amcp / README.md
moelove's picture
add anthropic and open_response LLM format support
fb6b08c unverified
|
Raw
History Blame Contribute Delete
5.32 kB

AMCP

CI Python 3.11+ License: Apache-2.0

tags: - building-mcp-track-creative - mcp-in-action-track-consumer - mcp-in-action-track-creative

AMCP

A Lego-style coding agent CLI with built-in tools (grep, read files, bash execution) and MCP server integration for extended capabilities (web search, etc.).

X: https://x.com/zhangjintao9020/status/1995170132973466018?s=20 Demo: https://drive.google.com/file/d/1FGoY4I_JFQ1FSz19XlVJZ6Z4lWUucD7a/view?usp=sharing

Features

  • Built-in Tools: read_file, grep, bash, think
  • MCP Integration: Connect to any MCP server for extended capabilities
  • Conversation History: Persistent sessions across runs
  • Flexible Configuration: YAML-based agent specifications
  • Tool Calling: Automatic tool selection and execution
  • ACP Support: Full Agent Client Protocol support for IDE integration (Zed, etc.)

Install (editable)

# using uv (recommended)
uv venv && source .venv/bin/activate
uv pip install -e .

# or with pip
python -m venv .venv && source .venv/bin/activate
pip install -e .

Usage

# Initialize config
amcp init

# Agent with tool calling (default command)
amcp  # interactive mode with conversation history
amcp --once "create a hello.py file with a hello function"  # single message
amcp --list  # list available agent specifications
amcp --agent path/to/agent.yaml  # use custom agent spec
amcp --session my-session  # use specific session ID
amcp --clear  # clear conversation history

# MCP server management
amcp mcp tools --server exa
amcp mcp call --server exa --tool web_search_exa --args '{"query":"rust async"}'

# Run as ACP agent (for IDE integration)
amcp-acp

ACP (Agent Client Protocol) Support

AMCP fully supports the Agent Client Protocol for integration with IDEs like Zed.

Features

  • Session Management: Create, load, and list sessions
  • Session Modes: Switch between ask, architect, and code modes
    • ask: Request permission before making changes
    • architect: Design and plan without implementation
    • code: Full tool access for implementation
  • Slash Commands: /clear, /plan, /search, /help
  • Agent Plans: Visual execution plans for complex tasks
  • Permission Requests: User approval for sensitive operations
  • Client Capabilities: Use client's filesystem and terminal when available

Running as ACP Agent

# Start the ACP agent server (stdio transport)
amcp-acp

Zed Integration

Add to your Zed settings (~/.config/zed/settings.json):

{
  "agent": {
    "profiles": {
      "amcp": {
        "name": "AMCP",
        "provider": {
          "type": "acp",
          "command": "amcp-acp"
        }
      }
    },
    "default_profile": "amcp"
  }
}

Built-in Tools

  • read_file: Read text files from the workspace
  • grep: Search for patterns in files using ripgrep
  • bash: Execute bash commands for file operations and system tasks
  • think: Internal reasoning and planning
  • todo: Manage a todo list to track tasks during complex operations
  • write_file: Write content to files (can be disabled via config)
  • edit_file: Edit files with search and replace (can be disabled via config)

Config

The CLI loads MCP servers from ~/.config/amcp/config.toml. Generate a starter config:

amcp init

Example (OpenAI-compatible API):

[servers.exa]
url = "https://mcp.exa.ai/mcp"

[servers.custom]
command = "npx"
args = ["-y", "@some/mcp-server"]
env.API_KEY = "your-key"

[chat]
api_type = "openai"  # "openai" (default) or "anthropic"
base_url = "https://api.openai.com/v1"
model = "gpt-4o"
api_key = "your-api-key"
mcp_tools_enabled = true
write_tool_enabled = true  # Enable/disable built-in write_file tool
edit_tool_enabled = true   # Enable/disable built-in edit_file tool

Example (OpenAI Responses API):

[chat]
api_type = "openai_responses"
model = "gpt-4o"
api_key = "your-api-key"

Example (Anthropic Claude):

[chat]
api_type = "anthropic"
model = "claude-sonnet-4-20250514"
api_key = "your-anthropic-api-key"  # or set ANTHROPIC_API_KEY env var

To use Anthropic, install with: pip install amcp[anthropic]

Development

Setup Development Environment

# Clone the repository
git clone <repo-url>
cd AMCP

# Install with development dependencies
pip install -e ".[dev]"

# Install pre-commit hooks
pre-commit install

Running Tests

# Run all tests
make test

# Run with coverage
make test-cov

# Run specific test
pytest tests/test_tools.py -v

Code Quality

# Lint code
make lint

# Format code
make format

# Type check
make type-check

See CONTRIBUTING.md for detailed development guidelines.

Notes

  • rg (ripgrep) must be installed and on PATH for the grep tool.
  • MCP servers must be installed separately and runnable (stdio transport).

License

Apache-2.0