Pipedream logo

Pipedream

OrganizationPopular
pipedreamhq

Connect APIs, remarkably fast. Free for developers.

Publisherpipedreamhq
Repositorypipedream
LanguageJavaScript
Forks
5.7K
Stars
11.3K
Available tools
0
Transport typestdio
Categories
LicenseNOASSERTION
Links
  • Connect tools to AI workflows

    Pipedream exposes MCP capabilities that can be used by compatible AI clients and agents.

  • 0 available tools

    Browse the callable actions below, including names and descriptions when provided by the server.

  • Ready-to-copy setup

    Use the installation snippets to configure this server in your preferred MCP client.

  • Open source signals

    11.3K stars and 5.7K forks from the linked repository.

pipedream

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 support@pipedream.com).

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.

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:

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

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:

javascript
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:

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.

javascript
// Node.js
import axios from "axios";
python
# Python
import pandas as pd
golang
// 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:

javascript
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():

javascript
$send.s3({
  bucket: "your-bucket-here",
  prefix: "your-prefix/",
  payload: event.body,
});

Pipedream supports the following destinations:

Contributors

Thank you to everyone who has contributed to the Pipedream codebase. We appreciate you!

Pricing

Pipedream has a generous free tier. You can run sources and workflows for free within the limits of the free tier. If you hit these limits, you can upgrade to one of our paid tiers.

Limits

The Pipedream platform imposes some runtime limits on sources and workflows. Read more about those in our docs.

Found a Bug? Have a Feature to suggest?

Before adding an issue, please search the existing issues or reach out to our team to see if a similar request already exists.

If an issue exists, please add a reaction or add a comment detailing your specific use case.

If an issue doesn't yet exist and you need to create one, please use the issue templates.

Security

You can read about our platform security and privacy here.

If you'd like to report a suspected vulnerability or security issue, or have any questions about the security of the product, please contact our security team at security@pipedream.com.

Installation

TypingMind
Prerequisites:

Node.js 18+

{
  "mcpServers": {
    "pipedream-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@pipedream/mcp"
      ]
    }
  }
}

Use Pipedream MCP with multiple AI models

TypingMind connects MCP tools at the workspace level, so once Pipedream is connected, you can use it with different AI models in TypingMind instead of setting it up separately for each model. This MCP runs locally through the TypingMind MCP connector on your device.

Setup guide to use the local connector

Use this when the MCP server needs access to local files, apps, or private resources on your computer.

1

Open the MCP settings

In TypingMind, go to Settings, Advanced Settings, then Model Context Protocol and choose Setup Connector.

  1. Open TypingMind in your browser.
  2. Click the Settings icon.
  3. Go to Advanced Settings.
  4. Open the Model Context Protocol section.
  5. Click Setup Connector and choose This Device.
TypingMind MCP connector setup screen with This Device selected
2

Run the connector command

Choose This Device, copy the command from TypingMind, and run it in Terminal. Keep the process running while you use MCP.

  1. Copy the setup command shown by TypingMind.
  2. Open Terminal on macOS or Windows Terminal on Windows.
  3. Paste and run the command.
  4. Approve the package install if Terminal asks you to proceed.
  5. Keep the Terminal window running while using MCP tools.
3

Add Pipedream as a server

When the connector status is Ready, click Edit Servers and paste the MCP server configuration.

  1. Wait until the connector status shows Ready.
  2. Click Edit Servers.
  3. Paste the Pipedream MCP server configuration.
  4. Save the server list.
  5. Refresh if you want to confirm the connector is still ready.
TypingMind MCP settings showing active server and Edit Servers button
{
  "mcpServers": {
    "pipedream": {
      "command": "npx",
      "args": [
        "-y",
        "@pipedream/mcp"
      ]
    }
  }
}
4

Use it across models

Save the server list, open Plugins, enable the Pipedream MCP tools, then select any supported AI model in TypingMind and use the tools in chat or assign them to an AI agent.

  1. Open the Plugins page in TypingMind.
  2. Enable the Pipedream MCP tools.
  3. Start a chat and choose the AI model you want to use.
  4. Use the MCP tools in chat or assign them to an AI agent.
  5. Switch to another AI model whenever needed without reconnecting MCP.
TypingMind chat using enabled MCP tools with a selected AI model
Can you use Pipedream to help me with this task?
Pipedream
Sure. I read it.
Here is what I found using Pipedream.

Frequently asked questions

What is the Pipedream MCP server used for?

Pipedream is an MCP server that lets compatible AI clients connect to external tools and context. In TypingMind, you can add this MCP server once and make its tools available in your AI workspace.

Can I use Pipedream MCP with multiple AI models in TypingMind?

Yes. TypingMind connects MCP tools at the workspace level, so you can use Pipedream with different AI models such as Claude, ChatGPT, Gemini, or other models you have configured in TypingMind without setting up the MCP server separately for each model.

Why use Pipedream MCP with TypingMind?

TypingMind is one of the best frontends for LLM chat because it brings multiple AI models, prompts, plugins, AI agents, API keys, and MCP tools into one workspace. With Pipedream connected, you can use its MCP tools across your preferred models while keeping your chat workflow organized in TypingMind.

How do I connect Pipedream MCP to TypingMind?

Pipedream runs through the TypingMind local MCP connector. This is best when the MCP server needs access to local files, desktop apps, command-line tools, or private resources on your computer.

What tools does Pipedream MCP provide in TypingMind?

Pipedream exposes MCP capabilities that can be enabled from the TypingMind Plugins page and used in chat or assigned to AI agents.

Do I need to share my API keys with TypingMind to use Pipedream MCP?

No. TypingMind is local-first and lets you keep your model providers, API keys, prompts, and MCP configuration under your control. If Pipedream requires authentication, add the required headers, OAuth settings, or local configuration for that MCP server when you create the connection.

Related MCP Servers

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇