Serving the layer to AI clients
One shared server per repository, every client a peer, the same layer over MCP, HTTP and the command line.
One shared server per repository, every client a peer, the same layer over MCP, HTTP and the command line.
- use cases
- 3
- described
- 3
-
described basic
Find an object of the layer without reading everything
Search durable records literally across kinds from the shell, and ask the shared server the same question over MCP with majordomus_search and majordomus_get.
search · knowledge · prompt -
described basic
See what the repository holds, and run one of its capabilities, without reading a file
Open the shared server in a browser and get the whole layer as pages: what exists, where each thing came from, what depends on what, what is failing, and a form that runs any capability.
doctor · knowledge -
described basic
Serve the repository's AI layer to every AI client through one shared server
Open the repository in any client the tool declares a provider for (docs/generated/providers.md) and have each of them read the same rules, prompts and knowledge over MCP from one process, seeing each other.
init · doctor