Machi
Agent behavior that compiles
What is Machi?
Machi is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to agent behavior that compiles
Agent behavior that compiles
This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Agent behavior that compiles
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx machiConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Machi
Machi is a lightweight, ergonomic AI agent framework written in Rust that lets you define and compile agent behavior through declarative configurations. It implements the Model Context Protocol and integrates with emerging web4 and agent-to-agent (A2A) protocols, including x402 micropayment flows. Developers building autonomous agents that need type-safe, compiled behavior definitions and multi-agent coordination use Machi as the runtime backbone.
Prerequisites
- Rust toolchain (rustup with stable channel) installed, or use the provided install script
- An MCP-compatible client such as Claude Desktop
- Git to clone the repository
- cargo build tools available
Install Machi via the install script
On Unix-like systems run the provided shell script. On Windows use the PowerShell script install.ps1. Alternatively install from crates.io with cargo.
curl -sSf https://raw.githubusercontent.com/qntx/machi/main/install.sh | sh
# or
cargo install machiClone the repository for development builds
Clone and build from source if you want the latest development version.
git clone https://github.com/qntx/machi.git
cd machi
cargo build --releaseConfigure Machi as an MCP server in Claude Desktop
Add Machi to your Claude Desktop configuration file, pointing to the compiled binary.
{
"mcpServers": {
"machi": {
"command": "/path/to/machi",
"args": []
}
}
}Define agent behaviors
Create declarative agent behavior configurations in your project. Machi compiles these at build time, giving you type-safe agent logic with no runtime surprises.
Connect agents via A2A and MCP protocols
Machi supports agent-to-agent (A2A) communication and x402 micropayment flows alongside standard MCP tool calls, enabling multi-agent pipelines.
Machi Examples
Client configuration
Claude Desktop config block for a locally built Machi binary.
{
"mcpServers": {
"machi": {
"command": "/usr/local/bin/machi",
"args": []
}
}
}Prompts to try
Example interactions once Machi is running as an MCP server.
- "List the available agent behaviors configured in Machi"
- "Execute the data-fetch agent behavior with input URL https://example.com"
- "Show the current agent session state"
- "Trigger the payment flow for agent task ID 42"Troubleshooting Machi
Cargo build fails with dependency errors
Run 'rustup update stable' to ensure you have the latest stable Rust toolchain. The workspace uses three crates (machi, machi-derive, machi-auto) so run 'cargo build --workspace' from the repository root.
MCP client cannot connect to the Machi binary
Verify the binary path in your config is correct and the binary is executable ('chmod +x /path/to/machi'). Check that the MCP server starts cleanly by running it directly in a terminal first.
Agent behavior compilation errors at startup
Machi validates behavior definitions at compile time. Review the Rust compiler error output — it will point to the specific behavior definition that is malformed. Ensure all referenced types and trait implementations are in scope.
Frequently Asked Questions about Machi
What is Machi?
Machi is a Model Context Protocol (MCP) server that agent behavior that compiles It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Machi?
Follow the installation instructions on the Machi GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Machi?
Machi works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Machi free to use?
Yes, Machi is open source and available under the NOASSERTION license. You can use it freely in both personal and commercial projects.
Machi Alternatives — Similar Coding Agents Servers
Looking for alternatives to Machi? Here are other popular coding agents servers you can use with Claude, Cursor, and VS Code.
Dify
★ 142.2kProduction-ready platform for agentic workflow development.
Ruflo
★ 54.0k🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, self-learning swarm intelligence, RAG integrat
Goose
★ 45.7kan open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
Antigravity Awesome Skills
★ 38.3kInstallable GitHub library of 1,400+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.
AgentScope
★ 25.5kBuild and run agents you can see, understand and trust.
Serena
★ 24.5kA coding agent toolkit that provides IDE-like semantic code retrieval and editing tools, enabling LLMs to efficiently navigate and modify codebases using symbol-level operations instead of basic file reading and string replacements.
Browse More Coding Agents MCP Servers
Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Machi in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Machi?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.