feat: add MCP server with HTTP/SSE transport for AI integration

Exposes homelab topology to MCP-compatible AI clients (Claude Code, etc.)
over LAN via HTTP/SSE on port 8001.

- New mcp/ service: FastAPI + mcp SDK, SSE transport
- Auth: X-API-Key for AI clients, X-MCP-Service-Key for backend (Docker-internal)
- Resources: canvas, nodes, edges, scan/pending, scan/runs
- Tools: create/update/delete nodes+edges, trigger scan, approve/hide devices
- Backend deps.py: accepts JWT or MCP service key (no plain-text password)
- 40 tests (auth, resources, tools) across asyncio + trio
- docker-compose.yml: mcp service on port 8001
- README: MCP setup section with Claude Code/Desktop config examples

.env.example

@@ -15,3 +15,10 @@ SCANNER_RANGES=["192.168.1.0/24"]
 
 # Status checker interval in seconds
 STATUS_CHECKER_INTERVAL=60
+
+# MCP server — used by the mcp service (port 8001)
+# MCP_API_KEY: authenticates AI clients (Claude Code, etc.) → MCP server
+# MCP_SERVICE_KEY: authenticates MCP server → backend (never exposed externally)
+# Generate keys: python3 -c "import secrets; print(secrets.token_hex(32))"
+MCP_API_KEY=mcp_sk_changeme
+MCP_SERVICE_KEY=svc_changeme