lichess_send_chat · Lichess MCP: Risk & Policy

WHAT IT DOES

What lichess_send_chat does on Lichess MCP

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

WHY IT NEEDS A POLICY

Why lichess_send_chat needs a policy

This tool creates new data (chat messages) in a reversible manner. Messages can typically be deleted, edited, or ignored. There is no code execution, data deletion, or financial impact. The blast radius is minimal — an AI sending unwanted or inappropriate chat messages would be a minor annoyance rather than a security risk, and the chat is scoped to an active game.

From the tool's definition Tool name 'lichess_send_chat' and description states it 'Send a chat message in an active Lichess chess game' — this creates/writes a new message that is visible to other players/spectators.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

lichess_send_chat Rate-limited

lichess_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": {
    "lichess_send_chat": {
      "limits": [
        {
          "counter": "lichess_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 Lichess MCP, so you can run agents against it safely.

FAQ

Questions about lichess_send_chat

What does the lichess_send_chat tool do? +

Send a chat message in an active Lichess chess game, to the player or spectator chat room. It is categorised as a Write tool in the Lichess MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on lichess_send_chat? +

Register the Lichess MCP server in PolicyLayer and add a rule for lichess_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 Lichess MCP. Nothing to install.

What risk level is lichess_send_chat? +

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

Can I rate-limit lichess_send_chat? +

Yes. Add a rate_limit block to the lichess_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 lichess_send_chat completely? +

Set action: deny in the PolicyLayer policy for lichess_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 lichess_send_chat? +

lichess_send_chat is provided by the Lichess MCP server (jamespdaily/lichess-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.