Get a summary of the current trace session — step count, errors, timing.
AI agents call trace_summary to retrieve information from Agent Safety without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves audit/telemetry data about the current trace session but does not modify, execute, delete, or commit any operations. It is purely informational and poses minimal risk even if accessed by an adversary—exposure would only reveal session metadata, not enable harmful actions.
From the tool's definition Tool returns summary information about trace session metrics (step count, errors, timing) with no modification, deletion, or execution capability. The verb 'Get' and focus on metrics retrieval indicates read-only data access.
Attacks that exploit this kind of access
Get a summary of the current trace session — step count, errors, timing. It is categorised as a Read tool in the Agent Safety MCP Server, which means it retrieves data without modifying state.
Register the Agent Safety MCP server in PolicyLayer and add a rule for trace_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 Agent Safety. Nothing to install.
trace_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 trace_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 trace_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.
trace_summary is provided by the Agent Safety MCP server (luciferforge/agent-safety-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 →