The tools

One tool per API route, generated from the same OpenAPI document as the endpoint reference. A tool takes the parameters its route takes.

Naming

<resource>_<action>, from the URL shape:

How many

47 read-only. With writes enabled, 149.

That gap is the argument for leaving writes off unless you need them: the read-only catalogue is roughly 12k tokens of context against 40k, spent before the model has read a single number of yours.

A grant without write access is not shown the mutating tools. They are absent from the catalogue rather than present and refused, so an agent never plans around a tool it cannot use.

Annotations

Every tool carries the three MCP hints, always set:

• readOnlyHint — true for the 47
• destructiveHint — true for deletes, bulk deletes, and merges
• openWorldHint — always false; everything is scoped to one wallet

A merge is marked destructive even though it is a POST, because folding one thing into another deletes the original. A client that asks before running a destructive tool will ask for those.

The ones worth reaching for

• data_* — the seventeen slices. Any question about a total, an average or a series belongs here.
• transactions_search — a POST that only reads; its filters are too structured for a query string. It is available to read-only grants for exactly that reason.
• wallets_list — the first call an OAuth-connected agent should make, since a grant can reach several wallets and tools need to be told which.

Results

Every tool answers { result: … }, with the route's response inside, unchanged. The envelope is declared in the output schema and the contents are not — describing every response shape put outputSchema at nearly half of the whole catalogue payload, which is context better spent on the inputs that tell a model what to send.