skills.rest
jurislm
jurislmOFFICIAL
Explore all skills by this author →
GitHub

langfuse

Manage Langfuse prompts, traces, observations, and scores via MCP.

Updated Feb 4, 2026
Search Tags:#mcp#observability#prompts#traces#langfuse#observations#scores
One-click install
npx skills add https://github.com/jurislm/jurislm-tools --skill langfuse-jurislm
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: langfuse
Source: https://github.com/jurislm/jurislm-tools/tree/main/plugins/jurislm-tools/skills/langfuse
Command: npx skills add https://github.com/jurislm/jurislm-tools --skill langfuse-jurislm

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Langfuse MCP provides a centralized way to manage Langfuse prompts, traces, observations, and scores, enabling product teams to coordinate versioning and observability without manual, scattered tooling.

Core Features & Use Cases

  • Prompt Management: list, get, create, and label prompts with immutable versions and production/staging workflows.
  • Traces and Observations: enumerate and inspect LLM traces and their observations for performance analysis.
  • Scoring and Sessions: create and list scores linked to traces/observations and group traces into sessions for experimentation.

Quick Start

Ask your assistant to list latest traces or create a score for a specific trace using Langfuse MCP.

Frequently Asked Questions about langfuse

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I manage Langfuse prompts and traces through MCP?▼

You can manage Langfuse prompts and traces through MCP by using the integration to list, get, create, and label prompts alongside enumerating LLM traces. This centralizes prompt versioning and observability without scattered manual tooling.

How do I score LLM traces and group them into sessions for experimentation?▼

To score LLM traces and group them into sessions, use the MCP integration to create and list scores linked to specific observations. Grouping traces into sessions enables structured experimentation across Langfuse deployments.

What environment variables do I need to configure Langfuse API access via MCP?▼

Configuring Langfuse API access via MCP requires the environment variables LANGFUSE_PUBLIC_KEY and LANGFUSE_SECRET_KEY, with an optional LANGFUSE_HOST variable to target specific deployments.

Can I create immutable prompt versions and label staging or production workflows in Langfuse?▼

Yes, you can create immutable prompt versions and label staging or production workflows in Langfuse. The MCP integration supports prompt management with versioning to coordinate releases across product teams.

What is the best way to inspect LLM traces and observations for performance analysis?▼

The best way to inspect LLM traces and observations for performance analysis is using the MCP integration to enumerate and inspect trace data. This provides a centralized view of LLM performance metrics across deployments.

Does Langfuse MCP work without any external package dependencies?▼

No, Langfuse MCP relies on the @jurislm/langfuse-mcp package to function. You must install this package and configure the required environment variables to manage prompts, traces, observations, and scores.

Related Skills

Explore More Software Engineering Skills→
Danik911Danik911
1

langfuse-extraction

Extracts Langfuse Cloud API traces, observations, and metrics for debugging, telemetry analysis, and audit trails.

Community
Advanced
seldoseldo
5

arize-trace

Export and analyze Arize traces and spans for LLM application debugging.

Community
Advanced
zhangziliang04zhangziliang04
2

oracle

Coordinate prompts, file context, and session state via the oracle CLI.

Community
Intermediate
AesopScottAesopScott
1

observe-agent-fuse

Execute a MAPS Phase 7 observation plan using Langfuse traces, sessions, and scores.

Community
Advanced