debug_project · Debug Companion MCP: Risk & Policy

WHAT IT DOES

What debug_project does on Debug Companion MCP

AI agents invoke debug_project to trigger actions in Debug Companion MCP. 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 debug_project needs a policy

The server description indicates it executes pytest and performs code analysis. 'debug_project' likely orchestrates multiple steps including running pytest (code execution) against a Python project. The description is empty, which lowers confidence, but the tool name and server context strongly suggest it triggers execution of tests and potentially fix suggestions.

From the tool's definition Tool name 'debug_project' on a server that 'runs pytest, extracts failure locations, displaying code context around failures' — sibling tools include 'run_pytest' and 'execute_script'-style operations.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

debug_project Rate-limited

debug_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": {
    "debug_project": {
      "limits": [
        {
          "counter": "debug_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 Debug Companion MCP, so you can run agents against it safely.

FAQ

Questions about debug_project

What does the debug_project tool do? +

debug_project. It is categorised as a Execute tool in the Debug Companion MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on debug_project? +

Register the Debug Companion MCP server in PolicyLayer and add a rule for debug_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 Debug Companion MCP. Nothing to install.

What risk level is debug_project? +

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

Can I rate-limit debug_project? +

Yes. Add a rate_limit block to the debug_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 debug_project completely? +

Set action: deny in the PolicyLayer policy for debug_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 debug_project? +

debug_project is provided by the Debug Companion MCP server (shanirap/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.