Pipedream

Pipedream

Official
pipedreamhq

Connect to 2,500+ APIs through hosted MCP servers or deploy your own, with built-in authentication for services like Slack, GitHub, Notion, and Google Drive.

Access hosted MCP servers or deploy your own for 2,500+ APIs like Slack, GitHub, Notion, Google Drive, and more, all with built-in auth and 10k tools.

11,137410 views5,597Local (stdio)

What it does

  • Access 2,500+ APIs with built-in authentication
  • Deploy custom MCP servers on hosted platform
  • Connect to Slack, GitHub, Notion, Google Drive APIs
  • Use 10,000+ pre-built integration tools
  • Run Node.js, Python, Golang, or Bash code
  • Build event-driven automations

Best for

Developers building integrations without handling authTeams automating workflows across multiple servicesApplications needing rapid API connectivity
Built-in auth for 2,500+ APIs10k tools availableSOC 2 compliant hosting

About Pipedream

Pipedream is an official MCP server published by pipedreamhq that provides AI assistants with tools and capabilities via the Model Context Protocol. Pipedream — Access hosted MCP servers or deploy your own for 2,500+ APIs (Slack, GitHub, Notion, Google Drive) with buil It is categorized under developer tools.

How to install

You can install Pipedream in your AI client of choice. Use the install panel on this page to get one-click setup for Cursor, Claude Desktop, VS Code, and other MCP-compatible clients. This server runs locally on your machine via the stdio transport.

License

Pipedream is released under the NOASSERTION license.

pipedream

README imageLink to pipedream.com README imageLink to pipedream.com README imageLink to twitter.com README imageLink to wellfound.com

Pipedream is an integration platform for developers.

Pipedream provides a free, hosted platform for connecting apps and developing event-driven automations. The platform has over 1,000 fully-integrated applications, so you can use pre-built components to quickly send messages to Slack, add a new row to Google Sheets, and more. You can also run any Node.js, Python, Golang, or Bash code when you need custom logic. Pipedream has demonstrated SOC 2 compliance and can provide a SOC 2 Type 2 report upon request (please email [email protected]).


HTTP trigger + step selection menu

This repo contains:

This README explains the key features of the platform and how to get started.

To get support, please visit https://pipedream.com/support.

Key Features

  • Workflows - Workflows run automations. Workflows are sequences of steps - pre-built actions or custom Node.js, Python, Golang, or Bash code - triggered by an event (HTTP request, timer, when a new row is added to a Google Sheets, and more).
  • Event Sources - Sources trigger workflows. They emit events from services like GitHub, Slack, Airtable, RSS and more. When you want to run a workflow when an event happens in any third-party app, you're using an event source.
  • Actions - Actions are pre-built code steps that you can use in a workflow to perform common operations across Pipedream's 1,000+ API integrations. For example, you can use actions to send email, add a row to a Google Sheet, and more.
  • Custom code - Most integrations require custom logic. Code is often the best way to express that logic, so Pipedream allows you to run any Node.js, Python, Golang, or Bash code. You can import any package from the languages' package managers, connect to any Pipedream connected app, and more. Pipedream is "low-code" in the best way: you can use pre-built components when you're performing common actions, but you can write custom code when you need to.
  • Destinations - Deliver events asynchronously to common destinations like Amazon S3, Snowflake, HTTP and email.
  • Free - No fees for individual developers (see limits)

Demo

Click the image below to watch a brief demo on YouTube.


Pipedream demo static image

Workflows

Workflows are sequences of linear steps triggered by an event (like an HTTP request, or when a new row is added to a Google sheet). You can quickly develop complex automations using workflows and connect to any of our 1,000+ integrated apps.

See our workflow quickstart to get started.

Event Sources

Event Sources watch for new data from services like GitHub, Slack, Airtable, RSS and more. When a source finds a new event, it emits it, triggering any linked workflows.

You can also consume events emitted by sources using Pipedream's REST API or a private, real-time SSE stream.

When a pre-built source doesn't exist for your use case, you can build your own. Here is the simplest event source: it exposes an HTTP endpoint you can send any request to, and prints the contents of the request when invoked:

export default {
  name: "http",
  version: "0.0.1",
  props: {
    http: "$.interface.http",
  },
  run(event) {
    console.log(event); // event contains the method, payload, etc.
  },
};

README imageLink to pipedream.com

You can find the code for all pre-built sources in the components directory. If you find a bug or want to contribute a feature, see our contribution guide.

Actions

Actions are pre-built code steps that you can use in a workflow to perform common operations across Pipedream's 500+ API integrations. For example, you can use actions to send email, add a row to a Google Sheet, and more.

You can create your own actions, which you can re-use across workflows. You can also publish actions to the entire Pipedream community, making them available for anyone to use.

Here's an action that accepts a name as input and prints it to the workflow's logs:

export default {
  name: "Action Demo",
  description: "This is a demo action",
  key: "action_demo",
  version: "0.0.1",
  type: "action",
  props: {
    name: {
      type: "string",
      label: "Name",
    },
  },
  async run() {
    return `hello ${this.name}!`;
  },
};

You can find the code for all pre-built actions in the components directory. If you find a bug or want to contribute a feature, see our contribution guide.

Custom code

Most integrations require custom logic. Code is often the best way to express that logic, so Pipedream allows you to run custom code in a workflow using:

Node.js Python
Go Bash

You can import any package from the languages' package managers by declaring the imports directly in code. Pipedream will parse and download the necessary dependencies.

// Node.js
import axios from "axios";
# Python
import pandas as pd
// Go
import (
    "fmt"
    pd "github.com/PipedreamHQ/pipedream-go"
)

You can also connect to any Pipedream connected app in custom code steps. For example, you can connect your Slack account and send a message to a channel:

import { WebClient } from "@slack/web-api";

export default defineComponent({
  props: {
    // This creates a connection called "slack" that connects a Slack account.
    slack: {
      type: "app",
      app: "slack",
    },
  },
  async run({ steps, $ }) {
    const web = new WebClient(this.slack.$auth.oauth_access_token);

    return await web.chat.postMessage({
      text: "Hello, world!",
      channel: "#general",
    });
  },
});

Destinations

Destinations, like actions, abstract the connection, batching, and delivery logic required to send events to services like Amazon S3, or targets like HTTP and email.

For example, sending data to an Amazon S3 bucket is as simple as calling $send.s3():


---

*README truncated. [View full README on GitHub](https://github.com/pipedreamhq/pipedream/tree/HEAD/modelcontextprotocol).*

Alternatives

Related Skills

Browse all skills
ui-design-system

UI design system toolkit for Senior UI Designer including design token generation, component documentation, responsive design calculations, and developer handoff tools. Use for creating design systems, maintaining visual consistency, and facilitating design-dev collaboration.

18
ai-sdk

Answer questions about the AI SDK and help build AI-powered features. Use when developers: (1) Ask about AI SDK functions like generateText, streamText, ToolLoopAgent, embed, or tools, (2) Want to build AI agents, chatbots, RAG systems, or text generation features, (3) Have questions about AI providers (OpenAI, Anthropic, Google, etc.), streaming, tool calling, structured output, or embeddings, (4) Use React hooks like useChat or useCompletion. Triggers on: "AI SDK", "Vercel AI SDK", "generateText", "streamText", "add AI to my app", "build an agent", "tool calling", "structured output", "useChat".

6
api-documenter

Master API documentation with OpenAPI 3.1, AI-powered tools, and modern developer experience practices. Create interactive docs, generate SDKs, and build comprehensive developer portals. Use PROACTIVELY for API documentation or developer portal creation.

4
openai-knowledge

Use when working with the OpenAI API (Responses API) or OpenAI platform features (tools, streaming, Realtime API, auth, models, rate limits, MCP) and you need authoritative, up-to-date documentation (schemas, examples, limits, edge cases). Prefer the OpenAI Developer Documentation MCP server tools when available; otherwise guide the user to enable `openaiDeveloperDocs`.

4
cli-builder

Guide for building TypeScript CLIs with Bun. Use when creating command-line tools, adding subcommands to existing CLIs, or building developer tooling. Covers argument parsing, subcommand patterns, output formatting, and distribution.

3
ydc-ai-sdk-integration

Integrate Vercel AI SDK applications with You.com tools (web search, AI agent, content extraction). Use when developer mentions AI SDK, Vercel AI SDK, generateText, streamText, or You.com integration with AI SDK.

2