MCP Server exposing the Urban Dictionary via the Model Context Protocol.
This can be run in Local CLI mode or Remote server mode.
In CLI mode using uv.
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"urban-dictionary": {
"type": "local",
"command": ["uvx", "urban-dictionary-mcp"]
}
}
}
In CLI mode using Python pip.
pip install urban-dictionary-mcp
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"urban-dictionary": {
"type": "local",
"command": ["urban-dictionary-mcp"]
}
}
}
With Docker run.
docker run --rm -p 80:8000 ghcr.io/cssnr/urban-dictionary-mcp:latest
With Docker Compose.
services:
app:
image: ghcr.io/cssnr/urban-dictionary-mcp:latest
ports:
- '80:8000'
With Python from source.
uv sync
uv run uvicorn urban_dictionary_mcp.server:app --app-dir src --host 0.0.0.0 --port 8000
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"urban-dictionary": {
"type": "remote",
"url": "http://localhost/mcp"
}
}
}
Note: Set the url to the host you are running the server on.
For a Docker Swarm + Traefik example see the docker-compose-swarm.yaml.
For a Portainer Deploy workflow see the .github/workflows/deploy.yaml.
This is for advanced configuration only.
| Variable | Description | Default |
|---|---|---|
HISHEL_CACHE_PATH | Path cache database file | ./hishel_cache.db |
HISHEL_CACHE_TTL | Cache TTL in seconds | 1209600 |
STATELESS_HTTP | Enable stateless HTTP mode | true |
Boolean True Values (case-insensitive): 1, on, t, true, y, yes
In Docker the cache path is /data/hishel_cache.db so you can mount /data as a volume.
Sync project.
uv sync
Run local server.
run cli
Run remote server (live reload).
run dev
Point your client to: http://localhost:8000/mcp
Run remote Docker Compose (live reload).
run compose
Point your client to: http://localhost/mcp
You can set the PORT environment variable.
To build and test the docker image run.
bash build.sh
docker compose up
Point your client to: http://localhost/mcp
This builds the bdist and wheel, if you have a use for it...
run build
If you run into any issues or need help getting started, please do one of the following:
Please consider making a donation to support the development of this project and additional open source projects.
For a full list of current projects visit: https://cssnr.github.io/
Content type
Image
Digest
sha256:d25a126e8…
Size
256.1 MB
Last updated
4 months ago
docker pull cssnr/urban-dictionary-mcp