start_project · MCP-TY MCP: Risk & Policy

WHAT IT DOES

What start_project does on MCP-TY

AI agents invoke start_project to trigger actions in MCP-TY. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why start_project needs a policy

Starting/initializing a project tool triggers an external operation (launching the ty type checker process and setting up project context). It's not purely reading data — it sets up state and potentially creates configuration or temporary files. 'Initialize' implies side effects beyond simple data retrieval, placing it in Execute rather than Write or Read.

From the tool's definition Initialize ty for a Python project. Must be called first.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

start_project Rate-limited

start_project stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "start_project": {
      "limits": [
        {
          "counter": "start_project_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches MCP-TY, so you can run agents against it safely.

FAQ

Questions about start_project

What does the start_project tool do? +

Initialize ty for a Python project. Must be called first. It is categorised as a Execute tool in the MCP-TY MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on start_project? +

Register the MCP-TY MCP server in PolicyLayer and add a rule for start_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 MCP-TY. Nothing to install.

What risk level is start_project? +

start_project is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit start_project? +

Yes. Add a rate_limit block to the start_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 start_project completely? +

Set action: deny in the PolicyLayer policy for start_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 start_project? +

start_project is provided by the MCP-TY MCP server (qinsehm1128/mcp-ty). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.