// MCP TOOL REFERENCE

AI AGENT TOOLS

2 tools from the Ai Agent MCP Server, categorised by risk level.

OTHER TOOLS

Incremental mode Skips unchanged files using string content equality comparison (client-side) Path isolation Complex skills NOT stored in `~/.cursor/skills/` to prevent AI auto-discovery and ensure telemetry tracking

// FAQ

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

The Ai Agent MCP server exposes 2 tools across 1 categories: Other.

How do I enforce policies on Ai Agent 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 Agent server.

What risk categories do Ai Agent tools fall into? +

Ai Agent tools are categorised as Other (2). Each category has a recommended default policy.

Enforce policies on Ai Agent

Open source. One binary. Zero dependencies.

npx -y @policylayer/intercept

github.com/policylayer/intercept →