List prompt

Returns the caller org's prompt library as one row per prompt: its name, type, every version number it has, its taxonomy and when it last changed.

GET /v1/prompt

Prompt → · All API references → · Get started →

Address	`https://api.hanzo.ai/v1/prompt`
Method	`GET`
Operation	`get_prompt`
Auth	`Authorization: Bearer $HANZO_API_KEY`

Returns the caller org's prompt library as one row per prompt: its name, type, every version number it has, its taxonomy and when it last changed. The template bodies are deliberately absent — fetch one prompt to read its text.

Request

GET /v1/prompt takes no parameters and no body — the credential is the whole request.

Response

Status	Body	Meaning
`200`	prompt.promptList	ok
`default`	problem-details	refused

200 body — 7 fields.

Field	In	Type	Always	Description
`data`	body	prompt.promptMeta[]	—	Data is one row per prompt the org owns, each with its version numbers and taxonomy — never the template bodies.
`data[].labels`	body	string[]	—	Labels is the creator's free-form taxonomy, stored as given after trimming and de-duplication.
`data[].lastUpdatedAt`	body	string	—	LastUpdatedAt is when the newest version was appended, RFC 3339 UTC.
`data[].name`	body	string	—	Name is the prompt's org-unique handle and the URL segment it is fetched by: GET /v1/prompt/<name>.
`data[].tags`	body	string[]	—	Tags is the second free-form taxonomy under the same rules as Labels.
`data[].type`	body	string	—	Type labels the template's kind, "text" unless the creator said otherwise.
`data[].versions`	body	integer (int64)[]	—	Versions lists every version NUMBER this prompt has, newest first, capped at the last 100.

Failure carries the platform error shape — see Errors.

Examples

CLI

SDK

HTTP

MCP

hanzo prompt list

.ts

.py

.go

.rs

.java

import { Configuration, PromptApi } from 'hanzoai';

const api = new PromptApi(new Configuration({ accessToken: process.env.HANZO_API_KEY }));
const { data } = await api.getPrompt();

from hanzoai.cloud import ApiClient, Configuration
from hanzoai.cloud.api import PromptApi

client = ApiClient(Configuration(access_token=os.environ["HANZO_API_KEY"]))
result = PromptApi(client).get_prompt()

cfg := hanzoai.NewConfiguration()
cfg.AddDefaultHeader("Authorization", "Bearer "+os.Getenv("HANZO_API_KEY"))
client := hanzoai.NewAPIClient(cfg)

resp, _, err := client.PromptAPI.GetPrompt(context.Background()).Execute()
if err != nil {
	return err
}

use hanzo_client::apis::{configuration::Configuration, prompt_api};

let mut cfg = Configuration::new();
cfg.bearer_access_token = std::env::var("HANZO_API_KEY").ok();

let result = prompt_api::get_prompt(&cfg, Default::default()).await?;

import ai.hanzo.cloud.ApiClient;
import ai.hanzo.cloud.api.PromptApi;

ApiClient client = new ApiClient();
client.setBearerToken(System.getenv("HANZO_API_KEY"));

var result = new PromptApi(client).getPrompt();

curl https://api.hanzo.ai/v1/prompt \
  -H "Authorization: Bearer $HANZO_API_KEY"

MCP reaches prompt through the prompt tool, which names its 6 operations with its own verbs — this one among them, under a name only MCP declares. describe explains any of them:

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

Prompt API · All Hanzo APIs · Interactive reference

Was this page useful?

PreviousList metrics NextCreate prompt