Server facts
ai-readme-mcp
Project
- Author
- Draco-Cheng
- Repository
- github.com/Draco-Cheng/ai-readme-mcp
- License
- Not specified
- Category
- Developer Tools
Tech
- Runtime / language
- Not specified
- Transports
- stdio
- Remote available
- No
- Authentication
- Not specified
Activity
- GitHub stars
- 3
- Last commit
- Data as of
Tags
- Claude
- Cursor
- Documentation
- Project Context
- ai coding
- ai context
- ai readme
- code assistant
- context
- developer tools
Overview
Project conventions stored in AI_README.md files give ai-readme-mcp its working context for AI-assisted development. Teams can document naming rules, architectural choices, and testing practices at the repository root or within individual directories, then share those guides through git. The discover_ai_readmes tool indexes guides by location, scope, and coverage, while get_context_for_file retrieves guidance relevant to a particular file. This directory-aware workflow supports repositories where different areas need different instructions, including monorepos, rather than relying only on a single project-wide document.
For initial setup, init_ai_readme identifies missing or empty guides, creates a root guide when needed, and supplies prompts for documenting local conventions. Assistants can use update_ai_readme to record decisions or revise conventions as development proceeds. Documentation maintenance has separate tools: validate_ai_readmes checks token counts, structure, and content quality, while compress_ai_readme applies deterministic text transformations without an LLM call and offers a preview before writing. The project documents integration with Claude Code, Cursor, GitHub Copilot, Claude Desktop, and OpenClaw, using stdio for MCP communication.
ai-readme-mcp setup notes
- ai-readme-mcp records stdio only; confirm a network transport upstream before planning remote access.
- ai-readme-mcp has no recorded license; confirm reuse terms in its repository.