AI Layer

Most “AI-native” tooling means a hosted assistant. Here it means something narrower and more checkable: an agent gets tools that operate your ecosystem and retrieval over engineering documents you wrote, through one server you run yourself.

Agents read the corpus through the MCP rag_context tool. The research pipeline writes to it, but only through a pull request a human merges, so the corpus grows on purpose.

Three moving parts, and they only connect in one direction: the research pipeline opens a pull request, a human merges it, mx rag ingest picks up the delta, and agents retrieve it. Nothing writes to the corpus without a merge.

Page	What it covers
MCP server	The 47 tools, grouped into four families; building the server and wiring a client
Techniques corpus & RAG	rag.toml, Neon or a local pgvector container, embeddings, and where your text actually goes
Research pipeline	How the corpus grows: weekly run, primary-source corroboration, PR gate, human merge
Agent execution rules	The rules agents in this repository work under

The documents themselves are published under Techniques Corpus. It is the same markdown that gets chunked, embedded and served to agents, rendered for humans.

What it is not

• Not a hosted service. There is no MechCrate API. The MCP server is a local binary; the corpus is a Postgres connection string you own.
• Not a model. mx never runs inference. Your agent supplies the model; mx supplies tools and retrieved text.
• Not magic retrieval. The corpus is 66 documents that a human merged. It answers well inside that surface and returns weak hits outside it, which is what mx rag gaps exists to surface.