dialogue_move · Warrant MCP: Risk & Policy

WHAT IT DOES

What dialogue_move does on Warrant

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

WHY IT NEEDS A POLICY

Why dialogue_move needs a policy

This tool writes a new speech act move into an ongoing dialogue, modifying the state of the dialogue. It is reversible in the sense that dialogues can be continued or revised, making it a Write operation. The blast radius is medium since misuse could corrupt argumentation state or introduce invalid moves into formal reasoning dialogues, but it has no external system effects beyond the MCP server's own data.

From the tool's definition 'Make a speech act move in a dialogue' — creates/adds a move within an existing dialogue session

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

dialogue_move Rate-limited

dialogue_move 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": {
    "dialogue_move": {
      "limits": [
        {
          "counter": "dialogue_move_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 Warrant, so you can run agents against it safely.

FAQ

Questions about dialogue_move

What does the dialogue_move tool do? +

Make a speech act move in a dialogue. It is categorised as a Write tool in the Warrant MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on dialogue_move? +

Register the Warrant MCP server in PolicyLayer and add a rule for dialogue_move: 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 Warrant. Nothing to install.

What risk level is dialogue_move? +

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

Can I rate-limit dialogue_move? +

Yes. Add a rate_limit block to the dialogue_move 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 dialogue_move completely? +

Set action: deny in the PolicyLayer policy for dialogue_move. 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 dialogue_move? +

dialogue_move is provided by the Warrant MCP server (jayden-chmod/warrant-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.