This MCP server is a reference implementation for self-hosting and is not actively maintained. For production use, Pipedream strongly recommends using the remote MCP server. The reference implementation may not be fully documented, and there are two server usage modes: App-specific endpoints and a Dynamic mode that powers tools on chat.pipedream.com. The SSE interface accepts two route parameters: external_user_id and app.

    Prerequisites

    Sign up for Pipedream, create a project, and create a Pipedream OAuth client. You will need Pipedream API credentials to run the MCP server. Environment variables must be set in a .env file, including PD_CLIENT_ID, PD_CLIENT_SECRET, PD_PROJECT_ID, and PD_PROJECT_ENVIRONMENT as shown in the docs.

    Details
    Last Updated1/1/2026
    SourceGitHub

    Compare Alternatives

    Similar MCP Tools

    6 related tools
    Anki MCP Server

    Anki MCP Server

    A Model Context Protocol (MCP) server that enables AI assistants to interact with Anki, the spaced repetition flashcard application. The Anki MCP Server allows AI models to access Anki's card data, enabling features like automated flashcard creation, review, and management.

    1MCP Agent

    1MCP Agent

    A unified Model Context Protocol server implementation that aggregates multiple MCP servers into one. The 1mcp-app/agent is an open-source project that provides a single entry point for multiple MCP servers, making it easier to manage and interact with various AI models and tools.

    Roundtable AI MCP Server

    Roundtable AI MCP Server

    Roundtable AI MCP Server is a zero-configuration local MCP server that unifies multiple AI coding assistants (Codex, Claude Code, Cursor, Gemini) through intelligent auto-discovery and a standardized interface. It coordinates specialized sub-agents from within your IDE to solve engineering problems in parallel, sharing context and synthesizing responses into a single, high-quality output. This documentation details installation, available MCP tools, integration with popular IDEs, and a broad ecosystem of specialized tools and CLIs that can be invoked as part of a roundtable-powered workflow, enabling developers to delegate tasks to the right AI for each facet of a problem without leaving their development environment.

    MCPJungle

    MCPJungle

    MCPJungle is a self-hosted MCP Gateway and Registry for AI agents. It serves as a central registry and gateway to manage Model Context Protocol (MCP) servers and the tools they expose. By consolidating MCP server registration, tool discovery, and access control, MCPJungle enables AI agents and clients to discover, group, and securely invoke tools from a single, unified gateway. The project provides a CLI, Docker-based deployment options, and enterprise-ready features such as tool grouping, access control, and observability to streamline MCP-based workflows across organizations.

    mcpmcp-server

    mcpmcp-server

    mcpmcp-server is a focused solution for discovering, setting up, and integrating MCP servers with your favorite clients to unlock AI-powered workflows. It streamlines how you connect MCP-powered servers to popular clients, enabling seamless AI-assisted interactions across your daily tools. The project emphasizes an approachable, config-driven approach to linking MCP servers with clients like Claude Desktop, while directing you to the homepage for variations across apps and platforms. This README highlights a practical JSON configuration example and notes on supported environments, helping you get started quickly and confidently.

    Imagen3-MCP

    Imagen3-MCP

    Imagen3-MCP is an image generation service based on Google's Imagen 3.0 that exposes its functionality through MCP (Model Control Protocol). The project provides a server to run a local MCP service that accesses Google Gemini-powered image generation, enabling developers to integrate advanced image synthesis into their applications. The documentation covers prerequisites (Gemini API key), installation steps for Cherry Studio, and a Cursor-based JSON configuration example for embedding the MCP server in broader tooling. This MCP is designed to be deployment-friendly, with configurable environment variables and optional proxy settings to adapt to various network environments.