Retrieve the full execution graph for a specific trace ID, showing each step with its inputs, outputs, latency, and token usage.
AI agents call trace_view to retrieve information from Scan Your Ai Toolkit without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns structured tracing data for analysis and monitoring purposes. It has no capability to modify, delete, or execute operations—only to fetch and display execution telemetry. The blast radius of misuse is minimal; an attacker could only exfiltrate trace data (potentially containing sensitive inputs/outputs), but cannot affect system state or trigger actions.
From the tool's definition Tool retrieves execution graph data showing 'each step with its inputs, outputs, latency, and token usage' for a specific trace ID. Uses action verbs 'Retrieve' and 'showing' which indicate data querying without modification or side effects.
Attacks that exploit this kind of access
Retrieve the full execution graph for a specific trace ID, showing each step with its inputs, outputs, latency, and token usage. It is categorised as a Read tool in the Scan Your Ai Toolkit MCP Server, which means it retrieves data without modifying state.
Register the Scan Your Ai Toolkit MCP server in PolicyLayer and add a rule for trace_view: 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 Scan Your Ai Toolkit. Nothing to install.
trace_view 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_view 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_view. 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_view is provided by the Scan Your Ai Toolkit MCP server (sakthivelchan89/scan_your_ai_toolkit). 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 →