Compare commits

...

17 Commits

Author SHA1 Message Date
smithery-ai[bot] 63c65f48bf Update README 2025-11-22 18:56:34 +00:00
github-actions[bot] 57db18c6a3 bump: version 0.46.0 → 0.46.1 2025-11-22 18:54:11 +00:00
Chris Coutinho ea79e94842 Merge pull request #343 from cbcoutinho/fix/vector-viz-search
perf: Optimize vector viz search performance
2025-11-22 19:53:40 +01:00
Chris Coutinho b0612cfa0f perf: Optimize vector viz search performance
- Replace sequential Qdrant scroll calls with batch retrieve
  (50 HTTP requests → 1 request, ~50x faster vector fetch)

- Add point_id to SearchResult to enable batch retrieval by Qdrant point ID

- Reuse query embedding from search algorithm in viz_routes
  (eliminates redundant embedding call, saves ~30ms)

- Make BM25 encode() async with thread pool to avoid blocking event loop
  (~4.4s was blocking, now properly async)

- Run PCA computation in thread pool to avoid blocking event loop
  (~1.2s was blocking, now properly async)

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-22 19:47:43 +01:00
github-actions[bot] 4e61d73da5 bump: version 0.45.0 → 0.46.0 2025-11-22 18:40:24 +00:00
Chris Coutinho 3b41776110 Merge pull request #342 from cbcoutinho/feature/smithery
feat: Add Smithery stateless deployment support (ADR-016)
2025-11-22 19:39:53 +01:00
Chris Coutinho 3e3d38696c docs(smithery): Make Smithery the primary Quick Start option
Reorganize README to promote Smithery as the fastest way to get started:
- Quick Start now features Smithery one-click deployment
- Docker instructions moved to separate "Docker (Self-Hosted)" section
- Added note about Smithery's stateless mode limitations

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-22 19:38:11 +01:00
Chris Coutinho 7b22e5be0f build: add smithery image to docker compose 2025-11-22 19:06:25 +01:00
Chris Coutinho 39fba49cfe fix(smithery): Add JSON Schema metadata to mcp-config endpoint
Add proper JSON Schema metadata fields per Smithery documentation:
- $schema: JSON Schema draft-07
- $id: Schema identifier URL
- title: Human-readable title
- description: Schema description
- x-query-style: "flat" (no nested objects in our schema)
- additionalProperties: false

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-22 18:28:05 +01:00
Chris Coutinho 706a15f0bc fix(smithery): Use container runtime pattern for config discovery
ADR-016: For container runtime deployment, Smithery does not auto-generate
the .well-known/mcp-config endpoint like it does for Python CLI runtime.

Changes:
- Remove [tool.smithery] from pyproject.toml (not used in container mode)
- Remove smithery_server.py (Python CLI runtime specific)
- Add .well-known/mcp-config endpoint to return JSON Schema config
- Add SmitheryConfigMiddleware to extract config from URL query params
- Use ContextVar to pass session config to tool handlers

The container runtime passes config as URL query parameters to /mcp:
  GET /mcp?nextcloud_url=...&username=...&app_password=...

Tested:
- All 164 unit tests passing
- Docker container builds successfully
- .well-known/mcp-config returns valid JSON Schema
- Health endpoints working

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-22 18:22:55 +01:00
Chris Coutinho b8dc413b73 feat: Add Smithery CLI deployment support
- Add smithery package as dependency
- Create smithery_server.py with @smithery.server() decorator
- Add SmitheryConfigSchema for session config (nextcloud_url, username, app_password)
- Add [tool.smithery] section to pyproject.toml
- Remove manual .well-known/mcp-config endpoint (Smithery handles this)

Smithery CLI will automatically:
- Extract config schema from the decorated function
- Handle session config parsing from query parameters
- Make config accessible via ctx.session_config in tools

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-22 18:05:33 +01:00
Chris Coutinho 8d29ce0122 fix: Add Smithery lifespan and auth mode detection
- Add SmitheryAppContext dataclass for stateless mode
- Add app_lifespan_smithery() with minimal lifespan (no shared state)
- Update is_oauth_mode() to detect Smithery mode and return BasicAuth
- Use Smithery lifespan when SMITHERY_DEPLOYMENT=true
- Add .well-known/mcp-config endpoint for config discovery
- Skip document processors in Smithery mode (not enabled)

Fixes startup issues in Smithery mode where missing env credentials
would incorrectly trigger OAuth mode.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-22 17:48:53 +01:00
Chris Coutinho a272e7cbab build: Fix Dockerfile.smithery 2025-11-22 17:35:16 +01:00
Chris Coutinho ce55b239e2 build: Fix Dockerfile.smithery 2025-11-22 17:33:12 +01:00
Chris Coutinho 432ab73741 build: Add missing deps 2025-11-22 17:32:20 +01:00
Chris Coutinho f93d650992 feat: Implement ADR-016 Smithery stateless deployment mode
Adds support for Smithery hosted deployment with stateless operation:

- Add DeploymentMode enum with SELF_HOSTED and SMITHERY_STATELESS modes
- Add get_deployment_mode() to detect mode from SMITHERY_DEPLOYMENT env var
- Update get_client() to create per-request clients from session config
- Add conditional tool registration (skip semantic search in Smithery mode)
- Add conditional /app admin UI mounting (skip in Smithery mode)
- Create smithery.yaml with configSchema for user credentials
- Create Dockerfile.smithery for minimal stateless container
- Create smithery_main.py entrypoint for Smithery deployment

In Smithery mode:
- Users provide nextcloud_url, username, app_password via session config
- Each request creates a fresh NextcloudClient (no state between requests)
- Semantic search tools are disabled (no vector database)
- Admin UI (/app) is disabled (no webhooks, vector viz)

All existing self-hosted functionality remains unchanged.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-22 17:30:42 +01:00
Chris Coutinho 482ef89a73 docs: Add ADR-016 for Smithery stateless deployment
Add architecture decision record for supporting Smithery-hosted MCP
server in a stateless mode for multi-user public Nextcloud instances.

Key decisions:
- New SMITHERY_STATELESS deployment mode alongside SELF_HOSTED
- Session-based configuration (nextcloud_url, username, app_password)
- Feature subset excluding semantic search and background sync
- Admin UI (/app) excluded in Smithery mode
- Per-request client creation from session config

This enables users to try the MCP server without self-hosting
infrastructure while supporting multiple Nextcloud instances.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-22 17:13:18 +01:00
18 changed files with 1191 additions and 152 deletions
+19
View File
@@ -1,3 +1,22 @@
## v0.46.1 (2025-11-22)
### Perf
- Optimize vector viz search performance
## v0.46.0 (2025-11-22)
### Feat
- Add Smithery CLI deployment support
- Implement ADR-016 Smithery stateless deployment mode
### Fix
- **smithery**: Add JSON Schema metadata to mcp-config endpoint
- **smithery**: Use container runtime pattern for config discovery
- Add Smithery lifespan and auth mode detection
## v0.45.0 (2025-11-22)
### Feat
+44
View File
@@ -0,0 +1,44 @@
# Dockerfile for Smithery stateless deployment
# ADR-016: Stateless mode for multi-user public Nextcloud instances
#
# This image excludes:
# - Vector database dependencies (qdrant-client)
# - Background sync workers
# - Admin UI routes (/app)
# - Semantic search tools
#
# Features included:
# - Core Nextcloud tools (notes, calendar, contacts, files, deck, tables, cookbook)
# - Per-session app password authentication
# - Multi-user support via Smithery session config
FROM docker.io/library/python:3.12-slim-trixie@sha256:2e683fc3e18a248aa23b8022f2a3474b072b04fb851efe9b49f6b516a8944939
WORKDIR /app
# Install uv for fast dependency management
COPY --from=ghcr.io/astral-sh/uv:0.9.10@sha256:29bd45092ea8902c0bbb7f0a338f0494a382b1f4b18355df5be270ade679ff1d /uv /uvx /bin/
# Install dependencies
# 1. git (required for caldav dependency from git)
# 2. sqlite for development with token db
RUN apt update && apt install --no-install-recommends --no-install-suggests -y \
git
# Copy project files
COPY . .
RUN uv sync --locked --no-dev --no-editable --no-cache
# Set Smithery mode environment variables
ENV SMITHERY_DEPLOYMENT=true
ENV VECTOR_SYNC_ENABLED=false
# Smithery sets PORT=8081 by default
EXPOSE 8081
# Health check endpoint
HEALTHCHECK --interval=30s --timeout=10s --start-period=5s --retries=3 \
CMD uv run python -c "import httpx; httpx.get('http://localhost:${PORT:-8081}/health/live').raise_for_status()"
CMD ["/app/.venv/bin/smithery-main"]
+18 -3
View File
@@ -1,9 +1,11 @@
```markdown
<p align="center">
<img src="astrolabe.svg" alt="Nextcloud MCP Server" width="128" height="128">
</p>
# Nextcloud MCP Server
[![smithery badge](https://smithery.ai/badge/@cbcoutinho/nextcloud-mcp-server)](https://smithery.ai/server/@cbcoutinho/nextcloud-mcp-server)
[![Docker Image](https://img.shields.io/badge/docker-ghcr.io/cbcoutinho/nextcloud--mcp--server-blue)](https://github.com/cbcoutinho/nextcloud-mcp-server/pkgs/container/nextcloud-mcp-server)
**A production-ready MCP server that connects AI assistants to your Nextcloud instance.**
@@ -17,7 +19,20 @@ This is a **dedicated standalone MCP server** designed for external MCP clients
## Quick Start
Get up and running in 60 seconds using Docker:
The fastest way to get started is via [Smithery](https://smithery.ai/server/@cbcoutinho/nextcloud-mcp-server) - no Docker or self-hosting required:
1. Visit the [Smithery marketplace page](https://smithery.ai/server/@cbcoutinho/nextcloud-mcp-server)
2. Click "Deploy" and configure:
- **Nextcloud URL**: Your Nextcloud instance (e.g., `https://cloud.example.com`)
- **Username**: Your Nextcloud username
- **App Password**: Generate one in Nextcloud → Settings → Security → Devices & sessions
> [!NOTE]
> Smithery runs in stateless mode without semantic search. For full features, use [Docker](#docker-self-hosted) or see [ADR-016](docs/ADR-016-smithery-stateless-deployment.md).
## Docker (Self-Hosted)
For full features including semantic search, run with Docker:
```bash
# 1. Create a minimal configuration
@@ -37,12 +52,11 @@ curl http://127.0.0.1:8000/health/ready
# 4. Connect to the endpoint
http://127.0.0.1:8000/sse
# 4. Or with --transport streamable-http
# Or with --transport streamable-http
http://127.0.0.1:8000/mcp
```
**Next Steps:**
- Create an app password in Nextcloud: Settings → Security → Devices & sessions
- Connect your MCP client (Claude Desktop, IDEs, `mcp dev`, etc.)
- See [docs/installation.md](docs/installation.md) for other deployment options (local, Kubernetes)
@@ -210,3 +224,4 @@ This project is licensed under the AGPL-3.0 License. See [LICENSE](./LICENSE) fo
- [Model Context Protocol](https://github.com/modelcontextprotocol)
- [MCP Python SDK](https://github.com/modelcontextprotocol/python-sdk)
- [Nextcloud](https://nextcloud.com/)
```
+2 -2
View File
@@ -2,8 +2,8 @@ apiVersion: v2
name: nextcloud-mcp-server
description: A Helm chart for Nextcloud MCP Server - enables AI assistants to interact with Nextcloud
type: application
version: 0.45.0
appVersion: "0.45.0"
version: 0.46.1
appVersion: "0.46.1"
keywords:
- nextcloud
- mcp
+20
View File
@@ -224,6 +224,26 @@ services:
- keycloak-tokens:/app/data
- keycloak-oauth-storage:/app/.oauth
# Smithery stateless deployment mode (ADR-016)
# Test with: docker compose --profile smithery up smithery
# Then: curl http://localhost:8081/.well-known/mcp-config
smithery:
build:
context: .
dockerfile: Dockerfile.smithery
restart: always
depends_on:
app:
condition: service_healthy
ports:
- 127.0.0.1:8081:8081
environment:
- SMITHERY_DEPLOYMENT=true
- VECTOR_SYNC_ENABLED=false
- PORT=8081
profiles:
- smithery
qdrant:
image: qdrant/qdrant:v1.16.0@sha256:1005201498cf927d835383d0f918b17d8c9da7db58550f169f694455e42d78f4
restart: always
@@ -0,0 +1,492 @@
# ADR-016: Smithery Stateless Deployment for Multi-User Public Nextcloud Instances
**Status:** Proposed
**Date:** 2025-01-22
**Deciders:** Development Team
**Related:** ADR-004 (OAuth), ADR-007 (Background Vector Sync), ADR-015 (Unified Provider)
## Context
[Smithery](https://smithery.ai) is a hosting platform and marketplace for MCP servers that provides:
- **Discovery**: Marketplace listing for MCP servers
- **Hosting**: Containerized deployment with auto-scaling
- **Authentication UI**: OAuth flow presentation for users
- **Session Configuration**: Per-user settings passed via URL parameters
- **Observability**: Usage logs and monitoring
### Current Architecture Limitations
The current nextcloud-mcp-server architecture assumes a **self-hosted deployment** with:
1. **Persistent Infrastructure**
- Qdrant vector database for semantic search
- Background sync worker for content indexing
- Refresh token storage for offline access
2. **Single-Tenant Configuration**
- Environment variables configure one Nextcloud instance
- `NEXTCLOUD_HOST`, `NEXTCLOUD_USERNAME`, `NEXTCLOUD_PASSWORD`
- Or OAuth with a single IdP
3. **Stateful Operations**
- Vector sync maintains index state across requests
- Token storage persists between sessions
### Smithery Hosting Constraints
Smithery-hosted containers are **stateless by design**:
- No persistent storage between requests
- No background workers or cron jobs
- No databases (Qdrant, Redis, etc.)
- Containers may be recycled at any time
- Configuration passed per-session via URL parameters
### Opportunity
Many users have **publicly accessible Nextcloud instances** and want to:
1. Try the MCP server without self-hosting infrastructure
2. Connect multiple users to different Nextcloud instances
3. Use basic Nextcloud tools without semantic search
4. Benefit from Smithery's discovery and OAuth UI
## Decision
Implement a **stateless deployment mode** for Smithery that:
1. **Disables stateful features** (vector sync, semantic search)
2. **Creates clients per-session** from Smithery configuration
3. **Supports multiple Nextcloud instances** via session config
4. **Provides a useful subset of tools** that work without infrastructure
### Architecture
```
┌─────────────────────────────────────────────────────────────────────────┐
│ Smithery-Hosted Stateless Mode │
├─────────────────────────────────────────────────────────────────────────┤
│ │
│ MCP Client Smithery │
│ (Cursor, Claude) Infrastructure │
│ │ │ │
│ │ 1. Connect │ │
│ ├───────────────────────────►│ │
│ │ │ │
│ │ 2. Config UI │ │
│ │◄───────────────────────────┤ User enters: │
│ │ (Smithery presents) │ - nextcloud_url │
│ │ │ - auth_mode (basic/oauth) │
│ │ │ - credentials │
│ │ 3. Tool call │ │
│ ├───────────────────────────►│ │
│ │ + session config │ │
│ │ │ │
│ │ ┌───────┴───────┐ │
│ │ │ MCP Server │ │
│ │ │ Container │ │
│ │ │ │ │
│ │ │ 4. Create │ │
│ │ │ client │ │
│ │ │ from │ │
│ │ │ config │ │
│ │ │ │ │ │
│ │ │ ▼ │ │
│ │ │ 5. Call │ │
│ │ │ Nextcloud │───────► User's Nextcloud │
│ │ │ API │ Instance │
│ │ │ │ │ │
│ │ │ ▼ │ │
│ │ 6. Response │ Return result │ │
│ │◄───────────────────┤ │ │
│ │ └───────────────┘ │
│ │
└─────────────────────────────────────────────────────────────────────────┘
```
### Session Configuration Schema
```python
from pydantic import BaseModel, Field
class SmitheryConfigSchema(BaseModel):
"""Configuration schema for Smithery session."""
# Required: Nextcloud instance
nextcloud_url: str = Field(
...,
description="Your Nextcloud instance URL (e.g., https://cloud.example.com)"
)
# Authentication mode
auth_mode: str = Field(
"app_password",
description="Authentication method: 'app_password' or 'oauth'"
)
# App Password authentication (recommended for Smithery)
username: str | None = Field(
None,
description="Nextcloud username (required for app_password auth)"
)
app_password: str | None = Field(
None,
description="Nextcloud app password (Settings → Security → App passwords)"
)
# OAuth authentication (advanced)
# When auth_mode='oauth', Smithery handles the OAuth flow
# and passes the access token automatically
```
### Feature Matrix
| Feature | Self-Hosted | Smithery Stateless |
|---------|-------------|-------------------|
| **Notes** | | |
| List/Search notes | ✓ | ✓ |
| Get/Create/Update notes | ✓ | ✓ |
| Semantic search | ✓ | ✗ |
| **Calendar** | | |
| List calendars | ✓ | ✓ |
| Get/Create events | ✓ | ✓ |
| **Contacts** | | |
| List address books | ✓ | ✓ |
| Search/Get contacts | ✓ | ✓ |
| **Files (WebDAV)** | | |
| List/Download files | ✓ | ✓ |
| Upload files | ✓ | ✓ |
| Search files | ✓ | ✓ (keyword only) |
| **Deck** | | |
| List boards/cards | ✓ | ✓ |
| Create/Update cards | ✓ | ✓ |
| **Tables** | | |
| List/Query tables | ✓ | ✓ |
| Create/Update rows | ✓ | ✓ |
| **Cookbook** | | |
| List/Get recipes | ✓ | ✓ |
| **Semantic Search** | | |
| Vector search | ✓ | ✗ |
| RAG answers | ✓ | ✗ |
| **Background Sync** | | |
| Auto-indexing | ✓ | ✗ |
| Webhook sync | ✓ | ✗ |
| **Admin UI (`/app`)** | | |
| Vector sync status | ✓ | ✗ |
| Vector visualization | ✓ | ✗ |
| Webhook management | ✓ | ✗ |
| Session management | ✓ | ✗ |
### Implementation
#### 1. Deployment Mode Detection
```python
# nextcloud_mcp_server/config.py
class DeploymentMode(Enum):
SELF_HOSTED = "self_hosted" # Full features, env-based config
SMITHERY_STATELESS = "smithery" # Stateless, session-based config
def get_deployment_mode() -> DeploymentMode:
"""Detect deployment mode from environment."""
if os.getenv("SMITHERY_DEPLOYMENT") == "true":
return DeploymentMode.SMITHERY_STATELESS
return DeploymentMode.SELF_HOSTED
```
#### 2. Session-Based Client Factory
```python
# nextcloud_mcp_server/context.py
async def get_client(ctx: Context) -> NextcloudClient:
"""Get NextcloudClient - from session config or environment."""
mode = get_deployment_mode()
if mode == DeploymentMode.SMITHERY_STATELESS:
# Create client from Smithery session config
config = ctx.session_config
if not config:
raise McpError("Session configuration required")
return NextcloudClient(
base_url=config.nextcloud_url,
username=config.username,
password=config.app_password,
)
else:
# Existing behavior: from environment or OAuth context
return await _get_client_from_context(ctx)
```
#### 3. Conditional Tool Registration
```python
# nextcloud_mcp_server/app.py
def create_mcp_server(mode: DeploymentMode) -> FastMCP:
"""Create MCP server with mode-appropriate tools."""
mcp = FastMCP("Nextcloud MCP")
# Always register core tools
configure_notes_tools(mcp)
configure_calendar_tools(mcp)
configure_contacts_tools(mcp)
configure_webdav_tools(mcp)
configure_deck_tools(mcp)
configure_tables_tools(mcp)
configure_cookbook_tools(mcp)
# Only register stateful tools in self-hosted mode
if mode == DeploymentMode.SELF_HOSTED:
configure_semantic_tools(mcp) # Requires Qdrant
register_oauth_tools(mcp) # Requires token storage
return mcp
```
#### 4. Exclude Admin UI Routes
The `/app` admin UI should **not be installed** in Smithery mode because:
- **Vector sync status** - No vector sync in stateless mode
- **Vector visualization** - No Qdrant to visualize
- **Webhook management** - No webhook sync without background workers
- **Session management** - No persistent sessions to manage
```python
# nextcloud_mcp_server/app.py
def create_app(mode: DeploymentMode) -> Starlette:
"""Create Starlette app with mode-appropriate routes."""
routes = [
Route("/health/live", health_live, methods=["GET"]),
Route("/health/ready", health_ready, methods=["GET"]),
]
# Only mount admin UI in self-hosted mode
if mode == DeploymentMode.SELF_HOSTED:
browser_app = create_browser_app()
routes.append(
Route("/app", lambda r: RedirectResponse("/app/", status_code=307))
)
routes.append(Mount("/app", app=browser_app))
logger.info("Admin UI mounted at /app")
else:
logger.info("Admin UI disabled in Smithery stateless mode")
# Mount FastMCP at root
mcp_app = create_mcp_server(mode).streamable_http_app()
routes.append(Mount("/", app=mcp_app))
return Starlette(routes=routes, lifespan=starlette_lifespan)
```
**Endpoints by Mode:**
| Endpoint | Self-Hosted | Smithery |
|----------|-------------|----------|
| `/mcp` | ✓ | ✓ |
| `/health/live` | ✓ | ✓ |
| `/health/ready` | ✓ | ✓ |
| `/.well-known/mcp-config` | ✓ | ✓ |
| `/app` | ✓ | ✗ |
| `/app/vector-sync/status` | ✓ | ✗ |
| `/app/vector-viz` | ✓ | ✗ |
| `/app/webhooks` | ✓ | ✗ |
#### 5. Smithery Integration Files
**smithery.yaml:**
```yaml
runtime: "container"
build:
dockerfile: "Dockerfile.smithery"
dockerBuildPath: "."
startCommand:
type: "http"
configSchema:
type: "object"
required: ["nextcloud_url", "username", "app_password"]
properties:
nextcloud_url:
type: "string"
title: "Nextcloud URL"
description: "Your Nextcloud instance URL (e.g., https://cloud.example.com)"
username:
type: "string"
title: "Username"
description: "Your Nextcloud username"
app_password:
type: "string"
title: "App Password"
description: "Generate at Settings → Security → App passwords"
exampleConfig:
nextcloud_url: "https://cloud.example.com"
username: "alice"
app_password: "xxxxx-xxxxx-xxxxx-xxxxx-xxxxx"
```
**Dockerfile.smithery:**
```dockerfile
FROM python:3.11-slim
WORKDIR /app
# Install uv
COPY --from=ghcr.io/astral-sh/uv:latest /uv /bin/uv
# Copy project files
COPY pyproject.toml uv.lock ./
COPY nextcloud_mcp_server ./nextcloud_mcp_server
# Install dependencies (without vector/semantic extras)
RUN uv sync --frozen --no-dev
# Set Smithery mode
ENV SMITHERY_DEPLOYMENT=true
ENV VECTOR_SYNC_ENABLED=false
# Smithery sets PORT=8081
EXPOSE 8081
CMD ["uv", "run", "python", "-m", "nextcloud_mcp_server.smithery_main"]
```
**nextcloud_mcp_server/smithery_main.py:**
```python
"""Smithery-specific entrypoint for stateless deployment."""
import os
import uvicorn
from starlette.middleware.cors import CORSMiddleware
from nextcloud_mcp_server.app import create_mcp_server
from nextcloud_mcp_server.config import DeploymentMode
def main():
# Force stateless mode
os.environ["SMITHERY_DEPLOYMENT"] = "true"
os.environ["VECTOR_SYNC_ENABLED"] = "false"
mcp = create_mcp_server(DeploymentMode.SMITHERY_STATELESS)
app = mcp.streamable_http_app()
# Add CORS for browser-based clients
app.add_middleware(
CORSMiddleware,
allow_origins=["*"],
allow_credentials=True,
allow_methods=["GET", "POST", "OPTIONS"],
allow_headers=["*"],
expose_headers=["mcp-session-id", "mcp-protocol-version"],
)
# Smithery sets PORT environment variable
port = int(os.environ.get("PORT", 8081))
uvicorn.run(app, host="0.0.0.0", port=port)
if __name__ == "__main__":
main()
```
### Security Considerations
1. **App Passwords over User Passwords**
- Smithery config encourages app passwords (revocable, scoped)
- Documentation guides users to create dedicated app passwords
- App passwords can be revoked without changing main password
2. **HTTPS Required**
- `nextcloud_url` must be HTTPS for production use
- Validation rejects HTTP URLs in Smithery mode
3. **No Credential Storage**
- Credentials exist only for request duration
- No server-side persistence of user credentials
- Smithery handles secure config transmission
4. **Scope Limitation**
- Stateless mode cannot access offline_access
- No background operations on user's behalf
- Clear user expectation: tools work during session only
### Migration Path
Users can start with Smithery stateless mode and migrate to self-hosted:
1. **Try on Smithery** → Basic tools, no setup
2. **Self-host for semantic search** → Add Qdrant, enable vector sync
3. **Full deployment** → Background sync, webhooks, multi-user OAuth
## Consequences
### Positive
1. **Lower barrier to entry** - Users can try without infrastructure
2. **Multi-user support** - Each session connects to different Nextcloud
3. **Smithery ecosystem** - Discovery, observability, OAuth UI
4. **Clear feature tiers** - Stateless (simple) vs self-hosted (full)
### Negative
1. **No semantic search** - Key differentiator unavailable on Smithery
2. **Per-request auth** - Credentials sent with each request
3. **No offline access** - Cannot perform background operations
4. **Maintenance burden** - Two deployment modes to support
### Neutral
1. **Feature subset** - May encourage users to self-host for full features
2. **Documentation needs** - Clear guidance on mode differences required
## Alternatives Considered
### 1. External MCP Only
**Approach:** Only support self-hosted external MCP registration on Smithery.
**Rejected because:**
- Higher barrier to entry for new users
- Misses opportunity for Smithery marketplace visibility
- Users want to try before committing to infrastructure
### 2. Embedded Vector DB (SQLite-vec)
**Approach:** Use SQLite with vector extensions for per-request indexing.
**Rejected because:**
- No persistence between requests anyway
- Indexing latency too high for synchronous requests
- Complexity without benefit in stateless context
### 3. External Vector DB Service
**Approach:** Connect to Pinecone/Weaviate Cloud from Smithery container.
**Rejected because:**
- Adds external dependency and cost
- Per-user collections require complex multi-tenancy
- Sync still impossible without background workers
### 4. Hybrid: Smithery + User's Qdrant
**Approach:** User provides their own Qdrant URL in session config.
**Considered for future:**
- Could enable semantic search for advanced users
- Adds complexity to session config
- Sync still requires external trigger (manual or webhook)
## References
- [Smithery Documentation](https://smithery.ai/docs)
- [Smithery Session Configuration](https://smithery.ai/docs/build/session-config)
- [Smithery External MCPs](https://smithery.ai/docs/build/external)
- [MCP Streamable HTTP Transport](https://modelcontextprotocol.io/docs/concepts/transports)
- [Nextcloud App Passwords](https://docs.nextcloud.com/server/latest/user_manual/en/session_management.html#app-passwords)
+276 -78
View File
@@ -3,6 +3,7 @@ import os
import time
from collections.abc import AsyncIterator
from contextlib import AsyncExitStack, asynccontextmanager
from contextvars import ContextVar
from dataclasses import dataclass
from typing import TYPE_CHECKING, Optional
@@ -25,6 +26,8 @@ from starlette.middleware.cors import CORSMiddleware
from starlette.responses import JSONResponse, RedirectResponse
from starlette.routing import Mount, Route
from starlette.staticfiles import StaticFiles
from starlette.types import ASGIApp, Receive, Send
from starlette.types import Scope as StarletteScope
from nextcloud_mcp_server.auth import (
InsufficientScopeError,
@@ -36,6 +39,8 @@ from nextcloud_mcp_server.auth import (
from nextcloud_mcp_server.auth.unified_verifier import UnifiedTokenVerifier
from nextcloud_mcp_server.client import NextcloudClient
from nextcloud_mcp_server.config import (
DeploymentMode,
get_deployment_mode,
get_document_processor_config,
get_settings,
)
@@ -264,17 +269,160 @@ class OAuthAppContext:
)
@dataclass
class SmitheryAppContext:
"""Application context for Smithery stateless mode.
ADR-016: No shared client - clients created per-request from session config.
"""
pass # No shared state needed - everything comes from session config
# ADR-016: Smithery config schema for container runtime
# This schema is served at /.well-known/mcp-config for Smithery discovery
# See: https://smithery.ai/docs/build/session-config
SMITHERY_CONFIG_SCHEMA = {
"$schema": "http://json-schema.org/draft-07/schema#",
"$id": "https://server.smithery.ai/nextcloud-mcp-server/.well-known/mcp-config",
"title": "Nextcloud MCP Server Configuration",
"description": "Configuration for connecting to your Nextcloud instance via app password authentication",
"x-query-style": "flat", # Our schema has no nested objects, so flat style works
"type": "object",
"required": ["nextcloud_url", "username", "app_password"],
"properties": {
"nextcloud_url": {
"type": "string",
"title": "Nextcloud URL",
"description": "Your Nextcloud instance URL (e.g., https://cloud.example.com). Must be publicly accessible.",
"pattern": "^https?://.+",
},
"username": {
"type": "string",
"title": "Username",
"description": "Your Nextcloud username",
"minLength": 1,
},
"app_password": {
"type": "string",
"title": "App Password",
"description": "Nextcloud app password. Generate at Settings > Security > App passwords. Do NOT use your main password.",
"minLength": 1,
},
},
"additionalProperties": False,
}
# ADR-016: Context variable to hold Smithery session config per-request
# This is set by SmitheryConfigMiddleware and accessed in context.py
_smithery_session_config: ContextVar[dict[str, str] | None] = ContextVar(
"smithery_session_config"
)
_smithery_session_config.set(None) # Set initial value
def get_smithery_session_config() -> dict | None:
"""Get the current Smithery session config from context variable.
Used by context.py to access config extracted from URL query parameters.
"""
return _smithery_session_config.get()
class SmitheryConfigMiddleware:
"""Middleware to extract Smithery config from URL query parameters.
ADR-016: For container runtime, Smithery passes configuration as URL query
parameters to the /mcp endpoint. This middleware extracts those parameters
and stores them in a context variable for access in tools.
Configuration parameters:
- nextcloud_url: Nextcloud instance URL
- username: Nextcloud username
- app_password: Nextcloud app password
The extracted config is stored in a ContextVar and can be accessed via
get_smithery_session_config() in context.py.
"""
def __init__(self, app: ASGIApp):
self.app = app
async def __call__(
self, scope: StarletteScope, receive: Receive, send: Send
) -> None:
if scope["type"] == "http":
# Extract config from query parameters
from urllib.parse import parse_qs
query_string = scope.get("query_string", b"").decode("utf-8")
params = parse_qs(query_string)
# Build session config from query parameters
# Smithery uses dot notation for nested objects, but our schema is flat
session_config = {}
for key in ["nextcloud_url", "username", "app_password"]:
if key in params:
# parse_qs returns lists, take first value
session_config[key] = params[key][0]
# Store in context variable for access by context.py
if session_config:
_smithery_session_config.set(session_config)
logger.debug(
f"Smithery config extracted: nextcloud_url={session_config.get('nextcloud_url')}, "
f"username={session_config.get('username')}"
)
try:
await self.app(scope, receive, send)
finally:
# Clear context variable after request
_smithery_session_config.set(None)
@asynccontextmanager
async def app_lifespan_smithery(server: FastMCP) -> AsyncIterator[SmitheryAppContext]:
"""
Manage application lifecycle for Smithery stateless mode.
ADR-016: Minimal lifespan with no shared state.
- No shared Nextcloud client (created per-request from session config)
- No vector sync (disabled in Smithery mode)
- No persistent storage (stateless deployment)
- No document processors (not enabled in Smithery mode)
"""
logger.info("Starting MCP server in Smithery stateless mode")
logger.info("Clients will be created per-request from session config")
try:
yield SmitheryAppContext()
finally:
logger.info("Shutting down Smithery stateless mode")
def is_oauth_mode() -> bool:
"""
Determine if OAuth mode should be used.
OAuth mode is enabled when:
- NEXTCLOUD_USERNAME and NEXTCLOUD_PASSWORD are NOT set
- AND we are NOT in Smithery stateless mode
- Or explicitly enabled via configuration
Returns:
True if OAuth mode, False if BasicAuth mode
"""
# ADR-016: Smithery stateless mode uses per-request BasicAuth from session config
# It's not OAuth mode even though env credentials aren't set
deployment_mode = get_deployment_mode()
if deployment_mode == DeploymentMode.SMITHERY_STATELESS:
logger.info(
"BasicAuth mode (Smithery stateless - credentials from session config)"
)
return False
username = os.getenv("NEXTCLOUD_USERNAME")
password = os.getenv("NEXTCLOUD_PASSWORD")
@@ -858,8 +1006,9 @@ def get_app(transport: str = "sse", enabled_apps: list[str] | None = None):
"OpenTelemetry tracing disabled (set OTEL_EXPORTER_OTLP_ENDPOINT to enable)"
)
# Determine authentication mode
# Determine authentication mode and deployment mode
oauth_enabled = is_oauth_mode()
deployment_mode = get_deployment_mode()
if oauth_enabled:
logger.info("Configuring MCP server for OAuth mode")
@@ -920,8 +1069,13 @@ def get_app(transport: str = "sse", enabled_apps: list[str] | None = None):
auth=auth_settings,
)
else:
logger.info("Configuring MCP server for BasicAuth mode")
mcp = FastMCP("Nextcloud MCP", lifespan=app_lifespan_basic)
# ADR-016: Use Smithery lifespan for stateless mode, BasicAuth otherwise
if deployment_mode == DeploymentMode.SMITHERY_STATELESS:
logger.info("Configuring MCP server for Smithery stateless mode")
mcp = FastMCP("Nextcloud MCP", lifespan=app_lifespan_smithery)
else:
logger.info("Configuring MCP server for BasicAuth mode")
mcp = FastMCP("Nextcloud MCP", lifespan=app_lifespan_basic)
@mcp.resource("nc://capabilities")
async def nc_get_capabilities():
@@ -957,8 +1111,12 @@ def get_app(transport: str = "sse", enabled_apps: list[str] | None = None):
)
# Register semantic search tools (cross-app feature)
# ADR-016: Skip in Smithery stateless mode (no vector database)
settings = get_settings()
if settings.vector_sync_enabled:
deployment_mode = get_deployment_mode()
if deployment_mode == DeploymentMode.SMITHERY_STATELESS:
logger.info("Skipping semantic search tools (Smithery stateless mode)")
elif settings.vector_sync_enabled:
logger.info("Configuring semantic search tools (vector sync enabled)")
configure_semantic_tools(mcp)
else:
@@ -1361,6 +1519,26 @@ def get_app(transport: str = "sse", enabled_apps: list[str] | None = None):
)
logger.info("Test webhook endpoint enabled: /webhooks/nextcloud")
# ADR-016: Add Smithery well-known config endpoint for container runtime discovery
if deployment_mode == DeploymentMode.SMITHERY_STATELESS:
def smithery_mcp_config(request):
"""Smithery MCP configuration endpoint.
Returns JSON Schema for Smithery's configuration UI.
This endpoint is required for Smithery container runtime discovery.
"""
return JSONResponse(SMITHERY_CONFIG_SCHEMA)
routes.append(
Route(
"/.well-known/mcp-config",
smithery_mcp_config,
methods=["GET"],
)
)
logger.info("Smithery config endpoint enabled: /.well-known/mcp-config")
# Note: Metrics endpoint is NOT exposed on main HTTP port for security reasons.
# Metrics are served on dedicated port via setup_metrics() (default: 9090)
@@ -1491,85 +1669,98 @@ def get_app(transport: str = "sse", enabled_apps: list[str] | None = None):
)
# Add user info routes (available in both BasicAuth and OAuth modes)
# These require session authentication, so we wrap them in a separate app
from nextcloud_mcp_server.auth.session_backend import SessionAuthBackend
from nextcloud_mcp_server.auth.userinfo_routes import (
revoke_session,
user_info_html,
vector_sync_status_fragment,
)
from nextcloud_mcp_server.auth.viz_routes import (
chunk_context_endpoint,
vector_visualization_html,
vector_visualization_search,
)
from nextcloud_mcp_server.auth.webhook_routes import (
disable_webhook_preset,
enable_webhook_preset,
webhook_management_pane,
)
# Create a separate Starlette app for browser routes that need session auth
# This prevents SessionAuthBackend from interfering with FastMCP's OAuth
browser_routes = [
Route("/", user_info_html, methods=["GET"]), # /app → user info with all tabs
Route(
"/revoke", revoke_session, methods=["POST"], name="revoke_session_endpoint"
), # /app/revoke → revoke_session
# Vector sync status fragment (htmx polling)
Route(
"/vector-sync/status",
# ADR-016: Skip /app admin UI in Smithery stateless mode (no vector sync, webhooks)
if deployment_mode != DeploymentMode.SMITHERY_STATELESS:
# These require session authentication, so we wrap them in a separate app
from nextcloud_mcp_server.auth.session_backend import SessionAuthBackend
from nextcloud_mcp_server.auth.userinfo_routes import (
revoke_session,
user_info_html,
vector_sync_status_fragment,
methods=["GET"],
), # /app/vector-sync/status
# Vector visualization routes
Route(
"/vector-viz", vector_visualization_html, methods=["GET"]
), # /app/vector-viz
Route(
"/vector-viz/search",
vector_visualization_search,
methods=["GET"],
), # /app/vector-viz/search
Route(
"/chunk-context",
chunk_context_endpoint,
methods=["GET"],
), # /app/chunk-context
# Webhook management routes (admin-only)
Route("/webhooks", webhook_management_pane, methods=["GET"]), # /app/webhooks
Route(
"/webhooks/enable/{preset_id:str}", enable_webhook_preset, methods=["POST"]
),
Route(
"/webhooks/disable/{preset_id:str}",
disable_webhook_preset,
methods=["DELETE"],
),
]
# Add static files mount if directory exists
static_dir = os.path.join(os.path.dirname(__file__), "auth", "static")
if os.path.isdir(static_dir):
browser_routes.append(
Mount("/static", StaticFiles(directory=static_dir), name="static")
)
logger.info(f"Mounted static files from {static_dir}")
from nextcloud_mcp_server.auth.viz_routes import (
chunk_context_endpoint,
vector_visualization_html,
vector_visualization_search,
)
from nextcloud_mcp_server.auth.webhook_routes import (
disable_webhook_preset,
enable_webhook_preset,
webhook_management_pane,
)
browser_app = Starlette(routes=browser_routes)
browser_app.add_middleware(
AuthenticationMiddleware, # type: ignore[invalid-argument-type]
backend=SessionAuthBackend(oauth_enabled=oauth_enabled),
)
# Create a separate Starlette app for browser routes that need session auth
# This prevents SessionAuthBackend from interfering with FastMCP's OAuth
browser_routes = [
Route(
"/", user_info_html, methods=["GET"]
), # /app → user info with all tabs
Route(
"/revoke",
revoke_session,
methods=["POST"],
name="revoke_session_endpoint",
), # /app/revoke → revoke_session
# Vector sync status fragment (htmx polling)
Route(
"/vector-sync/status",
vector_sync_status_fragment,
methods=["GET"],
), # /app/vector-sync/status
# Vector visualization routes
Route(
"/vector-viz", vector_visualization_html, methods=["GET"]
), # /app/vector-viz
Route(
"/vector-viz/search",
vector_visualization_search,
methods=["GET"],
), # /app/vector-viz/search
Route(
"/chunk-context",
chunk_context_endpoint,
methods=["GET"],
), # /app/chunk-context
# Webhook management routes (admin-only)
Route(
"/webhooks", webhook_management_pane, methods=["GET"]
), # /app/webhooks
Route(
"/webhooks/enable/{preset_id:str}",
enable_webhook_preset,
methods=["POST"],
),
Route(
"/webhooks/disable/{preset_id:str}",
disable_webhook_preset,
methods=["DELETE"],
),
]
# Add redirect from /app to /app/ (Starlette requires trailing slash for mounted apps)
routes.append(
Route("/app", lambda request: RedirectResponse("/app/", status_code=307))
)
# Add static files mount if directory exists
static_dir = os.path.join(os.path.dirname(__file__), "auth", "static")
if os.path.isdir(static_dir):
browser_routes.append(
Mount("/static", StaticFiles(directory=static_dir), name="static")
)
logger.info(f"Mounted static files from {static_dir}")
# Mount browser app at /app (webapp and admin routes)
routes.append(Mount("/app", app=browser_app))
logger.info("App routes with session auth: /app, /app/webhooks, /app/revoke")
browser_app = Starlette(routes=browser_routes)
browser_app.add_middleware(
AuthenticationMiddleware, # type: ignore[invalid-argument-type]
backend=SessionAuthBackend(oauth_enabled=oauth_enabled),
)
# Add redirect from /app to /app/ (Starlette requires trailing slash for mounted apps)
routes.append(
Route("/app", lambda request: RedirectResponse("/app/", status_code=307))
)
# Mount browser app at /app (webapp and admin routes)
routes.append(Mount("/app", app=browser_app))
logger.info("App routes with session auth: /app, /app/webhooks, /app/revoke")
else:
logger.info("Admin UI (/app) disabled in Smithery stateless mode")
# Mount FastMCP at root last (catch-all, handles OAuth via token_verifier)
routes.append(Mount("/", app=mcp_app))
@@ -1689,4 +1880,11 @@ def get_app(transport: str = "sse", enabled_apps: list[str] | None = None):
logger.info("WWW-Authenticate scope challenge handler enabled")
# ADR-016: Apply SmitheryConfigMiddleware in Smithery stateless mode
# This must be the outermost middleware to extract config from URL query parameters
# before any other middleware processes the request
if deployment_mode == DeploymentMode.SMITHERY_STATELESS:
app = SmitheryConfigMiddleware(app)
logger.info("SmitheryConfigMiddleware enabled for query parameter config")
return app
+44 -57
View File
@@ -218,71 +218,41 @@ async def vector_visualization_search(request: Request) -> JSONResponse:
}
)
# Fetch vectors for specific matching chunks from Qdrant
# Fetch vectors for specific matching chunks from Qdrant using batch retrieve
vector_fetch_start = time.perf_counter()
qdrant_client = await get_qdrant_client()
# Build filters for each specific chunk
from qdrant_client.models import FieldCondition, Filter, MatchValue
chunk_vectors_map = {} # Map (doc_id, chunk_start, chunk_end) -> vector
# Fetch vectors in batches by filtering on chunk-specific fields
for result in search_results:
chunk_start = result.chunk_start_offset
chunk_end = result.chunk_end_offset
# Collect point IDs from search results for batch retrieval
# point_id is the Qdrant internal ID returned by search algorithms
point_ids = [r.point_id for r in search_results if r.point_id]
# Build filter for this specific chunk
must_conditions = [
get_placeholder_filter(), # Always exclude placeholders from user-facing queries
FieldCondition(
key="doc_id",
match=MatchValue(value=result.id),
),
FieldCondition(
key="user_id",
match=MatchValue(value=username),
),
]
# Add chunk position filters if available
if chunk_start is not None:
must_conditions.append(
FieldCondition(
key="chunk_start_offset",
match=MatchValue(value=chunk_start),
)
)
if chunk_end is not None:
must_conditions.append(
FieldCondition(
key="chunk_end_offset",
match=MatchValue(value=chunk_end),
)
)
# Fetch this specific chunk vector
points_response = await qdrant_client.scroll(
if point_ids:
# Single batch retrieve call instead of N sequential scroll calls
# This is ~50x faster for 50 results (1 HTTP request vs 50)
points_response = await qdrant_client.retrieve(
collection_name=settings.get_collection_name(),
scroll_filter=Filter(must=must_conditions),
limit=1, # Only need the first match
ids=point_ids,
with_vectors=["dense"],
with_payload=False,
with_payload=["doc_id", "chunk_start_offset", "chunk_end_offset"],
)
points = points_response[0]
if points:
# Extract dense vector
point = points[0]
# Build chunk_vectors_map from batch response
for point in points_response:
if point.vector is not None:
# If named vectors (dict), extract "dense"
# Extract dense vector (handle both named and unnamed vectors)
if isinstance(point.vector, dict):
vector = point.vector.get("dense")
else:
vector = point.vector
chunk_key = (result.id, chunk_start, chunk_end)
chunk_vectors_map[chunk_key] = vector
if vector is not None and point.payload:
doc_id = point.payload.get("doc_id")
chunk_start = point.payload.get("chunk_start_offset")
chunk_end = point.payload.get("chunk_end_offset")
chunk_key = (doc_id, chunk_start, chunk_end)
chunk_vectors_map[chunk_key] = vector
vector_fetch_duration = time.perf_counter() - vector_fetch_start
@@ -341,16 +311,23 @@ async def vector_visualization_search(request: Request) -> JSONResponse:
chunk_vectors = np.array(chunk_vectors)
# Generate query embedding for visualization
# Reuse query embedding from search algorithm (avoids redundant embedding call)
query_embed_start = time.perf_counter()
from nextcloud_mcp_server.embedding.service import get_embedding_service
if search_algo.query_embedding is not None:
query_embedding = search_algo.query_embedding
logger.info(
f"Reusing query embedding from search algorithm "
f"(dimension={len(query_embedding)})"
)
else:
# Fallback: generate embedding if not available from search
from nextcloud_mcp_server.embedding.service import get_embedding_service
embedding_service = get_embedding_service()
query_embedding = await embedding_service.embed(query)
embedding_service = get_embedding_service()
query_embedding = await embedding_service.embed(query)
logger.info(f"Generated query embedding (dimension={len(query_embedding)})")
query_embed_duration = time.perf_counter() - query_embed_start
logger.info(f"Generated query embedding (dimension={len(query_embedding)})")
# Combine query vector with chunk vectors for PCA
# Query will be the last point in the array
all_vectors = np.vstack([chunk_vectors, np.array([query_embedding])])
@@ -380,9 +357,19 @@ async def vector_visualization_search(request: Request) -> JSONResponse:
)
# Apply PCA dimensionality reduction (768-dim → 3D) on normalized vectors
# Run in thread pool to avoid blocking the event loop (CPU-bound)
pca_start = time.perf_counter()
pca = PCA(n_components=3)
coords_3d = pca.fit_transform(all_vectors_normalized)
def _compute_pca(vectors: np.ndarray) -> tuple[np.ndarray, PCA]:
pca = PCA(n_components=3)
coords = pca.fit_transform(vectors)
return coords, pca
import anyio
coords_3d, pca = await anyio.to_thread.run_sync( # type: ignore[attr-defined]
lambda: _compute_pca(all_vectors_normalized)
)
pca_duration = time.perf_counter() - pca_start
# After fit, these attributes are guaranteed to be set
+29
View File
@@ -2,8 +2,37 @@ import logging
import logging.config
import os
from dataclasses import dataclass
from enum import Enum
from typing import Any, Optional
class DeploymentMode(Enum):
"""Deployment mode for the MCP server.
SELF_HOSTED: Full features, environment-based configuration.
Supports vector sync, semantic search, admin UI.
SMITHERY_STATELESS: Stateless mode for Smithery hosting.
Session-based configuration, no persistent storage.
Excludes semantic search, vector sync, admin UI.
"""
SELF_HOSTED = "self_hosted"
SMITHERY_STATELESS = "smithery"
def get_deployment_mode() -> DeploymentMode:
"""Detect deployment mode from environment.
Returns:
DeploymentMode.SMITHERY_STATELESS if SMITHERY_DEPLOYMENT=true,
otherwise DeploymentMode.SELF_HOSTED (default).
"""
if os.getenv("SMITHERY_DEPLOYMENT", "false").lower() == "true":
return DeploymentMode.SMITHERY_STATELESS
return DeploymentMode.SELF_HOSTED
LOGGING_CONFIG = {
"version": 1,
"disable_existing_loggers": False,
+110 -8
View File
@@ -1,21 +1,37 @@
"""Helper functions for accessing context in MCP tools."""
import logging
from httpx import BasicAuth
from mcp.server.fastmcp import Context
from nextcloud_mcp_server.client import NextcloudClient
from nextcloud_mcp_server.config import get_settings
from nextcloud_mcp_server.config import (
DeploymentMode,
get_deployment_mode,
get_settings,
)
logger = logging.getLogger(__name__)
async def get_client(ctx: Context) -> NextcloudClient:
"""
Get the appropriate Nextcloud client based on authentication mode.
ADR-005 compliant implementation supporting two modes:
1. BasicAuth mode: Returns shared client from lifespan context
2. Multi-audience mode (ENABLE_TOKEN_EXCHANGE=false, default):
Token already contains both MCP and Nextcloud audiences - use directly
3. Token exchange mode (ENABLE_TOKEN_EXCHANGE=true):
Exchange MCP token for Nextcloud token via RFC 8693
ADR-016 compliant implementation supporting three deployment modes:
1. Smithery stateless mode (SMITHERY_DEPLOYMENT=true):
Create client from session configuration (nextcloud_url, username, app_password)
No persistent state - client created per-request from Smithery session config.
2. BasicAuth mode: Returns shared client from lifespan context
3. OAuth mode:
a. Multi-audience mode (ENABLE_TOKEN_EXCHANGE=false, default):
Token already contains both MCP and Nextcloud audiences - use directly
b. Token exchange mode (ENABLE_TOKEN_EXCHANGE=true):
Exchange MCP token for Nextcloud token via RFC 8693
SECURITY: Token passthrough has been REMOVED. All OAuth modes validate
proper token audiences per MCP Security Best Practices specification.
@@ -24,7 +40,7 @@ async def get_client(ctx: Context) -> NextcloudClient:
by the MCP server via @require_scopes decorator, not by the IdP.
This function automatically detects the authentication mode by checking
the type of the lifespan context.
the deployment mode and type of the lifespan context.
Args:
ctx: MCP request context
@@ -34,6 +50,7 @@ async def get_client(ctx: Context) -> NextcloudClient:
Raises:
AttributeError: If context doesn't contain expected data
ValueError: If Smithery mode but session config is missing required fields
Example:
```python
@@ -43,6 +60,12 @@ async def get_client(ctx: Context) -> NextcloudClient:
return await client.capabilities()
```
"""
deployment_mode = get_deployment_mode()
# ADR-016: Smithery stateless mode - create client from session config
if deployment_mode == DeploymentMode.SMITHERY_STATELESS:
return _get_client_from_session_config(ctx)
settings = get_settings()
lifespan_ctx = ctx.request_context.lifespan_context
@@ -75,3 +98,82 @@ async def get_client(ctx: Context) -> NextcloudClient:
f"Lifespan context does not have 'client' or 'nextcloud_host' attribute. "
f"Type: {type(lifespan_ctx)}"
)
def _get_client_from_session_config(ctx: Context) -> NextcloudClient:
"""
Create NextcloudClient from Smithery session configuration.
ADR-016: In Smithery stateless mode, each request includes session config
with the user's Nextcloud credentials. This function creates a fresh client
for each request - no state is persisted between requests.
For container runtime, config is extracted from URL query parameters by
SmitheryConfigMiddleware and stored in a context variable.
Expected session config fields (from Smithery configSchema):
- nextcloud_url: str - Nextcloud instance URL (required)
- username: str - Nextcloud username (required)
- app_password: str - Nextcloud app password (required)
Args:
ctx: MCP request context (not used directly for Smithery config)
Returns:
NextcloudClient configured with session credentials
Raises:
ValueError: If required session config fields are missing
"""
# ADR-016: Get session config from context variable (set by SmitheryConfigMiddleware)
from nextcloud_mcp_server.app import get_smithery_session_config
session_config = get_smithery_session_config()
if session_config is None:
raise ValueError(
"Session configuration required in Smithery mode. "
"Ensure nextcloud_url, username, and app_password are provided as URL query parameters."
)
# Extract required fields - config is always a dict from SmitheryConfigMiddleware
nextcloud_url = session_config.get("nextcloud_url")
username = session_config.get("username")
app_password = session_config.get("app_password")
# Validate required fields
missing_fields = []
if not nextcloud_url:
missing_fields.append("nextcloud_url")
if not username:
missing_fields.append("username")
if not app_password:
missing_fields.append("app_password")
if missing_fields:
raise ValueError(
f"Missing required session config fields: {', '.join(missing_fields)}. "
f"Configure these in the Smithery connection settings."
)
# Type assertions after validation (for type checker)
# These are guaranteed to be str after the missing_fields check above
assert nextcloud_url is not None
assert username is not None
assert app_password is not None
# Validate URL format
if not nextcloud_url.startswith(("http://", "https://")):
raise ValueError(
f"Invalid nextcloud_url: {nextcloud_url}. "
f"Must start with http:// or https://"
)
logger.debug(f"Creating Smithery client for {nextcloud_url} as {username}")
# Create client with session credentials using BasicAuth
return NextcloudClient(
base_url=nextcloud_url,
username=username,
auth=BasicAuth(username, app_password),
)
@@ -37,7 +37,9 @@ class BM25SparseEmbeddingProvider:
def encode(self, text: str) -> dict[str, Any]:
"""
Generate BM25 sparse embedding for a single text.
Generate BM25 sparse embedding for a single text (synchronous).
Note: For async contexts, prefer encode_async() to avoid blocking the event loop.
Args:
text: Input text to encode
@@ -53,6 +55,23 @@ class BM25SparseEmbeddingProvider:
"values": sparse_embedding.values.tolist(),
}
async def encode_async(self, text: str) -> dict[str, Any]:
"""
Generate BM25 sparse embedding for a single text (async).
Runs CPU-bound BM25 encoding in thread pool to avoid blocking the event loop.
Args:
text: Input text to encode
Returns:
Dictionary with 'indices' and 'values' keys for Qdrant sparse vector
"""
import anyio
# Run CPU-bound BM25 encoding in thread pool
return await anyio.to_thread.run_sync(lambda: self.encode(text)) # type: ignore[attr-defined]
async def encode_batch(self, texts: list[str]) -> list[dict[str, Any]]:
"""
Generate BM25 sparse embeddings for multiple texts (batched).
@@ -140,6 +140,7 @@ class SearchResult:
page_number: Page number for PDF documents (None for other doc types)
chunk_index: Zero-based index of this chunk in the document
total_chunks: Total number of chunks in the document
point_id: Qdrant point ID for batch vector retrieval (None if not from Qdrant)
"""
id: int
@@ -153,6 +154,7 @@ class SearchResult:
page_number: int | None = None
chunk_index: int = 0
total_chunks: int = 1
point_id: str | None = None
def __post_init__(self):
"""Validate score is non-negative.
@@ -172,8 +174,15 @@ class SearchAlgorithm(ABC):
All search algorithms must implement the search() method with consistent
interface, allowing them to be used interchangeably.
Attributes:
query_embedding: The query embedding generated during the last search.
Available after search() completes for algorithms that use embeddings.
Can be reused by callers to avoid redundant embedding generation.
"""
query_embedding: list[float] | None = None
@abstractmethod
async def search(
self,
+4 -1
View File
@@ -101,11 +101,13 @@ class BM25HybridSearchAlgorithm(SearchAlgorithm):
# Generate dense embedding for semantic search
embedding_service = get_embedding_service()
dense_embedding = await embedding_service.embed(query)
# Store for reuse by callers (e.g., viz_routes PCA visualization)
self.query_embedding = dense_embedding
logger.debug(f"Generated dense embedding (dimension={len(dense_embedding)})")
# Generate sparse embedding for BM25 keyword search
bm25_service = get_bm25_service()
sparse_embedding = bm25_service.encode(query)
sparse_embedding = await bm25_service.encode_async(query)
logger.debug(
f"Generated sparse embedding "
f"({len(sparse_embedding['indices'])} non-zero terms)"
@@ -218,6 +220,7 @@ class BM25HybridSearchAlgorithm(SearchAlgorithm):
page_number=result.payload.get("page_number"),
chunk_index=result.payload.get("chunk_index", 0),
total_chunks=result.payload.get("total_chunks", 1),
point_id=str(result.id), # Qdrant point ID for batch retrieval
)
)
+3
View File
@@ -78,6 +78,8 @@ class SemanticSearchAlgorithm(SearchAlgorithm):
# Generate embedding for query
embedding_service = get_embedding_service()
query_embedding = await embedding_service.embed(query)
# Store for reuse by callers (e.g., viz_routes PCA visualization)
self.query_embedding = query_embedding
logger.debug(
f"Generated embedding for query (dimension={len(query_embedding)})"
)
@@ -164,6 +166,7 @@ class SemanticSearchAlgorithm(SearchAlgorithm):
page_number=result.payload.get("page_number"),
chunk_index=result.payload.get("chunk_index", 0),
total_chunks=result.payload.get("total_chunks", 1),
point_id=str(result.id), # Qdrant point ID for batch retrieval
)
)
+60
View File
@@ -0,0 +1,60 @@
"""Smithery-specific entrypoint for stateless deployment.
ADR-016: This entrypoint is used when deploying on Smithery's hosting platform.
It configures the server for stateless operation with per-session authentication.
Features disabled in Smithery mode:
- Vector sync / semantic search (no persistent storage)
- Admin UI at /app (no webhooks, no vector viz)
- OAuth provisioning tools (no token storage)
Features enabled:
- Core Nextcloud tools (notes, calendar, contacts, files, deck, tables, cookbook)
- Per-session app password authentication via Smithery configSchema
- Health check endpoints (/health/live, /health/ready)
"""
import logging
import os
import uvicorn
from nextcloud_mcp_server.config import setup_logging
logger = logging.getLogger(__name__)
def main():
"""Start the MCP server in Smithery stateless mode."""
# Setup logging first
setup_logging()
# Force stateless mode environment variables
os.environ["SMITHERY_DEPLOYMENT"] = "true"
os.environ["VECTOR_SYNC_ENABLED"] = "false"
logger.info("Starting Nextcloud MCP Server in Smithery stateless mode")
# Import app after setting environment variables
from nextcloud_mcp_server.app import get_app
# Create the app with streamable-http transport (required for Smithery)
app = get_app(transport="streamable-http")
# Smithery sets PORT environment variable
port = int(os.environ.get("PORT", 8081))
logger.info(f"Listening on port {port}")
uvicorn.run(
app,
host="0.0.0.0",
port=port,
log_level="info",
# Disable access log for cleaner output
access_log=False,
)
if __name__ == "__main__":
main()
+2 -1
View File
@@ -1,6 +1,6 @@
[project]
name = "nextcloud-mcp-server"
version = "0.45.0"
version = "0.46.1"
description = "Model Context Protocol (MCP) server for Nextcloud integration - enables AI assistants to interact with Nextcloud data"
authors = [
{name = "Chris Coutinho", email = "chris@coutinho.io"}
@@ -126,6 +126,7 @@ dev = [
[project.scripts]
nextcloud-mcp-server = "nextcloud_mcp_server.cli:run"
smithery-main = "nextcloud_mcp_server.smithery_main:main"
[[tool.uv.index]]
name = "testpypi"
+38
View File
@@ -0,0 +1,38 @@
# Smithery configuration for Nextcloud MCP Server
# See: https://smithery.ai/docs/build/configuration
# ADR-016: Stateless deployment mode for multi-user public Nextcloud instances
runtime: "container"
build:
dockerfile: "Dockerfile.smithery"
dockerBuildPath: "."
startCommand:
type: "http"
configSchema:
type: "object"
required:
- "nextcloud_url"
- "username"
- "app_password"
properties:
nextcloud_url:
type: "string"
title: "Nextcloud URL"
description: "Your Nextcloud instance URL (e.g., https://cloud.example.com). Must be publicly accessible."
pattern: "^https?://.+"
username:
type: "string"
title: "Username"
description: "Your Nextcloud username"
minLength: 1
app_password:
type: "string"
title: "App Password"
description: "Nextcloud app password. Generate at Settings > Security > App passwords. Do NOT use your main password."
minLength: 1
exampleConfig:
nextcloud_url: "https://cloud.example.com"
username: "alice"
app_password: "xxxxx-xxxxx-xxxxx-xxxxx-xxxxx"
Generated
+1 -1
View File
@@ -1936,7 +1936,7 @@ wheels = [
[[package]]
name = "nextcloud-mcp-server"
version = "0.45.0"
version = "0.46.1"
source = { editable = "." }
dependencies = [
{ name = "aiosqlite" },