run_linter · Reviewer MCP: Risk & Policy

WHAT IT DOES

What run_linter does on Reviewer MCP

AI agents invoke run_linter to trigger actions in Reviewer 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 run_linter needs a policy

The tool invokes a linter (a code analysis tool), which is a form of code execution. While linters are generally safe read-only analysis tools that don't modify code, they still execute external processes. The severity is low because linters have minimal blast radius—they typically only produce analysis output without side effects.

From the tool's definition Tool performs 'Run standardized linter' which executes an external process/tool on project code. This is a runtime execution action whose output and side effects depend on the project contents being linted.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_linter Rate-limited

run_linter 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": {
    "run_linter": {
      "limits": [
        {
          "counter": "run_linter_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 Reviewer MCP, so you can run agents against it safely.

FAQ

Questions about run_linter

What does the run_linter tool do? +

Run standardized linter for the project. It is categorised as a Execute tool in the Reviewer 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 run_linter? +

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

What risk level is run_linter? +

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

Can I rate-limit run_linter? +

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

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

run_linter is provided by the Reviewer MCP server (jaggederest/mcp_reviewer). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.