Skip to main content
Synclair’s knowledge reaches an agent three ways, and they’re genuinely different mechanisms with different costs. Knowing which is which is the difference between a foundation that helps and one that just sits there.

​
Ambient — how an agent learns the way you work

The AGENTS.md router and every capability’s one-line description sit in context from the start. That’s what lets a skill auto-trigger without anyone naming it, and it’s covered in Skills & agents. It’s the right shape for conventions — “build views this way, register components at creation” — and the wrong shape for facts. Which is what the other two are for.

​
Pull — the nine MCP tools

Ambient markdown is a poor way to ask one narrow question. “What’s the token for a warning background?” shouldn’t cost a 4,368-token read of tokens.ts. So the same data is served as task-shaped tools:
The AI Setup page's MCP servers tab showing the synclair server, serving, with nine tools

The MCP tab on /synclair/ai-setup. The synclair server's tool list is live from the same registry both transports share — so the page can't disagree with what an agent actually gets.

Three properties are the point:

No hub required

It reads JSON off disk — no Next, no port, no dev server. Agents stop needing the hub running to read the catalog.

No dependencies

Raw JSON-RPC over stdio rather than the SDK, so a cloned foundation works in any clone with zero install.

Two transports, one registry

stdio for agents in a clone; HTTP for a teammate with none. Both import the same registry, so they can’t answer differently.

​
Registering it

It resolves the target from data/setup.json, because the right answer depends on topology: It merges rather than clobbers an existing .mcp.json, and is deliberately not wired to postinstall. Writing a repo’s own .mcp.json is fair — it’s visible in git and gated by the client’s approval prompt. Writing your global agent config as an install side effect would be invisible and hard to undo.
Registration is the step that silently doesn’t happen. The server can run perfectly and its tools can return real content while every agent in the repo still reads whole files by hand — because nothing surfaces a tool that was never offered. check:mcp is in verify-ui for exactly this reason; see the guardrails.

​
The hosted endpoint

A teammate with no clone points their client at the hub’s /api/mcp route with a bearer token from SYNCLAIR_MCP_TOKENS. Same nine tools, same registry. With no tokens configured the endpoint returns 404 on every request — the endpoint simply does not exist. A clone that never sets them never exposes one.

​
Push — context that arrives without being asked

MCP tools are pull: an agent that never calls one gets nothing, and nothing tells it to. That’s a real limitation, and the fix is a PostToolUse hook that fires when an agent edits a file. The reasoning is worth stating plainly: a ruling recalled during review is an explanation; the same ruling surfaced before the code is written is a different outcome. The session brief tells an agent the repo’s state when a session opens — that’s the cheap half. Firing at the moment of an edit is the half that changes what gets written. The hook reads its payload on stdin, writes at most a couple of lines, and gets out of the way. Its failure modes are inverted from a normal script’s — printing when it shouldn’t is worse than crashing — so it carries its own self-test (check:augment).

​
Measuring any of this

Every change to the agent interface is judged against a baseline rather than a hunch:
The number, and what it isn’t. ~40% saving against equivalent file reads across comparable scenarios, versus a permanent +854-token tool surface.An earlier version of this harness reported 86–97%. It was wrong three ways: it counted skill bodies as lookup cost (a skill is process guidance read on demand — the tool layer doesn’t replace it), it compared filtered queries against whole-file reads (a narrower question dressed up as compression), and blank seed data produced fake wins (three scenarios had no data, so the tool answered “nothing here yet” cheaply and that read as a 97% saving).All three are now enforced in the script, which prints “not comparable” rather than a flattering percentage. The harness has caught three real defects — a missing tool, its own inflated arithmetic, and a stdout-truncation bug in the server — which is the argument for building it before the thing it measures.

Related: the guardrails

Including check:mcp and check:mcp-contract, which keep this interface honest.