local_dev_run_tests

Run automated tests in a local development sandbox to validate code functionality and detect issues during development.

Instructions

Auto-detect and run tests in a local development environment

Input Schema

TableJSON Schema

Name	Required	Description	Default
`env_id`	Yes	Environment identifier

Implementation Reference

src/mcp_local_dev/server.py:122-149 (handler)

Tool handler logic: retrieves environment by ID, calls run_environment_tests, formats response with success, summary, and coverage.

elif name == "local_dev_run_tests":
    env = get_environment(arguments["env_id"])
    if not env:
        return [
            types.TextContent(
                type="text",
                text=json.dumps(
                    {
                        "success": False,
                        "error": f"Unknown environment: {arguments['env_id']}",
                    }
                ),
            )
        ]
    result = await run_environment_tests(env)
    response = {
        "success": result["success"],
        "summary": result["summary"],
    }
    if result.get("coverage"):
        response["coverage"] = {
            "lines": result["coverage"].lines,
            "statements": result["coverage"].statements,
            "branches": result["coverage"].branches,
            "functions": result["coverage"].functions,
            "files": result["coverage"].files
        }
    return [types.TextContent(type="text", text=json.dumps(response))]

src/mcp_local_dev/server.py:46-56 (schema)

Tool schema definition including input schema requiring 'env_id'.

types.Tool(
    name="local_dev_run_tests",
    description="Auto-detect and run tests in a local development environment",
    inputSchema={
        "type": "object",
        "properties": {
            "env_id": {"type": "string", "description": "Environment identifier"}
        },
        "required": ["env_id"],
    },
),

src/mcp_local_dev/environments/environment.py:64-71 (helper)

Helper function that invokes the test detection and running logic, with error handling.

async def run_environment_tests(env: Environment) -> Dict[str, Any]:
    """Run tests in environment."""

    try:
        return await detect_and_run_tests(env)
    except Exception as e:
        return {"success": False, "error": str(e)}

src/mcp_local_dev/test_runners/runners.py:80-91 (helper)

Core helper that detects available test runners (pytest, jest, etc.), selects first, and executes tests.

async def detect_and_run_tests(env: Environment) -> Dict[str, Any]:
    """Auto-detect and run tests in environment."""

    runners = await detect_runners(env)
    if not runners:
        return {"success": False, "error": "No test runners detected"}

    config = RunConfig(runner=runners[0], env=env, test_dirs=[env.sandbox.work_dir])
    result = await execute_runner(config)

    return result

src/mcp_local_dev/server.py:76-80 (registration)
Registration of tools list via MCP server decorator, which includes the local_dev_run_tests tool.
```
@server.list_tools()
async def list_tools() -> List[types.Tool]:
    logger.debug("Tools requested")
    return tools
```

mcp-local-dev