workflowstacks
mcp-server

Composio: Build AI Agents Fast with 30k+ GitHub Stars

Turn user intent into automated actions using Composio’s searchable toolkit library, context handling, auth, and sandboxed workbench—ideal for founders building AI-driven products.

From the repo · “Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn intent into action.”

intermediate⏱ 30 minutes💵 Free (self-hosted)
30,686 stars+114★ this week4,893 forksTypeScriptGuide quality 9/10 · reviewed Oct 5Updated 10/22/2026100% free · open source
What it is

Build AI agents in a secure, all-in-one workbench.

Real use case example

"A founder wants to automate sending a personalized follow-up email to customers who abandoned their shopping carts. They use Composio to build an AI agent that checks for cart abandonments, sends the follow-up email, and also tracks conversion rates. After setting up the agent, they save time and effort by automating this tedious task and also gain valuable insights to improve their business."

Best insideClaude DesktopCursor
When to use it
  • •When you need to integrate multiple AI tools and services into a single workflow
  • •When you want to build custom AI agents with a sandboxed environment for testing and development
  • •When you require a flexible and scalable platform for managing AI-powered toolkits and workflows
Ready-to-paste prompt
Create a new AI agent with a sample toolkit by running `yarn create-agent --template=default`
Heads up: Make sure you have a compatible version of Node.js (14 or higher) and Yarn installed on your system, as Composio relies on these for building and running the workbench
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/composio && curl -fsSL https://workflowstacks.com/api/skills/composio/claude-skill -o ~/.claude/skills/composio/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How Composio: Build AI Agents Fast with 30k+ GitHub Stars works
Codeflow
Free to inspect

Composio: Build AI Agents Fast with 30k+ GitHub Stars is a very large TypeScript project (~154k lines across 1164 code files, plus 379 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, MIT license, has a test suite.

Size
Very large codebase
~154k lines · 1164 code files · days to read — use, don't read
Setup
Developer setup
A real software project. Use it via its install path; don't expect to read it all.
Runs on
Node.js · Python
No API keys detected
TypeScript 74%Python 21%Shell 2%JavaScript 2%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    AGENTS.md
    The instructions the AI actually follows
  3. 3
    harness/run.mjs
    Where the program starts running
  4. 4
    package.json
    Dependencies and the commands it exposes
  5. 5
    skills/composio/SKILL.md
    Inside skills/ — an example of what the AI is told to do
What's in each folder
skills/Prompts, skills & agent definitions4 files
docs/Documentation1204 files
ts/Folder1546 files
python/Folder257 files
harness/Folder12 files
install/Folder3 files
scripts/Helper scripts1 files
test/Tests — proof it works68 files
READMEHas testsDocumentedCI checksMIT licenseUpdated this month
Quick Actions
Details
Creator
ComposioHQ
Language
TypeScript
Category
mcp-server
Published
2/23/2024

Are you the creator of this tool? and earn 85% of every sale.

Show it off in your README:

Featured on WorkflowStacks
[![Featured on WorkflowStacks](https://workflowstacks.com/api/badge/composio.svg)](https://workflowstacks.com/skills/composio?utm_source=github&utm_medium=badge)
🔥 Hot this week, in your inbox
Skills like this, every Monday.

The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.

Do this with a working workflow

Pages we wrote and tested that put a skill like this to work — importable n8n templates, outcome guides and Claude Desktop configs.

Outcome guide

Recover abandoned carts with personalized emails

Export abandoned carts to a Google Sheet and the workflow drafts a warm, specific win-back email for each — referencing the actual product, without desperate discount-spam. You review and send.

Free n8n template

Abandoned Cart Win-Back

Draft a personalized, non-pushy win-back email for every abandoned cart — referencing the exact product left behind. You approve before sending.

MCP config

GitHub MCP config

Search repos, read code, open issues and PRs from Claude.

Related skills

More mcp-server tools founders pair with this one.

mcp-server★ 365,609
Rea: Reverse Engineer Apps
Inspect apps down to binary level with Rea. For founders needing code clarity.
mcp-server★ 156,480
open-webui: Self‑hosted AI Chat UI for Faster LLM Integration
Launch a sleek, web‑based AI interface that works with Ollama, OpenAI API, and more—ideal for founders needing a quick, customizable LLM front‑end. 153k+ GitHub stars.
mcp-server★ 132,268
graphify
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
mcp-server★ 916
NornicDB
Nornicdb is a distributed low-latency, Graph+Vector, Temporal MVCC with all sub-ms HNSW search, graph traversal, and writes. Using Neo4j Bolt/Cypher and qdrant's gRPC means you can switch with no changes while adding intelligent features like schemas, managed embeddings, reranking+llm, GPU accel, Auto-TLP, Policy-based Memory Decay, and MCP server.
mcp-server★ 16,709
mcp-toolbox: Unified Database MCP Server for Fast Scaling
Leverage mcp-toolbox to manage multiple databases through a single MCP server, cutting integration effort for founders building data‑centric apps. Backed by 16k+ GitHub stars.
mcp-server★ 1,941
video-search-and-summarization: Build GPU‑fast vision agents for video AI
Leverage ready‑made architectures to add real‑time video search, summarization and analytics to your product. Ideal for founders building AI‑powered vision services. 1.9k+ GitHub stars