// SCAN REPORT

Claude Mesh

4 tools. 3 can modify or destroy data without limits.

3 write tools that can modify data. Rate limits recommended.

Last updated: 11 Jun 2026

3 can modify or destroy data

1 read-only

4 tools total

Community server · catalogue entry verified 11/06/2026

How to control Claude Mesh ↓

TOOL MAP

What Claude Mesh exposes to your agents

Read (1) Write / Execute (3) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Claude Mesh tools

Execute · High respond_to_permission This tool approves or denies permission requests from other Claude instances in the mesh network. Write · High send_to_peer This is a Write category tool because it creates new message data that persists in the system. Write · Low set_summary This tool creates or updates a summary document that describes current work status.

3 of Claude Mesh's 4 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Claude Mesh

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

Rate limit write operations

{
  "send_to_peer": {
    "limits": [
      {
        "counter": "send_to_peer_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "list_peers": {
    "limits": [
      {
        "counter": "list_peers_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 Claude Mesh — 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 CLAUDE MESH →

Free to start. No card required.

FULL CATALOGUE

All 4 Claude Mesh tools

EXECUTE 1 tools

Execute respond_to_permission Allow or deny a pending permission_request from a peer. Only valid if a request with this request_id is live.

WRITE 2 tools

Write send_to_peer Send a message to a teammate (by handle) or the whole team (@team). Write set_summary Publish a short summary of what this Claude is working on.

READ 1 tools

Read list_peers List team members and their current summaries.

FAQ

Questions about Claude Mesh

How do I prevent bulk modifications through Claude Mesh? +

The Claude Mesh server has 2 write tools including send_to_peer, set_summary. 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 Claude Mesh.

How many tools does the Claude Mesh MCP server expose? +

4 tools across 2 categories: Read, Write. 1 are read-only. 3 can modify, create, or delete data.

How do I enforce a policy on Claude Mesh? +

Register the Claude Mesh 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 Claude Mesh tool call.

Deterministic rules across all 4 Claude Mesh tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON CLAUDE MESH →

Free to start. No card required.

4 Claude Mesh tools catalogued and risk-classified — across an index of 43,000+ MCP servers.