clean_project · ESP-IDF FastMCP Server MCP: Risk & Policy

WHAT IT DOES

What clean_project does on ESP-IDF FastMCP Server

AI agents invoke clean_project to trigger actions in ESP-IDF FastMCP Server. 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 clean_project needs a policy

Cleaning a project executes external build commands whose effects depend on the project context and can irreversibly remove build artifacts, object files, and intermediate outputs. While not destructive to source code, it is an active operation that triggers external execution and could disrupt a developer's workflow.

From the tool's definition Tool performs 'clean' operations on ESP-IDF projects, which executes build system commands (typically 'idf.py clean' or similar) that modify the project's build artifacts and state.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

clean_project Rate-limited

clean_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": {
    "clean_project": {
      "limits": [
        {
          "counter": "clean_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 ESP-IDF FastMCP Server, so you can run agents against it safely.

FAQ

Questions about clean_project

What does the clean_project tool do? +

Clean ESP-IDF project. Use this tool to clean project instead of run clean command directly. It is categorised as a Execute tool in the ESP-IDF FastMCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on clean_project? +

Register the ESP-IDF FastMCP Server MCP server in PolicyLayer and add a rule for clean_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 ESP-IDF FastMCP Server. Nothing to install.

What risk level is clean_project? +

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

Can I rate-limit clean_project? +

Yes. Add a rate_limit block to the clean_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 clean_project completely? +

Set action: deny in the PolicyLayer policy for clean_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 clean_project? +

clean_project is provided by the ESP-IDF FastMCP Server MCP server (jasper-zsh/espidf-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.