coverage · Python MCP: Risk & Policy

WHAT IT DOES

What coverage does on Python

AI agents invoke coverage to trigger actions in Python. 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 coverage needs a policy

The tool executes a test runner (with coverage instrumentation) against the codebase. Running tests constitutes code execution with side effects that depend on the test suite content. While primarily observational (returns structured coverage data), the act of running tests can trigger arbitrary code execution, making Execute the appropriate category.

From the tool's definition "Runs tests with coverage" — actively executes the test suite and coverage analysis tool

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

coverage Rate-limited

coverage 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": {
    "coverage": {
      "limits": [
        {
          "counter": "coverage_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 Python, so you can run agents against it safely.

FAQ

Questions about coverage

What does the coverage tool do? +

Runs tests with coverage and returns structured coverage summary per file. It is categorised as a Execute tool in the Python MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on coverage? +

Register the Python MCP server in PolicyLayer and add a rule for coverage: 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 Python. Nothing to install.

What risk level is coverage? +

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

Can I rate-limit coverage? +

Yes. Add a rate_limit block to the coverage 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 coverage completely? +

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

coverage is provided by the Python MCP server (Dave-London/Pare). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// THE FULL RECORD

coverage is one line of Python's registry record.

The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →