dialogue_create_thread · Claude Dialogue MCP: Risk & Policy

WHAT IT DOES

What dialogue_create_thread does on Claude Dialogue MCP

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

WHY IT NEEDS A POLICY

Why dialogue_create_thread needs a policy

Creating a new thread is a Write operation because it creates or modifies data reversibly. While the blast radius is limited (confined to conversation threads within a project), an AI agent could create numerous threads, pollute the project namespace, or create threads designed to confuse or mislead other Claude instances in subsequent interactions.

From the tool's definition Tool description states 'Start a new conversation thread within a project' — this creates a new entity (thread) in the shared notebook.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

dialogue_create_thread Rate-limited

dialogue_create_thread 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_create_thread": {
      "limits": [
        {
          "counter": "dialogue_create_thread_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 Claude Dialogue MCP, so you can run agents against it safely.

FAQ

Questions about dialogue_create_thread

What does the dialogue_create_thread tool do? +

Start a new conversation thread within a project. Threads are named conversations between Claude.ai and Claude Code. The initiating instance identifies itself via the. It is categorised as a Write tool in the Claude Dialogue 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 dialogue_create_thread? +

Register the Claude Dialogue MCP server in PolicyLayer and add a rule for dialogue_create_thread: 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 Claude Dialogue MCP. Nothing to install.

What risk level is dialogue_create_thread? +

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

Can I rate-limit dialogue_create_thread? +

Yes. Add a rate_limit block to the dialogue_create_thread 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_create_thread completely? +

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

dialogue_create_thread is provided by the Claude Dialogue MCP server (themethodolojeeorg/claude-dialogue-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.