Open a consultation thread before starting work
AI agents use announce_work to create or update resources in Mcp Coordinator — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Coordinator environment.
This tool creates a new consultation thread in the coordination system, which is a reversible write operation. It doesn't execute code or delete data, but it does create/modify coordination state. Misuse could disrupt multi-agent coordination by opening spurious threads, hence medium severity.
From the tool's definition Open a consultation thread before starting work
Attacks that exploit this kind of access
Open a consultation thread before starting work. It is categorised as a Write tool in the Mcp Coordinator MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Coordinator MCP server in PolicyLayer and add a rule for announce_work: 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 Coordinator. Nothing to install.
announce_work 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 announce_work 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 announce_work. 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.
announce_work is provided by the Mcp Coordinator MCP server (swoofer/mcp-coordinator). 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 →