OpenWebUI/docs
1
0
Fork 0
mirror of https://github.com/open-webui/docs synced 2025-05-19 18:58:41 +00:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

Update mcp.mdx

Browse Source
This commit is contained in:
Timothy Jaeryang Baek 2025-03-30 04:48:03 -07:00
parent 6ecd232c63
commit e986704582
1 changed files with 41 additions and 35 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

76
docs/openapi-servers/mcp.mdx
View File

@ -11,70 +11,75 @@ The MCP-to-OpenAPI proxy server lets you use tool servers implemented with MCP (
### ✅ Quickstart: Running the Proxy Locally ### ✅ Quickstart: Running the Proxy Locally
Here's how simple it is to launch the MCP-to-OpenAPI proxy server and expose tools already available from an MCP server: Here's how simple it is to launch the MCP-to-OpenAPI proxy server using the lightweight, easy-to-use tool **mcpo** ([GitHub Repository](https://github.com/open-webui/mcpo)):
1. **Prerequisites** 1. **Prerequisites**
- **Python 3.8+** with `pip` installed.
- MCP-compatible application (for example: `mcp-server-time`)
- (Optional but recommended) `uv` installed for faster startup and zero-config convenience.
- **Python 3.8+** with `pip` installed. 2. **Install mcpo**
- (Optional) `nodejs` with `npm` and/or `uv` installed to run the MCP server.
2. **Clone the Repository & Install Dependencies** Using **uv** (recommended):
```bash ```bash
git clone https://github.com/open-webui/openapi-servers uvx mcpo --port 8000 -- your_mcp_server_command
cd openapi-servers/servers/mcp-proxy
pip install -r requirements.txt
``` ```
3. **Run The Proxy Server** Or using `pip`:
Simply type:
```bash ```bash
python main.py --host 0.0.0.0 --port 8000 -- uvx mcp-server-time --local-timezone=America/New_York pip install mcpo
mcpo --port 8000 -- your_mcp_server_command
``` ```
- Replace `uvx mcp-server-time [options]` above with your custom MCP server command. 3. **Run the Proxy Server**
Example usage—exposing a time server:
```bash
uvx mcpo --port 8000 -- uvx mcp-server-time --local-timezone=America/New_York
```
Replace `uvx mcp-server-time [options]` with your custom MCP tool command.
### 🚀 Accessing the Generated APIs ### 🚀 Accessing the Generated APIs
As soon as it starts, the MCP Proxy automatically: As soon as it starts, the MCP Proxy (`mcpo`) automatically:
- Discovers available MCP tools dynamically and generates REST endpoints. - Discovers MCP tools dynamically and generates REST endpoints.
- Creates human-readable documentation accessible from the built-in interactive API page at: http://localhost:8000/docs - Creates interactive, human-readable OpenAPI documentation accessible at:
- `http://localhost:8000/docs`
- Now, simply call the generated API endpoints directly or use them with your AI agents or API clients! Simply call the auto-generated API endpoints directly via HTTP clients, AI agents, or other OpenAPI tools of your preference.
### 📖 Example Workflow for End-Users ### 📖 Example Workflow for End-Users
Assuming you ran the MCP command above (`uvx mcp-server-time`): Assuming you started the above server command (`uvx mcp-server-time`):
- Visit your local URL (`http://localhost:8000/docs`) - Visit your local API documentation at `http://localhost:8000/docs`.
- Find the generated endpoint (e.g. `/get_current_time`) and use the easy interactive form provided by FastAPI. - Select a generated endpoint (e.g. `/get_current_time`) and use the provided interactive form.
- Click "**Execute**", and immediately see the response output. - Click "**Execute**" and instantly receive your response.
You now have standard OpenAPI REST APIs made available instantly without complex setups. No setup complexity—just instant REST APIs.
## 🚀 Deploying in Production (Example) ## 🚀 Deploying in Production (Example)
Deploying your MCP-to-OpenAPI proxy to a production environment is easy. Here's a concise step-by-step example using Docker and popular deployment environments like cloud hosting or VPS. Deploying your MCP-to-OpenAPI proxy (powered by mcpo) is straightforward. Here's how to easily Dockerize and deploy it to cloud or VPS solutions:
### 🐳 Dockerize your Proxy Server ### 🐳 Dockerize your Proxy Server using mcpo
1. **Create a Dockerfile** (`Dockerfile`) inside your proxy server directory (`servers/mcp-proxy`): 1. **Dockerfile Example**
Create the following `Dockerfile` inside your deployment directory:
```dockerfile ```dockerfile
FROM python:3.11-slim FROM python:3.11-slim
WORKDIR /app WORKDIR /app
RUN pip install mcpo uv
COPY . /app
RUN pip install -r requirements.txt
# Replace with your MCP server command; example: uvx mcp-server-time # Replace with your MCP server command; example: uvx mcp-server-time
CMD ["python", "main.py", "--host", "0.0.0.0", "--port", "8000", "--", "uvx", "mcp-server-time", "--local-timezone=America/New_York"] CMD ["uvx", "mcpo", "--host", "0.0.0.0", "--port", "8000", "--", "uvx", "mcp-server-time", "--local-timezone=America/New_York"]
``` ```
2. **Build & Run the Container Locally** 2. **Build & Run the Container Locally**
@ -84,17 +89,18 @@ docker build -t mcp-proxy-server .
docker run -d -p 8000:8000 mcp-proxy-server docker run -d -p 8000:8000 mcp-proxy-server
``` ```
3. **Deploy to Production (AWS/Cloud/VPS Example)** 3. **Deploying Your Container**
Push to DockerHub or another registry:
- Push the Docker image to DockerHub or your favorite registry:
```bash ```bash
docker tag mcp-proxy-server yourdockerusername/mcp-proxy-server:latest docker tag mcp-proxy-server yourdockerusername/mcp-proxy-server:latest
docker push yourdockerusername/mcp-proxy-server:latest docker push yourdockerusername/mcp-proxy-server:latest
``` ```
- Use Docker Compose, Kubernetes manifests, or deploy directly to AWS ECS, Azure Container Instances, Render.com Containers, Heroku, or your desired cloud hosting platform. Deploy using Docker Compose, Kubernetes YAML manifests, or your favorite cloud container services (AWS ECS, Azure Container Instances, Render.com, or Heroku).
✔️ **Production-ready** — your MCP servers are now exposed and safely accessible using industry-standard REST APIs! ✔️ Your production MCP servers are now effortlessly available via REST APIs!
## 🧑‍💻 Technical Details and Background ## 🧑‍💻 Technical Details and Background