Substring search across all local agent session files. Returns matching sessions with the first few matching lines. Covers Claude, Codex, Gemini, OpenClaw, and Hermes.
AI agents call search_sessions to retrieve information from AgentWatch without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves data from existing session files without any side effects. It is a search/filter operation analogous to grep or find, which are classic Read-category tools. The ability to search across multiple session files and display results does not alter, execute, or destroy data.
From the tool's definition Tool performs 'Substring search across all local agent session files' and 'Returns matching sessions with the first few matching lines' — these are purely retrieval operations with no modification, deletion, or execution capabilities.
Documented attack patterns abuse exactly the kind of access search_sessions gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and AgentWatch, and nothing reaches the server without passing your rules. This is the rule we recommend for search_sessions:
{
"version": "1",
"default": "deny",
"tools": {
"search_sessions": {}
}
}search_sessions is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Substring search across all local agent session files. Returns matching sessions with the first few matching lines. Covers Claude, Codex, Gemini, OpenClaw, and Hermes. It is categorised as a Read tool in the AgentWatch MCP Server, which means it retrieves data without modifying state.
Register the AgentWatch MCP server in PolicyLayer and add a rule for search_sessions: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches AgentWatch. Nothing to install.
search_sessions is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the search_sessions rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for search_sessions. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
search_sessions is provided by the AgentWatch MCP server (mishanefedov/agentwatch). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from AgentWatch, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
5 AgentWatch tools catalogued and risk-classified — across an index of 43,000+ MCP servers.