// MCP TOOL REFERENCE

AGENT LOOP DETECTOR TOOLS

3 tools from the Agent Loop Detector MCP Server, categorised by risk level.

View the Agent Loop Detector policy → Token cost: 245 tokens →

// ALL 3 AGENT LOOP DETECTOR TOOLS

READ 3 tools

Read analyze_trace Full diagnostic: loop detection, cost breakdown, stuck-state classification, and fix recommendations for an... Read breakdown_cost Calculate per-model token usage and USD cost from an agent trace. Supports custom pricing overrides. Read detect_loops Detect exact-call repeats, periodic tool-call cycles, and ping-pong patterns in an agent trace.

// FAQ

How many tools does the Agent Loop Detector MCP server have? +

The Agent Loop Detector MCP server exposes 3 tools across 1 categories: Read.

How do I enforce policies on Agent Loop Detector tools? +

Route the Agent Loop Detector 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 Agent Loop Detector tools fall into? +

Agent Loop Detector tools are categorised as Read (3). Each category has a recommended default policy.

Let agents act without letting them run wild.

Route your MCP servers through PolicyLayer and every tool call is checked against your policy before it runs — allow, deny, or require approval. Per-identity grants. Full audit log. Live in minutes.

SECURE YOUR MCP →

Free to start. No card required.

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