AI Agents
babyagi
Yohei Nakajima's autonomous task agent - now a self-building agent framework in Python
★ 22.4k starsMIT
View guide →// agents · ArcadeAI/arcade-mcp
arcade-mcp
arcade-mcp is an open-source ai agents project by ArcadeAI (ArcadeAI/arcade-mcp on GitHub). It has 1,047 GitHub stars and 119 forks, is released under the MIT license, and was last updated on GitHub on 7 October 2026.
A Python framework for building MCP servers and agent tools.
★ 1.0k stars⑂ 119 forksMITupdated 2026-10
▦ visual — this project's README ships no embeddable screenshot,
so here's a placeholder. The guide below is complete regardless.
so here's a placeholder. The guide below is complete regardless.
// project facts
Project facts
- Repository
- ArcadeAI/arcade-mcp
- GitHub stars
- 1,047
- Forks
- 119
- License
- MIT
- Last updated on GitHub
- 7 October 2026
- Category
- AI Agents
- Listing
- Full install guide
- Official site
- Official site
// how it works
How it works
- Define the job
Know what you want the agent to accomplish before touching any code.
- Get the code
Clone the repo and read the README's requirements section.
- Wire up dependencies
Install what's needed and add API keys or configuration.
- Take it for a spin
Run the quickstart example, then iterate from there.
// features
Why people love it
MCP server scaffolding
Servers without the boilerplate.
Tool authoring
Focus on capabilities, not plumbing.
Auth handling
Secure your tools properly.
Multi-client compatible
Claude, Codex, and other MCP clients.
Python
The lingua franca of agent tooling.
Arcade ecosystem
Backed by Arcade's tooling work.
Advertisement
// run it
Run it yourself
- Step 1 — Clone the repo
Download the source and move into the project folder.
git clone https://github.com/ArcadeAI/arcade-mcp.git cd arcade-mcp - Step 2 — Create a venv and install
Isolate dependencies, then install requirements.
python -m venv .venv && source .venv/bin/activate pip install -r requirements.txt - Step 3 — Run it
Launch using the entry point shown in the README.
python -m arcade_mcp # check README for the exact command
// use cases
What you can build
- Expose your API to Claude as tools.
- Build custom MCP servers fast.
- Package internal tools for agents.
- Prototype new agent capabilities.
Advertisement
// faq
Questions, answered
Who maintains arcade-mcp?
It is an open-source project at ArcadeAI/arcade-mcp with 119 forks. Check the contributors tab and recent commits to judge how active maintenance is.
Is arcade-mcp free to use?
Yes — it's MIT licensed: free to use, modify, and ship commercially. Just keep the license notice in copies.
MCP vs plain APIs?
MCP gives agents a standard way to discover and call tools; arcade-mcp is the scaffolding for building those servers in Python.
Who is it for?
Developers whose agents need custom capabilities — internal APIs, proprietary data, special tools.
How do I get started?
Clone the repo and follow the README quickstart — the docs at https://docs.arcade.dev walk through setup.
// keep exploring
Similar tools
AI Agents
langroid
Langroid: a principled Python framework for building LLM multi-agent applications (from CMU/UW researchers)
★ 4.1k starsMIT
View guide →AI Agents
agent-framework
A framework for building, orchestrating and deploying AI agents and multi-agent workflows with support for Python and .NET.
★ 13.9k starsMIT
View guide →AI Agents
nanobot
Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat…
★ 48.8k starsMIT
View guide →AI Agents
mcp-agent
Simple workflow patterns for building effective agents on MCP.
★ 8.6k starsApache-2.0
View guide →AI Agents
hermes-agent
The agent that grows with you — a Python framework for adaptive AI agents.
★ 252.0k starsMIT
View guide →// alternatives
Alternatives in AI Agents
The most-starred other AI Agents projects in the LibreAI catalogue — the realistic shortlist if arcade-mcp is not the right fit.
- openclaw★ 391.6k
A personal AI that really does things — on any OS, with your data staying yours.
- superpowers★ 294.9k
An agentic skills framework & software development methodology that works.
- ECC★ 275.2k
Agent harness optimization system with skills, memory and security for Claude Code, Codex and more
- hermes-agent★ 252.0k
The agent that grows with you — a Python framework for adaptive AI agents.
- deepseek-harness★ 245.5k
DeepSeek's plugin-based agent harness where everything is a plugin.
// more in agents
More in AI Agents
Nearby AI Agents projects in the catalogue, closest in stars to arcade-mcp — keep exploring the shelf either side of it.
- autoevals★ 1.1k
Fast, best-practice evaluations for AI model outputs.
- Qwen-AgentWorld★ 1.0k
Qwen-AgentWorld: a language world model simulating MCP, terminal, web, and OS environments for agents.
- langsmith-sdk★ 1.1k
Official SDKs for tracing with LangSmith.
- tada★ 1.0k
An open-source speech language model from Hume.
- SandboxFusion★ 1.1k
ByteDance's SandboxFusion: a secure sandbox for running and judging LLM-generated code in 20+ languages.
- ClawBench★ 975
An open benchmark for browser AI agents on everyday tasks.
Get arcade-mcp
Free and open — grab the source, star the repo, and start creating.