feat: add MCP server module exposing search_regulations tool

- New backend/app/mcp/ module: MCPServer instance with a single
  search_regulations tool backed by the existing AgentConversationService.
- MCPAuthMiddleware reuses existing JWT auth (no new auth mechanism).
- Mounted at /mcp/ in api/main.py via Streamable HTTP transport; wired the
  MCP session manager into the existing lifespan() via AsyncExitStack
  (app.mount() does not propagate nested ASGI lifespans automatically).
- Fixed a doubled /mcp/mcp path by setting streamable_http_path to "/"
  (MCPServer.streamable_http_app() defaults to registering its own /mcp route).
- Verified end-to-end with the real mcp Python client: list_tools() returns
  search_regulations, auth correctly 401s without or with an invalid token.
- 7 new tests, 76 total (up from 69), all passing.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

backend/app/api/main.py

@@ -1,6 +1,6 @@
 """FastAPI application entrypoint."""
 
-from contextlib import asynccontextmanager
+from contextlib import AsyncExitStack, asynccontextmanager
 
 from fastapi import FastAPI, Request
 from fastapi.encoders import jsonable_encoder
@@ -13,6 +13,7 @@ from app.api.models import ErrorResponse
 from app.api.routes import api_router
 from app.config.logging import setup_logging
 from app.config.settings import settings
+from app.mcp.server import build_mcp_asgi_app
 from app.shared.bootstrap import cleanup_runtime_dependencies, preload_runtime_dependencies
 from app.shared.errors import VectorStoreSchemaError
 # Keep module behavior explicit so the backend flow stays easy to audit.
@@ -20,19 +21,32 @@ from app.shared.errors import VectorStoreSchemaError
 
 setup_logging(level="INFO" if not settings.debug else "DEBUG")
 
+# Built once at module scope so both lifespan() and app.mount() below reference
+# the same instance — mounting a second, separately-built instance would start
+# a second, unrelated MCP session manager.
+mcp_app = build_mcp_asgi_app()
+
 
 @asynccontextmanager
 async def lifespan(app: FastAPI):
     """Application lifecycle hooks."""
-    logger.info(f"启动 {settings.app_name} v{settings.app_version}")
-    logger.info(f"调试模式: {settings.debug}")
-    logger.info("预加载LLM客户端...")
-    preload_runtime_dependencies()
+    # FastMCP-style servers own a session manager that only starts via its own
+    # lifespan context. app.mount() does NOT propagate nested ASGI lifespans
+    # automatically (confirmed Starlette/ASGI limitation) — without this,
+    # every search_regulations call would fail because the MCP session
+    # manager was never started.
+    async with AsyncExitStack() as stack:
+        await stack.enter_async_context(mcp_app.router.lifespan_context(mcp_app))
 
-    yield
+        logger.info(f"启动 {settings.app_name} v{settings.app_version}")
+        logger.info(f"调试模式: {settings.debug}")
+        logger.info("预加载LLM客户端...")
+        preload_runtime_dependencies()
 
-    logger.info("应用关闭，执行清理...")
-    cleanup_runtime_dependencies()
+        yield
+
+        logger.info("应用关闭，执行清理...")
+        cleanup_runtime_dependencies()
 
 
 app = FastAPI(
@@ -65,6 +79,7 @@ app.add_middleware(
 app.add_middleware(AuditMiddleware)
 
 app.include_router(api_router, prefix="/api/v1")
+app.mount("/mcp", mcp_app)
 
 
 @app.exception_handler(VectorStoreSchemaError)

backend/app/mcp/__init__.py

@@ -0,0 +1,8 @@
+"""MCP (Model Context Protocol) server module.
+
+Exposes selected read-only platform capabilities — currently only regulation
+search — as MCP tools so external MCP clients (Claude Desktop, GitHub Copilot,
+Cursor, etc.) can query this platform's compliance knowledge base directly.
+"""
+# Kept deliberately empty beyond this docstring — see server.py for the
+# actual FastMCP instance and tool/middleware definitions.

backend/app/mcp/server.py

@@ -0,0 +1,88 @@
+"""MCPServer instance exposing the compliance knowledge base as an MCP tool.
+
+This module is a pure protocol adapter: search_regulations() below calls the
+existing AgentConversationService.ask() (the same application service backing
+the /api/v1/agent/ask REST endpoint) and reshapes its result into a plain
+dict. No new retrieval, ranking, or LLM orchestration logic lives here.
+"""
+
+from __future__ import annotations
+
+from mcp.server import MCPServer
+from starlette.responses import PlainTextResponse
+from starlette.types import ASGIApp, Receive, Scope, Send
+
+from app.config.settings import settings
+from app.shared.bootstrap import get_agent_conversation_service, get_jwt_handler
+
+# Single shared MCPServer instance — analogous to the single shared FastAPI
+# `app` instance in app/api/main.py. Tools registered via @mcp.tool() below.
+# Note: the installed mcp SDK (2.0.0) renamed the older "FastMCP" class to
+# "MCPServer" (mcp.server.mcpserver.MCPServer); the .tool()/.streamable_http_app()
+# API surface used here is unchanged across that rename.
+mcp = MCPServer("ai-regulations")
+
+
+@mcp.tool()
+def search_regulations(query: str, top_k: int = 5) -> dict:
+    """Search the compliance knowledge base and return a grounded answer.
+
+    query: Natural-language search question, e.g. "国六排放标准最新要求".
+    top_k: Maximum number of cited sources to return (default 5).
+    """
+    # No session_id is passed: this keeps each call stateless (no
+    # ConversationStore reads/writes), matching "search" semantics rather
+    # than multi-turn chat semantics.
+    _, result = get_agent_conversation_service().ask(query=query, top_k=top_k)
+    return {
+        "answer": result.answer,
+        "sources": [source.__dict__ for source in result.sources],
+    }
+
+
+class MCPAuthMiddleware:
+    """Reject unauthenticated requests before they reach the MCP protocol handler.
+
+    Mirrors the existing get_current_user dependency's behavior (auth.py) but
+    implemented as raw ASGI middleware, since the mounted MCP app is a plain
+    ASGI app, not a FastAPI/APIRouter instance that supports Depends().
+    """
+
+    def __init__(self, app: ASGIApp) -> None:
+        """Store the wrapped ASGI app to delegate to once auth passes."""
+        self.app = app
+
+    async def __call__(self, scope: Scope, receive: Receive, send: Send) -> None:
+        """Validate the bearer token for HTTP requests; pass non-HTTP scopes through."""
+        # Only HTTP requests carry an Authorization header to check; lifespan
+        # and other scope types must always pass through untouched.
+        if scope["type"] != "http" or not settings.auth_enabled:
+            await self.app(scope, receive, send)
+            return
+
+        headers = dict(scope["headers"])
+        auth_header = headers.get(b"authorization", b"").decode()
+        token = auth_header.removeprefix("Bearer ").strip()
+        try:
+            get_jwt_handler().decode_token(token)
+        except ValueError as exc:
+            # Reject before the MCP session/protocol layer ever sees the request.
+            response = PlainTextResponse(str(exc), status_code=401)
+            await response(scope, receive, send)
+            return
+
+        await self.app(scope, receive, send)
+
+
+def build_mcp_asgi_app() -> ASGIApp:
+    """Return the Streamable HTTP ASGI app for the MCP server, auth-guarded.
+
+    streamable_http_path="/" is required here: MCPServer.streamable_http_app()
+    registers its own internal route at "/mcp" by default, and this app is
+    itself mounted at "/mcp" in api/main.py — without overriding the internal
+    path to "/", the effective external path would be the confusing "/mcp/mcp"
+    instead of "/mcp".
+    """
+    asgi_app = mcp.streamable_http_app(streamable_http_path="/")
+    asgi_app.add_middleware(MCPAuthMiddleware)
+    return asgi_app

backend/requirements.txt

@@ -2,6 +2,10 @@
 fastapi>=0.110.0
 uvicorn[standard]>=0.27.0
 python-multipart>=0.0.9
+# MCP server module (backend/app/mcp/) — pin >=2.0.0: that release renamed the
+# older "FastMCP" class to "MCPServer" (mcp.server.MCPServer), which is the
+# class actually used in app/mcp/server.py.
+mcp>=2.0.0
 
 # ── Config & utilities ────────────────────────────────────────────────────────
 pydantic>=2.0.0

backend/tests/mcp/__init__.py

@@ -0,0 +1,2 @@
+"""Test package for the MCP module (backend/app/mcp/)."""
+# Empty package marker — no shared fixtures needed yet for this small test suite.

backend/tests/mcp/test_mcp_auth_middleware.py

@@ -0,0 +1,85 @@
+"""Unit tests for MCPAuthMiddleware.
+
+Wraps a minimal dummy ASGI app (not the real MCP app) so these tests exercise
+only the auth gate, not the MCP protocol itself — keeps the test fast and
+independent of FastMCP internals.
+"""
+
+from __future__ import annotations
+
+import sys
+from unittest.mock import MagicMock, patch
+
+# app.mcp.server imports app.shared.bootstrap at module scope (needed for
+# get_agent_conversation_service/get_jwt_handler), which in turn eagerly
+# imports several Postgres store modules that do `import psycopg2` at their
+# own module scope. Since this is the only test file in backend/tests/mcp/
+# that imports app.mcp.server at module scope (not inside a test function),
+# it is the first thing to trigger that chain during pytest collection —
+# guard psycopg2 here the same way backend/tests/observability/
+# test_model_usage_bootstrap.py and test_model_usage_persistence.py already
+# do, so a real (network-connecting) psycopg2 never gets bound first.
+mock_psycopg2 = MagicMock()
+mock_psycopg2.extras = MagicMock()
+sys.modules.setdefault("psycopg2", mock_psycopg2)
+sys.modules.setdefault("psycopg2.extras", mock_psycopg2.extras)
+sys.modules.setdefault("psycopg2.pool", MagicMock())
+
+from starlette.applications import Starlette
+from starlette.responses import PlainTextResponse
+from starlette.routing import Route
+from starlette.testclient import TestClient
+
+from app.mcp.server import MCPAuthMiddleware
+
+
+def _dummy_app() -> Starlette:
+    """Build a minimal Starlette app that MCPAuthMiddleware can wrap."""
+    async def _ok(request):
+        """Return a fixed 200 response so tests can assert pass-through."""
+        return PlainTextResponse("ok")
+
+    app = Starlette(routes=[Route("/ping", _ok)])
+    app.add_middleware(MCPAuthMiddleware)
+    return app
+
+
+def test_missing_token_rejected_when_auth_enabled():
+    """No Authorization header + auth_enabled=True -> 401."""
+    with patch("app.mcp.server.settings") as fake_settings:
+        fake_settings.auth_enabled = True
+        client = TestClient(_dummy_app())
+        response = client.get("/ping")
+    assert response.status_code == 401
+
+
+def test_invalid_token_rejected_when_auth_enabled():
+    """A token that fails decode_token() -> 401, request never reaches the app."""
+    fake_handler = type("H", (), {"decode_token": lambda self, t: (_ for _ in ()).throw(ValueError("bad token"))})()
+    with patch("app.mcp.server.settings") as fake_settings, \
+         patch("app.mcp.server.get_jwt_handler", return_value=fake_handler):
+        fake_settings.auth_enabled = True
+        client = TestClient(_dummy_app())
+        response = client.get("/ping", headers={"Authorization": "Bearer garbage"})
+    assert response.status_code == 401
+
+
+def test_valid_token_passes_through_when_auth_enabled():
+    """A token that decodes successfully -> request reaches the wrapped app."""
+    fake_handler = type("H", (), {"decode_token": lambda self, t: object()})()
+    with patch("app.mcp.server.settings") as fake_settings, \
+         patch("app.mcp.server.get_jwt_handler", return_value=fake_handler):
+        fake_settings.auth_enabled = True
+        client = TestClient(_dummy_app())
+        response = client.get("/ping", headers={"Authorization": "Bearer good"})
+    assert response.status_code == 200
+    assert response.text == "ok"
+
+
+def test_auth_disabled_always_passes_through():
+    """auth_enabled=False (dev mode) -> no token needed, matches get_current_user's dev bypass."""
+    with patch("app.mcp.server.settings") as fake_settings:
+        fake_settings.auth_enabled = False
+        client = TestClient(_dummy_app())
+        response = client.get("/ping")
+    assert response.status_code == 200

backend/tests/mcp/test_search_regulations_tool.py

@@ -0,0 +1,77 @@
+"""Unit tests for the search_regulations MCP tool function.
+
+Mocks AgentConversationService so no real retrieval/LLM call happens —
+verifies only the protocol-adapter contract: correct call shape in,
+correct dict shape out.
+"""
+
+from __future__ import annotations
+
+from dataclasses import dataclass
+from unittest.mock import MagicMock, patch
+
+
+@dataclass
+class _FakeSource:
+    """Minimal stand-in for a real Source dataclass (only __dict__ is used)."""
+
+    doc_id: str
+    doc_title: str
+    score: float
+
+
+@dataclass
+class _FakeAnswerResult:
+    """Minimal stand-in for AnswerResult — only .answer/.sources are read."""
+
+    answer: str
+    sources: list
+
+
+def test_search_regulations_calls_agent_ask_without_session():
+    """search_regulations must call ask() with no session_id (stateless search)."""
+    from app.mcp.server import search_regulations
+
+    fake_service = MagicMock()
+    fake_service.ask.return_value = (
+        None,
+        _FakeAnswerResult(answer="国六排放标准要求...", sources=[_FakeSource("doc-1", "国六标准", 0.9)]),
+    )
+
+    with patch("app.mcp.server.get_agent_conversation_service", return_value=fake_service):
+        search_regulations(query="国六排放标准最新要求", top_k=3)
+
+    fake_service.ask.assert_called_once_with(query="国六排放标准最新要求", top_k=3)
+    assert "session_id" not in fake_service.ask.call_args.kwargs
+
+
+def test_search_regulations_shapes_response_dict():
+    """The returned dict must expose 'answer' and 'sources' (list of plain dicts)."""
+    from app.mcp.server import search_regulations
+
+    fake_service = MagicMock()
+    fake_service.ask.return_value = (
+        None,
+        _FakeAnswerResult(answer="答案文本", sources=[_FakeSource("doc-2", "国标GB1589", 0.8)]),
+    )
+
+    with patch("app.mcp.server.get_agent_conversation_service", return_value=fake_service):
+        result = search_regulations(query="q")
+
+    assert result == {
+        "answer": "答案文本",
+        "sources": [{"doc_id": "doc-2", "doc_title": "国标GB1589", "score": 0.8}],
+    }
+
+
+def test_search_regulations_default_top_k():
+    """top_k defaults to 5 when the caller omits it."""
+    from app.mcp.server import search_regulations
+
+    fake_service = MagicMock()
+    fake_service.ask.return_value = (None, _FakeAnswerResult(answer="a", sources=[]))
+
+    with patch("app.mcp.server.get_agent_conversation_service", return_value=fake_service):
+        search_regulations(query="q")
+
+    assert fake_service.ask.call_args.kwargs["top_k"] == 5