// SCAN REPORT

Mcp Coordinator

26 tools. 14 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 30 Jun 2026

14 can modify or destroy data

12 read-only

26 tools total

Community server · catalogue entry verified 30/06/2026

How to control Mcp Coordinator ↓

TOOL MAP

What Mcp Coordinator exposes to your agents

Read (12) Write / Execute (13) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Mcp Coordinator tools

Destructive · Medium cancel_thread Cancelling a thread is likely irreversible; once a consultation thread is cancelled, its state and any in-progress coordination/conflict resolution data are destroyed and cannot be recovered. Execute · Medium wait_for_message This tool executes a blocking operation that suspends execution pending external message receipt. Execute · Medium wait_for_peers This tool executes a blocking wait operation that affects the execution flow and timing of coordinated agent activities. Execute · Medium mqtt_publish Publishing to MQTT is an external side-effecting operation: it dispatches a message to a broker which may trigger subscribers, automation systems, or other agents.

14 of Mcp Coordinator's 26 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Mcp Coordinator

PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Coordinator, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "cancel_thread": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "announce_work": {
    "limits": [
      {
        "counter": "announce_work_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "agent_activity": {
    "limits": [
      {
        "counter": "agent_activity_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Mcp Coordinator — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON MCP COORDINATOR →

Instant setup, no code required.

FULL CATALOGUE

All 26 Mcp Coordinator tools

DESTRUCTIVE 1 tools

Destructive cancel_thread Cancel a consultation thread

EXECUTE 3 tools

Execute mqtt_publish Publish a message to an MQTT topic Execute wait_for_message Block until an MQTT consultation message arrives or timeout Execute wait_for_peers Block until at least N other online agents are registered, or timeout. Use before the first announce_work to a

WRITE 10 tools

Write announce_work Open a consultation thread before starting work Write approve_resolution Approve the proposed resolution Write close_thread Close a consultation thread Write contest_resolution Contest the proposed resolution Write heartbeat Update agent activity status and last seen timestamp Write log_action_summary Log a one-liner summary of an action Write post_to_thread Post a message to a consultation thread Write propose_resolution Propose a resolution for the consultation Write register_agent Register agent as online with module list Write set_dependency_map Load module dependency graph

READ 12 tools

Read agent_activity Get activity status for all online agents Read check_file_conflict Check if another agent is editing a file Read coordinator_status Full system status Read get_blast_radius Calculate impact of changes to a module Read get_module_info Get module dependency info Read get_queued_messages Get all queued MQTT messages without blocking Read get_session_files Get files modified in a session Read get_thread Get a thread with all messages Read get_thread_updates Get new messages since timestamp Read hot_files List files modified by multiple agents Read list_agents List registered agents Read list_threads List consultation threads

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Mcp Coordinator

Can an AI agent delete data through the Mcp Coordinator MCP server? +

Yes. The Mcp Coordinator server exposes 1 destructive tools including cancel_thread. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Mcp Coordinator? +

The Mcp Coordinator server has 10 write tools including announce_work, approve_resolution, close_thread. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Mcp Coordinator.

How many tools does the Mcp Coordinator MCP server expose? +

26 tools across 4 categories: Destructive, Execute, Read, Write. 12 are read-only. 14 can modify, create, or delete data.

How do I enforce a policy on Mcp Coordinator? +

Register the Mcp Coordinator MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Mcp Coordinator tool call.

Deterministic rules across all 26 Mcp Coordinator tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MCP COORDINATOR →

Instant setup, no code required.

26 Mcp Coordinator tools catalogued and risk-classified — across an index of 43,000+ MCP servers.