Train

train: 35 operations.

Also for this capability: API · CLI · MCP · SDKs

train: 35 operations. Name one in "op" and pass that operation's own arguments in "input". describe returns an operation's input schema.

Tooltrain
Addresshttps://api.hanzo.ai/v1/mcp
Methodtools/call (JSON-RPC 2.0)
Arguments2, 1 required
OperationGET /v1/capabilities/capture · GET /v1/capabilities/corrections · POST /v1/capabilities · DELETE /v1/capabilities/{name} · POST /v1/capabilities/{name}/disable · GET /v1/capabilities/{name} · GET /v1/capabilities · POST /v1/capabilities/{name}/publish · POST /v1/capabilities/{name}/rollback · PUT /v1/capabilities/capture · POST /v1/capabilities/{name}/train
Producttrain

Arguments

FieldTypeRequiredDefaultValuesDescription
inputobject———arguments for the chosen op
opstringyes———

tools/list declares a type, a description, which fields are required and an enumerated value set for each field and nothing further, and every column above is MCP's own. This tool takes an operation name and that operation's arguments, so what the document constrains is what goes inside input, field by field, on the operation you name — ask describe for that. A — means MCP does not constrain the field.

Call it

A tools/call carries every argument in one flat object — nothing binds to a path or a query string. This call carries exactly the arguments the operation requires, so it is the smallest one that can run.

curl -X POST https://api.hanzo.ai/v1/mcp \
  -H "Authorization: Bearer $HANZO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
       "jsonrpc": "2.0",
       "id": 1,
       "method": "tools/call",
       "params": {
         "name": "train",
         "arguments": {
           "op": "list_train_artifacts"
         }
       }
     }'

Values are the operation's own defaults and enumerated values where it declares them, and a <placeholder> where neither source declares one. tools/list needs no credential; tools/call does — called without one MCP answers HTTP 200 with a JSON-RPC result whose isError is set and whose text says what was missing. How to get a key →

The operation behind it

train dispatches to 35 operations. 11 of them MCP names exactly as the document ids them, and those are below; for the rest MCP has its own verb, which describe resolves.

OperationRouteProductSummary
capabilitiesCaptureGET /v1/capabilities/capturetrainAnswers whether the org's Kai decisions keep their states for its capabilities to learn from.
capabilitiesCorrectionsGET /v1/capabilities/correctionstrainAnswers every correction of the org's decisions, newest first, each captured (it can teach) or missing (its decision was made with capture off), and the questions they ask, each counted: what a capability is made from.
capabilitiesCreatePOST /v1/capabilitiestrainMakes a capability in draft from captured corrections of one question: that question (its key, type and labels) is the route it will be installed behind.
capabilitiesDeleteDELETE /v1/capabilities/{name}trainDeletes a capability and its versions; their artifacts go with the org's retention.
capabilitiesDisablePOST /v1/capabilities/{name}/disabletrainTakes a capability's installed version out of the org's published set: its questions are answered by base Kai, bit for bit, from the next decision.
capabilitiesGetGET /v1/capabilities/{name}trainAnswers one capability: its versions with their evaluations, newest first, and what its installed version did live.
capabilitiesListGET /v1/capabilitiestrainAnswers the org's capabilities by name, each with its state, its latest and installed versions, and what the installed one did live.
capabilitiesPublishPOST /v1/capabilities/{name}/publishtrainInstalls a version in the org's published set, where ai attaches it to the org's decisions: the version's evaluation must have passed, and it must have been taught over the base Kai serves now.
capabilitiesRollbackPOST /v1/capabilities/{name}/rollbacktrainPuts the version installed before the installed one back in the org's published set: exactly that version's artifact, nothing retrained.
capabilitiesSetCapturePUT /v1/capabilities/capturetrainTurns capture on or off for the org's Kai decisions from the next one.
capabilitiesTrainPOST /v1/capabilities/{name}/traintrainTeaches a capability a new version from its corrections, on the CPU over the states its org's decisions captured: no row is encoded again.

The same capability over plain HTTP is in the train API reference, on https://api.hanzo.ai.


All 127 tools · MCP · API reference

Generated from tools/list on https://api.hanzo.ai/v1/mcp — 127 tools captured 2026-11-10.

Was this page useful?
Broken link or missing step? Drop it in #docs on Discord or open a PR.