fix: use correct Starlette mount pattern for MCP SSE routing

The previous implementation added health route directly to mcp_app and
returned it, which broke MCP's internal /mcp endpoint routing.

Now matches the working pattern from komodo-mcp-custom:
- Mount mcp_app at / inside a parent Starlette app
- Pass lifespan=mcp_app.lifespan for proper task group init
- Health check is a separate route in the parent app

PROBLEM.md

@@ -0,0 +1,45 @@
+# PROBLEM: Monarch MCP Server SSE Routing and Handshake Failures
+
+## Issue Description
+The Monarch MCP server, implemented using `FastMCP` and `Starlette`, is experiencing persistent `404 Not Found`, `TypeError`, or `400 Bad Request` errors when AI agent clients attempt to establish an SSE connection at `http://docker.local.ben.io:8070/mcp`. While the `/health` endpoint is functioning correctly, the MCP handshake fails to complete or routes to non-existent endpoints.
+
+## Root Cause Analysis (Suspected)
+The primary issue stems from the complexity of mounting a `FastMCP` HTTP application within a `Starlette` wrapper. 
+1. **Endpoint Overlap:** `FastMCP.http_app()` generates its own internal routing (e.g., `/mcp` or `/sse`). When this app is mounted at `/mcp` in a parent `Starlette` app, the resulting path becomes `/mcp/mcp`, leading to `404` errors on the expected `/mcp` path.
+2. **ASGI Signature Mismatches:** Manual attempts to bridge the `SseServerTransport` with Starlette routes led to `TypeError: 'NoneType' object is not callable` or missing positional arguments (`receive`, `send`), indicating that the custom endpoint wrappers were not correctly following the ASGI/Starlette interface.
+3. **Transport Defaults:** `FastMCP` default transport ("streamable-http") expects specific headers and session IDs that differ from standard MCP SSE implementations, causing `400 Bad Request: Missing session ID` when using generic tools like `curl`.
+
+## Troubleshooting Steps Taken
+1. **Refactored Auth:** Removed `keyring` from the Docker runtime to prevent headless environment crashes; moved to `MONARCH_TOKEN` environment variable.
+2. **Infrastructure Validation:** Verified port `8070` is unique on the `local.ben.io` server.
+3. **Internal Logic Debugging:**
+   - Attempted mounting `FastMCP` at root (`/`) and sub-paths (`/mcp`).
+   - Inspected `FastMCP` source code to identify internal attributes (`_mcp_server`, `_lifespan`).
+   - Switched from manual `SseServerTransport` handling to `mcp.http_app()`.
+4. **Endpoint Verification:** 
+   - Confirmed `/health` returns `200 OK`.
+   - Tested `/mcp` with `Accept: text/event-stream`, which yielded `400 Bad Request` or `406 Not Acceptable` depending on the mount point.
+5. **Session Exploration:** Investigated OpenCode session storage (`~/.local/share/opencode/storage/session/`) to understand how clients identify and connect to projects.
+
+## Current State
+The server is running in a Komodo stack, healthy on port `8070`, and visible at `https://monarch-mcp.ext.ben.io`. However, the handshake remains broken. 
+
+## Resolution (Applied)
+The fix was to match the working pattern from `komodo-mcp-custom`:
+
+```python
+def create_app():
+    mcp_app = mcp.http_app()
+    routes = [
+        Route("/health", health, methods=["GET"]),
+        Mount("/", app=mcp_app),  # MCP handles /mcp endpoint internally
+    ]
+    return Starlette(routes=routes, lifespan=mcp_app.lifespan)
+
+app = create_app()
+```
+
+Key changes:
+1. **Mount at root:** `Mount("/", app=mcp_app)` lets FastMCP handle `/mcp` internally
+2. **Pass lifespan:** `lifespan=mcp_app.lifespan` ensures proper task group initialization
+3. **Separate health route:** `/health` is a standalone route in the parent Starlette app

src/monarch_mcp_custom/server.py

@@ -5,17 +5,13 @@ Monarch Money MCP Server - Custom SSE Implementation.
 import os
 import logging
 import json
-import asyncio
+from typing import Optional, Any
-from typing import Optional, List, Dict, Any
-from datetime import datetime
 
 from dotenv import load_dotenv
 from fastmcp import FastMCP
 from starlette.applications import Starlette
 from starlette.responses import JSONResponse
 from starlette.routing import Route, Mount
-from mcp.server.sse import SseServerTransport
-import uvicorn
 
 from monarch_mcp_custom.auth import get_authenticated_client
 
@@ -166,35 +162,36 @@ async def refresh_accounts() -> str:
         return f"Error: {str(e)}"
 
 
-# --- Health Check ---
+# --- Health Check Endpoint ---
 
 
-async def health_check(request):
+async def health(request):
-    """Simple health check endpoint."""
+    """Health check endpoint for Docker."""
-    return JSONResponse({"status": "ok", "timestamp": datetime.now().isoformat()})
+    return JSONResponse({"status": "ok"})
 
 
-# --- ASGI App Setup ---
+# --- ASGI Application ---
 
 
-def create_app() -> Starlette:
+def create_app():
-    """Create the Starlette application with health check and MCP."""
+    """Create the ASGI application with health check and MCP routes."""
     mcp_app = mcp.http_app()
 
-    # Add health check route directly to the MCP app
+    # Wrapper app: /health is standalone, everything else goes to MCP
-    mcp_app.add_route("/health", health_check, methods=["GET"])
+    # IMPORTANT: Must pass mcp_app.lifespan for task group initialization
+    routes = [
+        Route("/health", health, methods=["GET"]),
+        Mount("/", app=mcp_app),  # MCP handles /mcp endpoint
+    ]
 
-    return mcp_app
+    return Starlette(routes=routes, lifespan=mcp_app.lifespan)
 
 
+# Create the app instance for uvicorn
 app = create_app()
 
 
-def main():
-    """Entry point for running the server."""
-    port = int(os.getenv("PORT", 8000))
-    uvicorn.run(app, host="0.0.0.0", port=port)
-
-
 if __name__ == "__main__":
-    main()
+    import uvicorn
+
+    uvicorn.run(app, host="0.0.0.0", port=8000)