provisioning
provisioning: 21 operations.
provisioning: 21 operations. Name one in "op" and pass that operation's own arguments in "input". describe returns an operation's input schema.
| Tool | provisioning |
| Door | https://api.hanzo.ai/v1/mcp |
| Method | tools/call (JSON-RPC 2.0) |
| Arguments | 2, 1 required |
| Operation | GET /v1/search · GET /v1/search/{name} · GET /v1/datastore · GET /v1/datastore/{name} · GET /v1/docdb · GET /v1/docdb/{name} · GET /v1/kv · GET /v1/kv/{name} · GET /v1/s3 · GET /v1/s3/{name} · GET /v1/sql · GET /v1/sql/{name} · GET /v1/vector · GET /v1/vector/{name} |
| Product | search |
Arguments
| Field | Type | Required | Default | Values | Description |
|---|---|---|---|---|---|
input | object | — | — | — | arguments for the chosen op |
op | string | yes | — | — | delete_search — Deletes one search index from the shared backend and removes its metadata row. get_search — Lists the caller org's search indexes. get_search_by_name — Returns one search index's metadata. |
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 the door'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 the door 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": "provisioning",
"arguments": {
"op": "get_search"
}
}
}'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 the door 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
provisioning dispatches to 21 operations. 14 of them the door names exactly as the document ids them, and those are below; for the rest the door has its own verb, which describe resolves.
| Operation | Route | Product | Summary |
|---|---|---|---|
get_search | GET /v1/search | search | Lists the caller org's search indexes. |
get_search_by_name | GET /v1/search/{name} | search | Returns one search index's metadata. |
get_datastore | GET /v1/datastore | datastore | Lists the caller org's Hanzo Datastore warehouses. |
get_datastore_by_name | GET /v1/datastore/{name} | datastore | Returns one Hanzo Datastore warehouse's metadata. |
get_docdb | GET /v1/docdb | docdb | ListDocDB lists the caller org's Hanzo DocDB document databases. |
get_docdb_by_name | GET /v1/docdb/{name} | docdb | GetDocDB returns one Hanzo DocDB database's metadata. |
get_kv | GET /v1/kv | kv | ListKV lists the caller org's Hanzo KV stores. |
get_kv_by_name | GET /v1/kv/{name} | kv | GetKV returns one Hanzo KV store's metadata. |
get_s3 | GET /v1/s3 | s3 | Lists the caller org's object-storage buckets. |
get_s3_by_name | GET /v1/s3/{name} | s3 | Returns one bucket's metadata. |
get_sql | GET /v1/sql | sql | ListSQL lists the caller org's Hanzo SQL databases. |
get_sql_by_name | GET /v1/sql/{name} | sql | GetSQL returns one Hanzo SQL database's metadata. |
get_vector | GET /v1/vector | vector | Lists the caller org's vector collections. |
get_vector_by_name | GET /v1/vector/{name} | vector | Returns one vector collection's metadata. |
The same capability over plain HTTP is in the search API reference, on https://api.hanzo.ai.
How is this guide?