// SCAN REPORT

CC2CC

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

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

Last updated: 12 Jun 2026

4 can modify or destroy data

3 read-only

7 tools total

Community server · catalogue entry verified 12/06/2026

How to control CC2CC ↓

TOOL MAP

What CC2CC exposes to your agents

Read (3) Write / Execute (4) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous CC2CC tools

Write · Medium broadcast This tool creates and sends messages to all known agents on the local machine, which is a Write operation that modifies state (agents receive new messages). Write · Medium register The tool modifies agent identity or registration state, which is a reversible write operation affecting this agent's configuration within the inter-agent communication system. Write · Medium reply The tool creates new reply messages and modifies task completion state. Write · Medium send This tool creates or modifies data reversibly by writing messages to the file-based communication system between Claude Code instances.

4 of CC2CC's 7 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control CC2CC

PolicyLayer is an MCP gateway — it sits between your AI agents and CC2CC, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "broadcast": {
    "limits": [
      {
        "counter": "broadcast_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "check_inbox": {
    "limits": [
      {
        "counter": "check_inbox_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 CC2CC — 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 CC2CC →

Free to start. No card required.

FULL CATALOGUE

All 7 CC2CC tools

WRITE 4 tools

Write broadcast Send a message to all known agents Write register Change this agent Write reply Reply to a received message by msg_id. Auto-completes tasks when replying to task messages. Write send Send a message to another agent. Notes if the recipient is offline.

READ 3 tools

Read check_inbox Check for new incoming messages. Also happens automatically on every other tool call. Read list_agents Returns all known agents with their status (online/offline) and last seen time Read whoami Returns this agent

FAQ

Questions about CC2CC

How do I prevent bulk modifications through CC2CC? +

The CC2CC server has 4 write tools including broadcast, register, reply. 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 CC2CC.

How many tools does the CC2CC MCP server expose? +

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

How do I enforce a policy on CC2CC? +

Register the CC2CC 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 CC2CC tool call.

Deterministic rules across all 7 CC2CC tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON CC2CC →

Free to start. No card required.

7 CC2CC tools catalogued and risk-classified — across an index of 43,000+ MCP servers.