run_project_tests · AI Development Pipeline MCP

WHAT IT DOES

What run_project_tests does on AI Development Pipeline MCP

AI agents invoke run_project_tests to trigger actions in AI Development Pipeline 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_project_tests needs a policy

Running tests invokes external processes and executes code whose effects depend on test suite content and environment state. While typically intended for benign purposes, test execution can spawn side effects (file writes, network calls, environment modifications). This is Execute rather than Write because the tool triggers code execution rather than directly creating/modifying files.

From the tool's definition Tool runs project tests via npm test, yarn test, etc., which executes arbitrary code and shell commands in the development environment. The sibling tool 'run_shell_command' confirms this server has command execution capability.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_project_tests Rate-limited

run_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": {
    "run_project_tests": {
      "limits": [
        {
          "counter": "run_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 AI Development Pipeline MCP, so you can run agents against it safely.

FAQ

Questions about run_project_tests

What does the run_project_tests tool do? +

Run project tests (npm test, yarn test, etc.). It is categorised as a Execute tool in the AI Development Pipeline 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_project_tests? +

Register the AI Development Pipeline MCP server in PolicyLayer and add a rule for run_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 AI Development Pipeline MCP. Nothing to install.

What risk level is run_project_tests? +

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

Can I rate-limit run_project_tests? +

Yes. Add a rate_limit block to the run_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 run_project_tests completely? +

Set action: deny in the PolicyLayer policy for run_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 run_project_tests? +

run_project_tests is provided by the AI Development Pipeline MCP server (theburgerllc/ai-development-pipeline-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.