查询已注册的 Agent 列表。支持按状态、角色筛选。
AI agents call query_agents to retrieve information from Agent-Comm-Hub without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and lists registered agents with optional filtering by status and role. It retrieves information without side effects, matching the Read category definition. Severity is low because querying a list of agents poses minimal risk—an agent cannot misuse this to cause harm, only to gather metadata about system participants.
From the tool's definition Tool name 'query_agents' and description '查询已注册的 Agent 列表。支持按状态、角色筛选' (Query registered Agent list. Support filtering by status, role) clearly indicate data retrieval with filtering capabilities.
Attacks that exploit this kind of access
查询已注册的 Agent 列表。支持按状态、角色筛选。. It is categorised as a Read tool in the Agent-Comm-Hub MCP Server, which means it retrieves data without modifying state.
Register the Agent-Comm-Hub MCP server in PolicyLayer and add a rule for query_agents: 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 Agent-Comm-Hub. Nothing to install.
query_agents 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 query_agents 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 query_agents. 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.
query_agents is provided by the Agent-Comm-Hub MCP server (liuboacean/agent-comm-hub). 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 →