A native MCP interface to the canonical model
Read a canonical model's native MCP interface as the source of truth for how humans and agents query one org's estate - why the surface is native rather than adapted, the protocol contract it commits to, and the tools and resources you call. Cogitave's Core is the worked example.
Units5
Duration25 min
Levelintermediate
By the end of this module, you'll be able to:
- Explain why a canonical model's MCP tools and resources can be its query surface rather than an adapter bolted onto REST - the decision Cogitave recorded in ADR-0003.
- State the protocol baseline such an MCP server commits to: spec revision, transports, schema dialect, and how tool errors are reported - with Cogitave's Core as the worked instance.
- Name the MCP tools and resources such a surface exposes, what each returns, and how a bounded graph-query tool is kept from becoming a general escape hatch.
- Distinguish the read tools from the propose-only request-lifecycle tools, and explain why writes never mutate protected state directly.
Prerequisites
- Familiarity with a single canonical property graph (such as Cogitave's Core) is helpful.
- No prior Model Context Protocol experience required.
Units
- 01Introduction4 min
- 02Why MCP is the native surface7 min
- 03Tools, resources, and propose-only governance7 min
- 04Knowledge check4 min
- 05Summary3 min
Related
- The one-model architecture Explain why an AI-native organization runs on one canonical property graph that humans and agents both query, what its node/edge model and identity scheme look like, and why a labeled property graph is the right substrate. Cogitave's Core is the concrete example.
- Project products into the canonical model See how content projects into one canonical model as typed, content-addressed nodes rather than separate silos - Cogitave's Core is the worked example - and how the fact registry's cite-not-restate rule and fact-drift scanner keep one owner per fact across your estate.
- Query your canonical model Learn how a query layer resolves a request against one canonical graph - lexical BM25 and dense HNSW vectors fused by Reciprocal Rank Fusion, a graph-aware rerank and ranking signals, and a bounded, read-only profile agents call directly. Cogitave Query is the reference implementation you'll trace.