AI agents call swarm_get_stats 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 queries and retrieves statistical data about the swarm system's operations, costs, and performance metrics. It performs no modifications, deletions, or external operations—purely a read operation returning monitoring information. The blast radius of misuse is minimal since it only exposes observational data about system usage patterns.
From the tool's definition Tool description indicates it retrieves usage statistics: '获取蜂群系统的使用统计信息，包括请求次数、模型使用分布、成本监控、错误统计等' (Get swarm system usage statistics, including request counts, model usage distribution, cost monitoring, error statistics, etc.).
Attacks that exploit this kind of access
获取蜂群系统的使用统计信息，包括请求次数、模型使用分布、成本监控、错误统计等。. 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_stats: 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_stats 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_stats 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_stats. 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_stats 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 →