查询当前通过 SSE 在线连接的 Agent 列表，分配任务前可先确认对方在线。
AI agents call get_online_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 retrieves status information about connected agents. It performs a read-only query to determine which agents are currently online, enabling informed task assignment decisions. There are no side effects, data modifications, or operational triggers. The information gathered is purely informational and cannot cause harm through misuse, making this a straightforward Read category tool with low severity.
From the tool's definition Tool name 'get_online_agents' and description state it queries/lists currently online Agent connections via SSE. The verb '查询' (query) and 'Agent 列表' (Agent list) indicate data retrieval with no modification.
Attacks that exploit this kind of access
查询当前通过 SSE 在线连接的 Agent 列表，分配任务前可先确认对方在线。. 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 get_online_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.
get_online_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 get_online_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 get_online_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.
get_online_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 →