AI agents call swarm_get_metrics to retrieve information from Mcp Swarm without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves system performance metrics and statistics. It is a read-only operation that queries existing data about the swarm system's performance characteristics. There are no side effects, no data modifications, no code execution, no deletions, and no financial implications.
From the tool's definition Tool name 'swarm_get_metrics' and description '获取蜂群系统的性能指标，包括响应时间、成功率等' (Get swarm system performance metrics, including response time, success rate, etc.) indicates retrieval of monitoring/telemetry data without modification or execution of operations.
Attacks that exploit this kind of access
获取蜂群系统的性能指标，包括响应时间、成功率等。. It is categorised as a Read tool in the Mcp Swarm MCP Server, which means it retrieves data without modifying state.
Register the Mcp Swarm MCP server in PolicyLayer and add a rule for swarm_get_metrics: 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 Swarm. Nothing to install.
swarm_get_metrics 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 swarm_get_metrics 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 swarm_get_metrics. 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.
swarm_get_metrics is provided by the Mcp Swarm MCP server (moselu/mcp-swarm). 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 →