About mcpo-docker
mcpo-docker is an example Docker image and configuration for running mcpo, which exposes MCP servers as OpenAPI-compatible HTTP endpoints. It is intended for connecting those endpoints to OpenWebUI.
Key features
- 01Example Docker image for mcpo
- 02Sample server configuration
- 03Separate endpoint for each MCP server
Use cases
- 01Run mcpo in Docker
- 02Expose configured MCP servers over HTTP
- 03Connect server endpoints to OpenWebUI
MCP support
The image runs mcpo, which exposes MCP servers through OpenAPI-compatible HTTP endpoints. Each configured MCP server receives a separate endpoint.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEmcpo-docker
The source from alephpiece .
An example Docker image for mcpo, a tool that exposes MCP (Model Context Protocol) servers as OpenAPI-compatible HTTP endpoints for OpenWebUI.
Still waiting for the official mcpo docker!
Quick start
# Pull the repo
git clone https://github.com/lkoujiu/mcpo-docker.git
cd mcpo-docker
# Copy sample files and edit them as you like.
cp config.example.json config.json
cp docker-compose.example.yml docker-compose.yml
# Create a container and wait for the servers to start.
# It may take time if you have many servers enabled.
docker compose up -d
Or you can build the docker from source.
docker build -t mcpo .
Connect OpenWebUI to your servers
See OpenAPI Tool Servers for details.
- Open OpenWebUI > Settings > Tools
- Add a connection
http://localhost:8000/memory - Check available tools on the chat page
With mcpo, each MCP server gets a separate endpoint. For example:
http://localhost:8000/sequential-thinkinghttp://localhost:8000/memoryhttp://localhost:8000/time
MCP configuration
Standard MCP configuration file, see config.example.json.
License
MIT
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.