send-chat · Defcon MCP: Risk & Policy

WHAT IT DOES

What send-chat does on Defcon

AI agents use send-chat to create or update resources in Defcon — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Defcon environment.

WHY IT NEEDS A POLICY

Why send-chat needs a policy

The send-chat tool creates new data (chat messages) that persist in the game state and are visible to other players. This is a reversible write operation—messages can be deleted or ignored, and they have no destructive consequences. While chat could theoretically be misused to spread misinformation or harassment within the game, the blast radius is limited to social/reputational impact within a single game session.

From the tool's definition Tool description states it 'Sends a chat message visible to all players in the game'. This is a write operation that creates a new message/communication artifact.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

send-chat Rate-limited

send-chat stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "send-chat": {
      "limits": [
        {
          "counter": "send-chat_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Defcon, so you can run agents against it safely.

FAQ

Questions about send-chat

What does the send-chat tool do? +

Sends a chat message visible to all players in the game. It is categorised as a Write tool in the Defcon MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on send-chat? +

Register the Defcon MCP server in PolicyLayer and add a rule for send-chat: 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 Defcon. Nothing to install.

What risk level is send-chat? +

send-chat is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit send-chat? +

Yes. Add a rate_limit block to the send-chat 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.

How do I block send-chat completely? +

Set action: deny in the PolicyLayer policy for send-chat. 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.

What MCP server provides send-chat? +

send-chat is provided by the Defcon MCP server (jorisvddonk/defcon-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.