Web UI
6 min
the docker image includes a built in chat interface that lets you interact with litmus edge using natural language no mcp client configuration required start the server with the web ui docker run d name litmus mcp server \\ p 8000 8000 p 9000 9000 \\ e anthropic api key=\<key> \\ ghcr io/litmusautomation/litmus mcp server\ latest 9000 web ui open http //localhost 9000 in your browser, add a litmus edge instance via the config page, and start chatting 8000 sse endpoint for external mcp clients still available; using the web ui does not disable it first run setup if no llm api key is configured, opening http //localhost 9000 lands on a setup screen enter at least one of anthropic api key openai api key gemini api key the web ui saves the keys and immediately fetches the live model catalog from each provider so you can pick a specific model pages path purpose / chat interface streams the model's response, renders markdown, shows tool call badges, supports a stop button /update env configuration api keys, model selection, litmus edge instances, nats, influxdb, lem /health one status card per configured litmus edge instance shows reachability and active instance state /setup first run api key entry (auto redirected to when no key is set) llm providers supported providers anthropic claude, openai, google gemini the active provider and model are switchable from /update env at any time see llm providers # for details multiple litmus edge instances the web ui lets you register and switch between multiple litmus edges from a single mcp server each instance keeps its own url and oauth2 credentials; the active instance is mirrored into the canonical edge url / edge api client id / edge api client secret so the rest of the system works unchanged manage instances under config > litmus edge instances , or check status per instance from the health page see multi instance edge # splitting the web ui and mcp server across hosts if you deploy the mcp server and the web ui on separate hosts, point the web ui at the server with e mcp sse url=http //\<mcp server host> 8000/sse live litmus documentation as mcp resources the server exposes litmus\ //docs/\<section> uris that fetch live content from docs litmus io https //docs litmus io on demand mcp aware clients can pull current reference material directly into the model's context see mcp resources #