// MCP TOOL REFERENCE

AI README TOOLS

6 tools from the Ai Readme MCP Server, categorised by risk level.

READ TOOLS

compress_ai_readme Compress an AI_README.md file using deterministic filler-language removal (no LLM call). WHEN TO CALL: - validate_ai_readmes reports 'filler-langu... discover_ai_readmes Scan the project and discover all AI_README.md files. Returns an index of all README files with their paths, scopes, and coverage patterns. get_context_for_file ALWAYS CALL THIS FIRST - NO EXCEPTIONS. WHEN TO CALL (check these FIRST before responding): - User asks: optimize, improve, analyze, review, sugges... 2/5 validate_ai_readmes Validate all AI_README.md files in a project. Checks token count, structure, and content quality. Returns validation results with suggestions for i...

WRITE TOOLS

update_ai_readme CALL THIS to record DECISIONS and CONVENTIONS. WHEN TO CALL: A. CONFLICT RESOLUTION — STOP IMMEDIATELY when any of these occur: - User says: "don... 2/5

DESTRUCTIVE TOOLS

init_ai_readme Initialize and populate empty AI_README files within a project. When to use: - First-time setup when no AI_README exists. - get_context_for_file re... 5/5

// FAQ

How many tools does the Ai Readme MCP server have? +

The Ai Readme MCP server exposes 6 tools across 3 categories: Read, Write, Destructive.

How do I enforce policies on Ai Readme tools? +

Use Intercept, the open-source MCP proxy. Write YAML rules for each tool — rate limits, argument validation, or deny rules — then run Intercept in front of the Ai Readme server.

What risk categories do Ai Readme tools fall into? +

Ai Readme tools are categorised as Read (4), Write (1), Destructive (1). Each category has a recommended default policy.

Enforce policies on Ai Readme

Open source. One binary. Zero dependencies.

npx -y @policylayer/intercept

github.com/policylayer/intercept →