start_project_tests · Openl MCP: Risk & Policy

WHAT IT DOES

What start_project_tests does on Openl

AI agents invoke start_project_tests to trigger actions in Openl. 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 start_project_tests needs a policy

This tool executes test code against a project, which constitutes running code with effects that depend on what tests are configured and what they test. While not arbitrary code execution, it triggers external operations that can modify system state (e.g., test databases, mock services). This is Execute rather than Write because tests inherently run code rather than merely creating/modifying data structures.

From the tool's definition 'Start project test execution' indicates the tool triggers automated test runs, which are external operations whose effects depend on test configuration and arguments.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

start_project_tests Rate-limited

start_project_tests 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": {
    "start_project_tests": {
      "limits": [
        {
          "counter": "start_project_tests_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 Openl, so you can run agents against it safely.

FAQ

Questions about start_project_tests

What does the start_project_tests tool do? +

Start project test execution. For design repositories the project is automatically opened if closed; for repository. It is categorised as a Execute tool in the Openl MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on start_project_tests? +

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

What risk level is start_project_tests? +

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

Can I rate-limit start_project_tests? +

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

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

start_project_tests is provided by the Openl MCP server (openl-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.