// MCP TOOL REFERENCE

AI AGENT TOOLS

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

View the Ai Agent policy → Token cost: 4,725 tokens →

// ALL 8 AI AGENT TOOLS

READ 2 tools

Read query_usage_stats Query current user's AI resource usage statistics. Returns aggregated usage data from the remote API, incl... Read search_resources Search for available resources by team, type, or keyword

WRITE 4 tools

Write manage_subscription Manage resource subscriptions (subscribe, unsubscribe, list). When action is "subscribe" or "batch_subscrib... Write resolve_prompt_content Retrieve the fully resolved content of a Command or Skill prompt without relying on native prompts/get. Use... Write track_usage Record the invocation of an AI Resource (Command or Skill) for telemetry. MUST be called at the very beginn... Write upload_resource Upload a new AI resource (command, skill, rule, or mcp) to a CSP source repository. The user selects files ...

DESTRUCTIVE 1 tools

Destructive uninstall_resource Uninstall a resource from the user's local machine. Command/Skill resources: unregisters MCP Prompt from me...

EXECUTE 1 tools

Execute sync_resources Synchronize subscribed AI resources with hybrid sync strategy. Command and Skill resources: registered as M...

// RUNNING THIS SERVER

The managed route: connect Ai Agent through the PolicyLayer gateway — every tool call above is checked against your policy before it runs, with a full audit log.

DIRECT INSTALL (UNMANAGED) npx -y @elliotding/ai-agent-mcp

// FAQ

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

The Ai Agent MCP server exposes 8 tools across 4 categories: Read, Write, Destructive, Execute.

How do I enforce policies on Ai Agent tools? +

Route the Ai Agent server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard — they are enforced on every call before it reaches the server.

What risk categories do Ai Agent tools fall into? +

Ai Agent tools are categorised as Read (2), Write (4), Destructive (1), Execute (1). Each category has a recommended default policy.

Enforce policy on every Ai Agent tool call.

Deterministic rules across all 8 Ai Agent tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

GOVERN AI AGENT →

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.