Retrieve error occurrence traces with details including error message, type, stack traces, and host. Supports filtering by error type (METHOD, SUBSCRIPTION, CLIENT), status (NEW, IGNORED, FIXED), and exact error message. IMPORTANT: Default time range is last 1 hour. If no data is returned, try a ...
AI agents call get_error_traces to retrieve information from Monti APM MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries performance monitoring data (error traces, stack traces, metadata) from a Monti APM system with no side effects. It supports filtering by error attributes but does not create, modify, delete, or execute any actions. The primary function is inspection and analysis of historical error data, which is characteristic of a Read operation.
From the tool's definition Tool description states it 'Retrieve[s] error occurrence traces' with filtering capabilities. No modification, deletion, or execution of operations described—only data retrieval and querying of existing error logs.
Attacks that exploit this kind of access
Retrieve error occurrence traces with details including error message, type, stack traces, and host. Supports filtering by error type (METHOD, SUBSCRIPTION, CLIENT), status (NEW, IGNORED, FIXED), and exact error message. IMPORTANT: Default time range is last 1 hour. If no data is returned, try a wider startTime. It is categorised as a Read tool in the Monti APM MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Monti APM MCP Server MCP server in PolicyLayer and add a rule for get_error_traces: 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 Monti APM MCP Server. Nothing to install.
get_error_traces 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 get_error_traces 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 get_error_traces. 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.
get_error_traces is provided by the Monti APM MCP Server MCP server (quavedev/montiapm-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 →