This MCP server analyzes codebases using tree-sitter and generates AGENTS.md files, which serve as a README for AI agents. It supports various MCP-capable clients and provides tools for codebase analysis and payload streaming.
From the registry: Analyzes codebases with tree-sitter and generates AGENTS.md files for AI coding agents.
Please install the `agents-md-generator` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Python 3.11+** — Required runtime.
- **Git** — Required for file discovery.
Canonical MCP server config (stdio transport):
- command: `uvx`
- args: ["agents-md-generator"]
- optional environment variables:
- `AGENTS_MD_LOG_LEVEL`: Server log verbosity. Values: DEBUG, INFO, WARNING, ERROR. (example: `INFO`)
Note: uvx is the simplest path (no prior install). Also installable via pip (pip install agents-md-generator) with a setup wizard.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.AGENTS_MD_LOG_LEVELServer log verbosity. Set to DEBUG to see per-file analysis details.Real-time infrastructure monitoring with metrics, logs, alerts, and ML-based anomaly detection.
Persistent codebase knowledge graph. Survives session restarts and context compaction.
Validate oh-my-posh configurations and segment snippets against the official schema.