Block until at least N other online agents are registered, or timeout. Use before the first announce_work to avoid the race where one agent announces before peers have booted.
AI agents invoke wait_for_peers to trigger actions in Mcp Coordinator. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool executes a blocking wait operation that affects the execution flow and timing of coordinated agent activities. While it doesn't directly read, write, or delete data, it does trigger and control external operations (agent registration checks) whose behavior depends on runtime arguments (the peer count threshold N and timeout). This makes it an Execute-category tool.
From the tool's definition Tool description states it 'Block[s] until at least N other online agents are registered' — this is a blocking operation that triggers external state-dependent behavior (waiting for peer agents to register).
Attacks that exploit this kind of access
Block until at least N other online agents are registered, or timeout. Use before the first announce_work to avoid the race where one agent announces before peers have booted. It is categorised as a Execute tool in the Mcp Coordinator MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Mcp Coordinator MCP server in PolicyLayer and add a rule for wait_for_peers: 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.
wait_for_peers is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the wait_for_peers 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 wait_for_peers. 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.
wait_for_peers 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 →