qonto-assistant/src/qonto_assistant/app.py
tegwick d2ffd372b5 QONTO-WP-0003-T03: MCP client auth + shared multi-harness config snippet
Gate /mcp with a shared-secret bearer token (QONTO_ASSISTANT_MCP_TOKEN,
mcp_auth.py::BearerTokenAuthMiddleware, constant-time compare, REST
untouched) since no OIDC issuer exists in this fleet yet -- pointing
FastMCP's OAuth Protected Resource flow at a non-existent issuer would be
worse than not having it. This token is a service credential, never a bank
credential; per-actor identity stays the existing X-Actor-* convention.

Add docs/mcp-integration.md: tool catalog, the two-layer auth model (workload
auth today vs. deferred OIDC target), and one shared {"mcpServers": {...}}
client config snippet (url + headers) usable across Claude Code, Claude
Desktop, Cursor, and Codex/Grok-style harnesses.

Verified live using only that snippet: unauthenticated and wrong-token
requests get 401 before reaching any tool; a request built from the
snippet's URL + headers lists tools and calls qonto_org_summary
successfully against the fixture-backed server.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-07-23 09:41:25 +02:00

186 lines
6.6 KiB
Python

from __future__ import annotations
from collections.abc import AsyncIterator, Callable
from contextlib import AsyncExitStack, asynccontextmanager, suppress
import logging
from uuid import uuid4
import uvicorn
from fastapi import FastAPI, Request
from fastapi.responses import JSONResponse
from starlette.concurrency import run_in_threadpool
from qonto_assistant import __version__
from qonto_assistant.audit import AuditLogger
from qonto_assistant.auth import actor_claims_from_request
from qonto_assistant.config import Settings
from qonto_assistant.credentials import build_credential_provider
from qonto_assistant.errors import QontoAssistantError, UpstreamError
from qonto_assistant.mcp_auth import BearerTokenAuthMiddleware
from qonto_assistant.mcp_server import create_mcp_server
from qonto_assistant.policy import PolicyEngine
from qonto_assistant.qonto_client import FixtureQontoClient, QontoClient
from qonto_assistant.rate_limits import ConcurrencyLimiter, RateLimiter
from qonto_assistant.service import CapabilityService
def create_app(
*,
settings: Settings | None = None,
service: CapabilityService | None = None,
audit_logger: AuditLogger | None = None,
rate_limiter: RateLimiter | None = None,
concurrency_limiter: ConcurrencyLimiter | None = None,
) -> FastAPI:
settings = settings or Settings.from_env()
audit_logger = audit_logger or AuditLogger()
service = service or _build_service(
settings=settings,
audit_logger=audit_logger,
rate_limiter=rate_limiter,
concurrency_limiter=concurrency_limiter,
)
mcp_server = create_mcp_server(settings=settings, service=service)
mcp_app = mcp_server.streamable_http_app()
if settings.mcp_auth_token:
mcp_app.add_middleware(BearerTokenAuthMiddleware, token=settings.mcp_auth_token)
@asynccontextmanager
async def lifespan(_: FastAPI) -> AsyncIterator[None]:
async with AsyncExitStack() as stack:
await stack.enter_async_context(mcp_app.router.lifespan_context(mcp_app))
yield
with suppress(Exception):
service.client.close()
app = FastAPI(title="qonto-assistant", version=__version__, lifespan=lifespan)
app.state.settings = settings
app.state.service = service
app.mount("/mcp", mcp_app)
@app.exception_handler(QontoAssistantError)
def handle_qonto_error(_: Request, exc: QontoAssistantError) -> JSONResponse:
body = {"error_code": exc.error_code, "detail": exc.message}
if isinstance(exc, UpstreamError) and exc.upstream_status is not None:
body["upstream_status"] = exc.upstream_status
return JSONResponse(status_code=exc.status_code, content=body)
@app.get("/v1/health")
async def health() -> dict[str, str]:
return {
"status": "ok",
"service": settings.service_name,
"version": __version__,
"policy_file": str(settings.policy_file),
}
@app.get("/v1/accounts")
async def get_accounts(request: Request) -> JSONResponse:
claims = actor_claims_from_request(request, settings)
request_id = _request_id(request)
payload = await run_in_threadpool(service.get_accounts, claims=claims, request_id=request_id)
return JSONResponse(content=payload, headers={"X-Request-ID": request_id})
@app.get("/v1/transactions")
async def get_transactions(
request: Request,
account_slug: str | None = None,
page: int = 1,
page_size: int = 50,
window_days: int = 31,
status: str | None = "completed",
side: str | None = None,
) -> JSONResponse:
claims = actor_claims_from_request(request, settings)
request_id = _request_id(request)
payload = await run_in_threadpool(
service.list_transactions,
claims=claims,
request_id=request_id,
account_slug=account_slug,
page=page,
page_size=page_size,
window_days=window_days,
status=status,
side=side,
)
return JSONResponse(content=payload, headers={"X-Request-ID": request_id})
@app.get("/v1/snapshot")
async def get_snapshot(
request: Request,
window_days: int = 31,
page_size: int = 50,
) -> JSONResponse:
claims = actor_claims_from_request(request, settings)
request_id = _request_id(request)
payload = await run_in_threadpool(
service.get_snapshot,
claims=claims,
request_id=request_id,
window_days=window_days,
page_size=page_size,
)
return JSONResponse(content=payload, headers={"X-Request-ID": request_id})
return app
def _request_id(request: Request) -> str:
existing = getattr(request.state, "request_id", None)
if existing:
return existing
request.state.request_id = request.headers.get("x-request-id", str(uuid4()))
return request.state.request_id
def _build_service(
*,
settings: Settings,
audit_logger: AuditLogger,
rate_limiter: RateLimiter | None,
concurrency_limiter: ConcurrencyLimiter | None,
) -> CapabilityService:
policy = PolicyEngine.from_file(
settings.policy_file,
required_scope=settings.required_scope,
enforce_scope=settings.enforce_scope,
)
if settings.qonto_fixture_dir is not None:
client = FixtureQontoClient(fixture_dir=settings.qonto_fixture_dir)
else:
credential_provider = build_credential_provider(settings)
client = QontoClient(
base_url=settings.qonto_base_url,
organization_path=settings.qonto_organization_path,
transactions_path=settings.qonto_transactions_path,
auth_mode=settings.qonto_auth_mode,
timeout_seconds=settings.qonto_timeout_seconds,
max_retries=settings.qonto_max_retries,
credential_provider=credential_provider,
)
return CapabilityService(
client=client,
policy=policy,
audit_logger=audit_logger,
rate_limiter=rate_limiter
or RateLimiter(
limit=settings.rate_limit_requests,
window_seconds=settings.rate_limit_window_seconds,
),
concurrency_limiter=concurrency_limiter
or ConcurrencyLimiter(limit=settings.max_concurrency),
)
def main() -> None:
settings = Settings.from_env()
logging.basicConfig(level=logging.INFO, format="%(message)s")
uvicorn.run(
"qonto_assistant.app:create_app",
factory=True,
host=settings.host,
port=settings.port,
reload=False,
)