Lab Virtual MCP Server

Instructions

Implementation Reference

• app.py:385-410 (handler)

  The entry point for the 'execute_code' MCP tool, which orchestrates code preparation and calls the execution handler.

  @mcp.tool(name="execute_code", description="Execute code in a secure sandbox environment.")
  async def execute_code(
      payload: Optional[str] = None,
      filepath: Optional[str] = None,
      latest_generated: Optional[str] = None
  ) -> str:
      """
      Executes code in a secure sandbox.
      Accepts:
      - payload: code directly
      - filepath: path to code file
      - latest_generated: fallback prompt-generated code
      """
      host_id=""
      sample_code = read_code_input(payload, filepath, latest_generated)
      
      user_access = await handle_code_execution(sample_code)
  
      if "error" in user_access:
          return f"Error: {user_access['error']}"
      
      user_access_list = json.loads(user_access['userAccess'])
  
      # # Extract the ServerIP
      server_ip = next(item['value'] for item in user_access_list if item['key'] == 'ServerIP')

• app.py:317-321 (handler)

  The handler function 'handle_code_execution' that initializes the lab session and language detection for code execution.

  async def handle_code_execution(payload: str) -> str:
      username = create_lab_sessionInfo()
      detected_lang = detect_language(payload)
      user_access = await _create_lab(username, detected_lang)
      return user_access

• app.py:325-340 (handler)

  The core logic 'run_code_in_sandbox' that performs the actual code execution by sending a request to the sandbox server.

  async def run_code_in_sandbox(host_id: str, code: str) -> dict:
      url = f"http://{host_id}:8000/run_code"
      headers = {"Content-Type": "application/json"}
      payload = {"code": code}
  
      try:
          async with httpx.AsyncClient() as client:
              response = await client.post(url, headers=headers, json=payload)
              response.raise_for_status()
              result = response.json()
          
          return json.dumps({
              "status": "success",
              "message": "Code executed successfully.",
              "result": result
          })