Refresh presence between polls; returns currently-online agents.
AI agents call heartbeat to retrieve information from Mcp Switchboard without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool refreshes a presence signal and returns a list of currently-online agents. This is a read/query operation with no data modification, no destructive effects, and no financial implications. The blast radius of misuse is minimal — at worst it could be used to enumerate active agents, but that information is already available via list_agents.
From the tool's definition Refresh presence between polls; returns currently-online agents
Attacks that exploit this kind of access
Refresh presence between polls; returns currently-online agents. It is categorised as a Read tool in the Mcp Switchboard MCP Server, which means it retrieves data without modifying state.
Register the Mcp Switchboard MCP server in PolicyLayer and add a rule for heartbeat: 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 Switchboard. Nothing to install.
heartbeat 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 heartbeat 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 heartbeat. 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.
heartbeat is provided by the Mcp Switchboard MCP server (jemplayer82/mcp-switchboard). 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 →