Add MCP injection support to Jupyter backend

- start_kernel() now accepts injection_code and bridge_socket_path
- Bridge Unix domain socket mounted as volume in container
- Injection code executed once on kernel startup (silent, no history)
- New _execute_injection_code() helper method with error handling
- Parameters passed through SessionManager.create_session()
- Parameters passed through JupyterBackend.execute()
- Updated JUPYTER_IMPLEMENTATION_STATUS.md

This mirrors the MCP injection pattern from the simple executor,
allowing MCP tools to be available in Jupyter sessions.

src/mcp_forge/execution/jupyter/sessions.py

@@ -121,7 +121,9 @@ class SessionManager:
         self,
         session_id: str,
         resource_limits: ResourceLimits,
-        volumes: Optional[Dict[str, dict]] = None
+        volumes: Optional[Dict[str, dict]] = None,
+        injection_code: Optional[str] = None,
+        bridge_socket_path: Optional[str] = None
     ) -> Session:
         """
         Create new stateful session.
@@ -130,6 +132,8 @@ class SessionManager:
             session_id: Unique identifier for session
             resource_limits: Resource limits for session
             volumes: Optional volume mounts
+            injection_code: Optional MCP tool injection code to execute at startup
+            bridge_socket_path: Optional path to MCP bridge socket for mounting
         
         Returns:
             Created Session object
@@ -144,8 +148,13 @@ class SessionManager:
         # Check max concurrent limit
         self._enforce_max_concurrent()
         
-        # Start kernel
-        kernel_id = self.kernel_manager.start_kernel(session_id, volumes=volumes)
+        # Start kernel with MCP injection if provided
+        kernel_id = self.kernel_manager.start_kernel(
+            session_id,
+            volumes=volumes,
+            injection_code=injection_code,
+            bridge_socket_path=bridge_socket_path
+        )
         
         # Create session
         now = datetime.utcnow()