tool_get_eval_summary
AI agents call tool_get_eval_summary to retrieve information from Inspect Logs without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays evaluation summaries from existing logs. It has no capability to modify, delete, or execute operations—it only queries and presents data. The lack of a description reduces confidence slightly, but the server's stated purpose (exploration and analysis) and sibling tool names strongly indicate this is a Read operation with minimal blast radius if misused.
From the tool's definition Tool name 'tool_get_eval_summary' and server description indicating it 'view[s] evaluation summaries' for inspection/analysis of logs.
Attacks that exploit this kind of access
tool_get_eval_summary. It is categorised as a Read tool in the Inspect Logs MCP Server, which means it retrieves data without modifying state.
Register the Inspect Logs MCP server in PolicyLayer and add a rule for tool_get_eval_summary: 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 Inspect Logs. Nothing to install.
tool_get_eval_summary 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 tool_get_eval_summary 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 tool_get_eval_summary. 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.
tool_get_eval_summary is provided by the Inspect Logs MCP server (pranshusrivastava/inspect-logs-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →