Step 1 of 2. Pass in a stack trace and receive instructions on what to find.
AI agents call blame_stack_trace to retrieve information from Triage Agent without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool accepts a stack trace as input and returns instructions/guidance. It does not modify data, execute code, or delete anything — it reads/analyzes input and produces advisory output. Severity is low as misuse has minimal blast radius. Confidence is moderate because the description is brief and the actual backend behavior is not fully described.
From the tool's definition Pass in a stack trace and receive instructions on what to find
Attacks that exploit this kind of access
Step 1 of 2. Pass in a stack trace and receive instructions on what to find. It is categorised as a Read tool in the Triage Agent MCP Server, which means it retrieves data without modifying state.
Register the Triage Agent MCP server in PolicyLayer and add a rule for blame_stack_trace: 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 Triage Agent. Nothing to install.
blame_stack_trace 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 blame_stack_trace 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 blame_stack_trace. 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.
blame_stack_trace is provided by the Triage Agent MCP server (rahulnayanegali/triage-agent-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 →