📊 Performance monitoring tool for query metrics, system health, and performance analysis.
AI agents call performance_monitor to retrieve information from MCP Sigmund without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads/queries performance metrics and system health data without modifying any data or triggering external operations. Monitoring and analysis tools are passive by nature. The slight uncertainty comes from the vague description—it could theoretically execute diagnostic queries—but the framing as 'monitoring' and 'analysis' strongly suggests read-only behavior.
From the tool's definition Performance monitoring tool for query metrics, system health, and performance analysis
Attacks that exploit this kind of access
📊 Performance monitoring tool for query metrics, system health, and performance analysis. It is categorised as a Read tool in the MCP Sigmund MCP Server, which means it retrieves data without modifying state.
Register the MCP Sigmund MCP server in PolicyLayer and add a rule for performance_monitor: 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 MCP Sigmund. Nothing to install.
performance_monitor 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 performance_monitor 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 performance_monitor. 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.
performance_monitor is provided by the MCP Sigmund MCP server (radup/mcp-sigmund). 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 →