harness_check · Harness Engineering MCP: Risk & Policy

WHAT IT DOES

What harness_check does on Harness Engineering MCP

AI agents invoke harness_check to trigger actions in Harness Engineering 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 harness_check needs a policy

The tool executes scripts/checks (cross-platform replacement for PowerShell/shell scripts), running automated checks against a configuration file. This constitutes executing external operations/scripts, not merely reading data. Misuse could trigger unintended script execution or expose configuration details, warranting medium severity.

From the tool's definition 'Run Engineering Harness checks based on .harness/config.json' and described as 'Cross-platform replacement for .harness/scripts/engineering-check.ps1/sh'

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

harness_check Rate-limited

harness_check 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": {
    "harness_check": {
      "limits": [
        {
          "counter": "harness_check_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 Harness Engineering MCP, so you can run agents against it safely.

FAQ

Questions about harness_check

What does the harness_check tool do? +

Run Engineering Harness checks based on .harness/config.json. Cross-platform replacement for .harness/scripts/engineering-check.ps1/sh. Returns structured PASS/WARN/FAIL summary plus per-check details. It is categorised as a Execute tool in the Harness Engineering 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 harness_check? +

Register the Harness Engineering MCP server in PolicyLayer and add a rule for harness_check: 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 Harness Engineering MCP. Nothing to install.

What risk level is harness_check? +

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

Can I rate-limit harness_check? +

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

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

harness_check is provided by the Harness Engineering MCP server (movebrickschi/harness-engineering-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.