init_project · Trace MCP: Risk & Policy

WHAT IT DOES

What init_project does on Trace MCP

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

WHY IT NEEDS A POLICY

Why init_project needs a policy

The tool creates a new configuration directory and project structure on disk. This is a reversible write operation (the directory can be deleted). It does not execute code, move money, or irreversibly destroy data. Severity is low because it only scaffolds config files with minimal blast radius.

From the tool's definition Initialize a trace project with .trace-mcp config directory. Creates project structure for watch mode and caching.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

init_project Rate-limited

init_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": {
    "init_project": {
      "limits": [
        {
          "counter": "init_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 Trace MCP, so you can run agents against it safely.

FAQ

Questions about init_project

What does the init_project tool do? +

Initialize a trace project with .trace-mcp config directory. Creates project structure for watch mode and caching. It is categorised as a Write tool in the Trace 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 init_project? +

Register the Trace MCP server in PolicyLayer and add a rule for init_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 Trace MCP. Nothing to install.

What risk level is init_project? +

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

Can I rate-limit init_project? +

Yes. Add a rate_limit block to the init_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 init_project completely? +

Set action: deny in the PolicyLayer policy for init_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 init_project? +

init_project is provided by the Trace MCP server (mnehmos/mnehmos.trace.mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.