---
title: "Langfuse integration for LuumenAI"
url: "https://www.luumen.ai/integrations/langfuse/"
entity: SoftwareIntegration
category: "Source control & CI/CD"
audience: "SRE, DevOps, platform engineering, IT operations"
---

# Langfuse integration for LuumenAI

Read traces, scores and prompts from Langfuse, then record your own scores

## What LuumenAI can do with Langfuse

LuumenAI connects to Langfuse with an API token and exposes 10 tools (9 read-only · 1 write). 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: 10 tools (9 read-only · 1 write)
- Plan: available on all plans
- Category: Source control & CI/CD

## About Langfuse with LuumenAI

Langfuse holds the traces, scores and prompts behind your LLM application. Connect it with an API key and Luumen can read that history directly in the terminal: which generations ran slow, how a prompt version is scored, what an experiment produced. When you want to record a judgment of your own, Luumen attaches a score to the trace it just showed you.

## Example tools

Read-only (9 in total):

- `LANGFUSE_GET_PROMPT` — Retrieve a Langfuse text or chat prompt by name, deployment label, or exact version, with optional dependency resolution.
- `LANGFUSE_LIST_ANNOTATION_QUEUES` — List annotation queues configured for human evaluation in the connected Langfuse project.
- `LANGFUSE_LIST_DATASET_ITEMS` — List dataset items, optionally scoped to a dataset, source trace or observation, or historical dataset version.
- `LANGFUSE_LIST_DATASETS` — List datasets available to the connected Langfuse project.
- `LANGFUSE_LIST_EXPERIMENTS` — List Langfuse experiments active in a required time range, optionally including metadata and directly attached scores.
- `LANGFUSE_LIST_MODELS` — List Langfuse-managed and project-custom model pricing definitions used for usage and cost calculation.
- `LANGFUSE_LIST_OBSERVATIONS` — Search Langfuse observations such as generations, spans, events, agents, and tool calls, selecting only the field groups needed.
- `LANGFUSE_LIST_SCORES` — Search numeric, boolean, categorical, text, and correction scores with subject and annotation context.

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

- `LANGFUSE_CREATE_SCORE` — Attach an evaluation score to exactly one Langfuse trace, session, or dataset run, optionally narrowing a trace score to an observation.

## Frequently asked questions

### How does LuumenAI connect to Langfuse?

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 Langfuse on its own?

Read actions answer immediately. Anything that writes is shown as a plan and requires approval by default. Administrators configure that per tool.

### Is there an audit trail?

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

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