dialogue_create_project · Claude Dialogue MCP: Risk & Policy

WHAT IT DOES

What dialogue_create_project does on Claude Dialogue MCP

AI agents use dialogue_create_project 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_project needs a policy

This tool creates a new project, which is a data structure in a file-based notebook system. It modifies state by adding a new entity, but the operation is reversible (the project can be deleted). There are no side effects beyond creating a folder/container, no code execution, no data deletion, and no financial impact.

From the tool's definition Tool description states 'Create a new project folder in the shared dialogue workspace' — the verb 'create' and action of instantiating a new container is a reversible write operation.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

dialogue_create_project Rate-limited

dialogue_create_project 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_project": {
      "limits": [
        {
          "counter": "dialogue_create_project_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_project

What does the dialogue_create_project tool do? +

Create a new project folder in the shared dialogue workspace. Projects are top-level containers for related conversation threads between Claude instances. Examples:. 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_project? +

Register the Claude Dialogue MCP server in PolicyLayer and add a rule for dialogue_create_project: 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_project? +

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

Can I rate-limit dialogue_create_project? +

Yes. Add a rate_limit block to the dialogue_create_project 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_project completely? +

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

dialogue_create_project 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.