// MCP TOOL REFERENCE

AGENTWATCH TOOLS

5 tools from the AgentWatch MCP Server, categorised by risk level.

View the AgentWatch policy →
// ALL 5 AGENTWATCH TOOLS
READ 5 tools
Read get_session_cost Return total cost (USD), token counts broken down by input / cache read / cache create / output, and turn c... Read get_session_events Return the raw events for a given session ID. JSONL for file-based agents (Claude/Codex/Gemini/OpenClaw); H... Read get_tool_usage_stats Aggregate tool invocation counts, total duration, and error counts. If sessionId is given, stats are scoped... Read list_recent_sessions List the most recent local agent sessions across Claude Code, Codex, Gemini, OpenClaw, and Hermes, newest f... Read search_sessions Substring search across all local agent session files. Returns matching sessions with the first few matchin...

Route AgentWatch through PolicyLayer and every one of its 5 tools is checked against your policy before it runs.

CHECK YOUR STACK →

See every tool, the dangerous ones, and the token cost across your stack.

// FAQ
How many tools does the AgentWatch MCP server have? +

The AgentWatch MCP server exposes 5 tools across 1 categories: Read.

How do I enforce policies on AgentWatch tools? +

Route the AgentWatch 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 AgentWatch tools fall into? +

AgentWatch tools are categorised as Read (5). Each category has a recommended default policy.

Enforce policy on every AgentWatch tool call.

Start from AgentWatch, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →

Free to start. No card required.

43,000+ MCP servers and 220,000+ tools scanned and risk-classified.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.