aicoolies logo
Pipedream logo

Pipedream

Connect 2,800+ APIs for workflows and AI agents

Share
freemium
Visit Website →

Pipedream is a developer-focused workflow automation platform that connects over 2,800 APIs with managed OAuth and credential handling, letting teams build integrations using Node.js, Python, Go, or Bash alongside a visual no-code builder. Its MCP server exposes 10,000+ pre-built tools to AI agents for direct API access through LangChain, CrewAI, and other frameworks. Pipedream is SOC 2 Type II and HIPAA compliant with credit-based pricing starting at a free tier of 100 credits per month.

Pipedream is a serverless workflow automation platform that bridges the gap between code-heavy API integration and no-code tools like Zapier. Developers can write custom steps in Node.js, Python, Go, or Bash with full access to npm and PyPI packages, while the visual builder handles the plumbing — triggers, step sequencing, branching, error handling, and retries. What sets Pipedream apart from simpler automation tools is that it manages the messy parts of API integration: OAuth token refresh, credential rotation, webhook signature verification, and rate limiting across 2,800+ connected services including Slack, Google Sheets, GitHub, Stripe, Twilio, and Salesforce.

The platform has expanded significantly into the AI agent ecosystem through Pipedream Connect, which provides SDKs and an MCP server that expose over 10,000 pre-built tools to AI agents. Instead of writing custom API integration code for each service an agent needs to access, developers can point their LangChain, CrewAI, or other agent framework at Pipedream's MCP server and get managed authentication, tool discovery, and execution across thousands of APIs. This makes Pipedream particularly valuable as a tool-use layer for autonomous agents that need to interact with real-world SaaS services — sending emails, updating CRMs, managing project tasks, or querying databases — without each integration being hand-coded.

Pricing uses a credit-based model where one credit covers 30 seconds of compute at 256MB memory. The free tier includes 100 credits per month, 3 active workflows, and unlimited testing. Paid plans start at $45/month (Basic) with 2,000 credits and 10 workflows, $74/month (Advanced) with unlimited workflows and GitHub sync, and $150/month (Connect) for production agent integrations with 100 external users. Enterprise plans offer custom pricing with HIPAA support, SLAs, and priority integration development. The platform is SOC 2 Type II compliant. Users include startups prototyping quickly and enterprises running business-critical automations, though some users note the pricing can scale unpredictably with heavy AI agent usage.

Pricing

Free tier 100 credits/mo, Basic $45/mo, Advanced $74/mo

Platforms

Cloud SaaS, Node.js/Python/Go/Bash, MCP server, REST API

Categories

Tags

Use Cases

Alternatives

Related Tools

Hermes Agent logo

Hermes Agent

Top Pick

Open-source AI agent framework with persistent memory, reusable skills, tools, and messaging gateways

Hermes Agent is an open-source AI agent framework with persistent memory, reusable skills, 40+ tools, cron jobs, and messaging gateways.

open-sourceOpen Source
BeeAI Framework logo

BeeAI Framework

Python and TypeScript framework for production multi-agent systems

BeeAI Framework is an Apache-2.0 toolkit for building production-ready AI agents and multi-agent systems in Python and TypeScript. Its docs cover agents, tools, RAG, memory, workflows, backend providers, serving, and A2A/MCP integration surfaces, making it a vendor-neutral option for teams comparing LangGraph, CrewAI, Mastra, and related agent runtimes.

open-sourceOpen SourceTelemetry

Notion MCP Server

Official Notion MCP server for AI-agent workspace access

Notion MCP Server is Notion's official MIT-licensed MCP server for connecting AI assistants to Notion workspaces. It supports the vendor-backed remote OAuth path and tools designed for page, workspace, and Markdown-style operations, making it a safer default than unofficial Notion bridges for teams already using Notion for docs, projects, or internal knowledge bases.

open-sourceOpen SourceTelemetry
Superserve logo

Superserve

Open-source Firecracker sandboxes for long-running AI agents

Superserve is an open-source sandbox infrastructure layer for AI agents that need durable computers instead of short-lived shells. It runs isolated Firecracker microVMs, supports pause, resume, snapshot, fork, preview URLs, MCP connectivity, SDK/API control, Docker workloads, and self-hosting, while the hosted service adds pay-as-you-go agent sandboxes for teams.

open-sourceOpen Source

Linear MCP Server

Official authenticated remote MCP endpoint for Linear issues, projects, comments, and coding-agent workflows.

Linear MCP Server is Linear’s official authenticated remote MCP endpoint for agent access to issues, projects, and comments. It gives Claude, Codex, Cursor, VS Code, Windsurf, Zed, and other clients a centrally hosted way to find, create, and update Linear work items through OAuth-backed MCP without maintaining a local connector or brittle API glue.

freemiumTelemetry

Slack MCP Server

Official Slack MCP server for approved workspace search, messaging, canvas, and user-context actions.

Slack MCP Server is Slack’s official remote MCP layer for giving approved AI clients workspace context and controlled actions. It lets agents search messages, files, users, and channels, draft or send messages, read threads, manage canvases, and authenticate through Slack OAuth while workspace admins approve integrations and normal Slack rate limits still apply.

freemiumTelemetry