ModelBrain's MCP server tools: the full list of five calls

Every MCP tool ModelBrain's server exposes, in one place: remember, recall, forget, expand, connector_sync. It would be easy to add a dozen more, one per internal operation. We didn't, because every call an assistant can make is a call it can also get wrong.

The five

remember, recall, forget, expand, and connector_sync are the entire MCP surface. Anything an assistant needs to do with your memory reduces to one of these five: save something, retrieve something, remove something, get more detail on something already retrieved, or bring a connected folder up to date.

Why not a sixth, for the thing that's obviously missing

The most tempting sixth call is something like dataset_query, for structured queries over tabular data (CSV, XLSX, JSON). It's sketched, not built, and deliberately deferred rather than bolted on early. Structured-data tooling is a genuinely different problem from document-and-assertion memory, and shipping a half-designed version of it now would mean living with an API shape decided under time pressure rather than after the ingestion formats it depends on actually exist.

The correction operations: two inside forget, one inside remember

Delete and exclude are forget's own two independent switches, not a menu of named modes. Reverting to an earlier version runs through remember instead, since it's really "store this earlier version as current again," not a removal. Between the two calls, deletion, permanent exclusion, and correction are all covered without a sixth or seventh tool (described in more detail here), because the assistant calling these tools shouldn't need to memorize which of several near-synonymous verbs does what.

A small surface is a design decision, not a limitation

Every additional call is one more thing a host has to learn correctly and one more way an assistant can misuse the API on your behalf. Five calls that map cleanly onto five real actions has held up so far. It grows only when a genuinely new action shows up that the existing five can't express, not because a bigger API looks more capable on a docs page.