worker.heartbeat
Refresh worker load, warm-model state, and content-addressed artifact locality.
This record as markdown: /tools/visionmcp/worker.heartbeat.md
What worker.heartbeat does on Visionmcp
AI agents call worker.heartbeat to retrieve information from Visionmcp without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why worker.heartbeat is rated Low
A heartbeat operation that refreshes/queries state information (worker load, model warm state, artifact locality) is fundamentally a status/monitoring read operation. It retrieves and updates internal health metadata without creating, modifying user data, executing code, or causing destructive effects.
From the tool's definition Refresh worker load, warm-model state, and content-addressed artifact locality
Attacks that exploit this kind of access
The rule that runs worker.heartbeat safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Visionmcp, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For worker.heartbeat, this is the rule to start with:
worker.heartbeat is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Visionmcp, apply this rule, and every worker.heartbeat call is checked against it from then on.
Questions about worker.heartbeat
Refresh worker load, warm-model state, and content-addressed artifact locality. It is categorised as a Read tool in the Visionmcp MCP Server, which means it retrieves data without modifying state.
Register the Vision MCP server in PolicyLayer and add a rule for worker.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 Visionmcp. Nothing to install.
worker.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 worker.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 worker.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.
worker.heartbeat is provided by the Vision MCP server (joshuahickscorp/visionmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Vision, and thousands of servers like it.
This server
Across the catalogue