Send a heartbeat to indicate agent is still active. Call periodically during long operations.
AI agents use agent_heartbeat to create or update resources in Agent Orchestration — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Agent Orchestration environment.
The tool writes/updates the agent's active status in a shared coordination system. It modifies state (marks the agent as alive) but does not delete data, execute code, or have financial implications. The blast radius of misuse is low — worst case, it falsely signals an agent is active, potentially causing minor coordination issues.
From the tool's definition 'Send a heartbeat to indicate agent is still active. Call periodically during long operations.'
Documented attack patterns abuse exactly the kind of access agent_heartbeat gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Agent Orchestration, and nothing reaches the server without passing your rules. This is the rule we recommend for agent_heartbeat:
{
"version": "1",
"default": "deny",
"tools": {
"agent_heartbeat": {
"limits": [
{
"counter": "agent_heartbeat_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}agent_heartbeat stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Send a heartbeat to indicate agent is still active. Call periodically during long operations. It is categorised as a Write tool in the Agent Orchestration MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Agent Orchestration MCP server in PolicyLayer and add a rule for agent_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 Agent Orchestration. Nothing to install.
agent_heartbeat is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the agent_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 agent_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.
agent_heartbeat is provided by the Agent Orchestration MCP server (madebyaris/agent-orchestration). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Agent Orchestration, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
35 Agent Orchestration tools catalogued and risk-classified — across an index of 43,000+ MCP servers.