---
title: "PromptHub integration for LuumenAI"
url: "https://www.luumen.ai/integrations/prompthub/"
entity: SoftwareIntegration
category: "AI & automation"
audience: "SRE, DevOps, platform engineering, IT operations"
---

# PromptHub integration for LuumenAI

Read versioned prompts from PromptHub and run a committed project on request

## What LuumenAI can do with PromptHub

LuumenAI connects to PromptHub with an API token and exposes 4 tools (3 read-only · 1 destructive). Reads answer immediately; writes are shown as a plan and require approval by default, configurable per tool by an administrator.

## Key facts

- Authentication: API token
- Tools available: 4 tools (3 read-only · 1 destructive)
- Plan: available on all plans
- Category: AI & automation

## About PromptHub with LuumenAI

Your prompts live in PromptHub with versions, branches, and model settings attached. Connect it and Luumen can tell you which projects a team owns, what the latest committed prompt and model configuration look like, and what a run actually returns. Execution is an approved step, with the generated text, token usage, cost, and timing reported back.

## Example tools

Read-only (3 in total):

- `PROMPT_HUB_GET_CURRENT_TEAM` — Return the current PromptHub team ID for the connected account.
- `PROMPT_HUB_GET_PROJECT_HEAD` — Retrieve a project's latest committed prompt and model configuration, with optional branch and variable resolution.
- `PROMPT_HUB_LIST_PROJECTS` — List projects in a PromptHub team, optionally filtered by group, model, or provider.

Write and destructive (1 in total, approval required by default):

- `PROMPT_HUB_RUN_PROJECT` — Execute a committed PromptHub project prompt with optional variables and return the generated text, usage, cost, and timing metadata.

## Frequently asked questions

### How does LuumenAI connect to PromptHub?

Authorize once with API token. Luumen lists the scopes each action needs before you approve the connection, and credentials never appear in the chat.

### Can LuumenAI change things in PromptHub on its own?

Read actions answer immediately. Anything that writes is shown as a plan and requires approval by default, including the 1 action classified as destructive. Administrators configure that per tool.

### Is there an audit trail?

Every call to PromptHub — read or write, approved or declined — is recorded with the actor, the input, and the result.

Full page: https://www.luumen.ai/integrations/prompthub/