MCP For Claude Marketplace
Langfuse (LLM Tracing & Evals)

Langfuse (LLM Tracing & Evals) MCP Connector for Claude

A+

Monitor LLM apps via Langfuse — track traces, manage prompt templates, and audit evaluation scores.

10 tools Official Updated Oct 1, 2026 Official Vinkius Partner
More Details Connect to Claude

Connect your Langfuse account to any AI agent and take full control of your LLM observability, prompt management, and quality evaluation through natural conversation.

What you can do

  • Trace Orchestration — List and retrieve detailed traces of LLM API sessions, exposing latencies, token counts, and exact chained payloads directly from your agent
  • Prompt Vault Access — Query actively managed prompt templates and versions to inspect system instructions and expected input variables
  • Observation Analysis — Deep-dive into individual spans, events, and generations within a trace to pinpoint failures or performance bottlenecks securely
  • Evaluation & Scoring — Attach structured human feedback or automated evaluation metrics to specific traces to monitor model grounding and accuracy
  • Usage Metrics — Generate aggregated daily reports on USD costs and average latency to track your AI infrastructure spending in real-time
  • Session Monitoring — Extract correlated user sessions to understand multi-turn interaction boundaries and improve long-term agentic workflows

How it works

  1. Subscribe to this server
  2. Enter your Langfuse API URL, Public Key, and Secret Key
  3. Start monitoring your LLM application from Claude, Cursor, or any MCP-compatible client

Who is this for?

  • LLM Engineers — debug complex AI chains and measure exact token latencies through natural conversation without manual dashboard searching
  • Product Owners — monitor daily AI costs and user satisfaction scores across multiple production environments
  • Data Scientists — manage prompt templates and audit evaluation metrics to improve model response quality and grounding efficiently
llm-tracingprompt-managementevaluation-metricstoken-trackingai-analyticsllm-ops

10 tools expose this connector's capabilities to your AI agent.

list_sessions

List high-level user session entities encapsulating multiple traces

create_observation

Create a new LLM observation (span, event, generation) inside a trace

create_score

g. 1-5 stars) or automated pipeline metrics bounding exactly onto the specified Trace or Observation. Attach human feedback or evaluation metrics to a trace/observation

get_trace

Get complete telemetry and nested graph for a single trace

list_traces

List all traces tracking LLM API sessions

get_daily_metrics

Generate rolled-up USD cost and aggregated latency statistics

list_prompts

Extract actively managed prompt templates and versions

get_observation

Retrieve explicit span or generation context within a trace

list_observations

List raw observation objects spanning across traces

list_scores

List all explicit scores mapping quality or cost algorithms

See how to talk to your AI agent using Langfuse (LLM Tracing & Evals).

List the last 5 traces in my Langfuse project

I've retrieved the latest 5 traces. Highlights include 'Email-Summarization' (Latency: 1.2s, 450 tokens), 'Chat-Interaction-987' (Latency: 2.4s, 1,200 tokens), and 'Data-Extraction-Fail' (Status: Error). Would you like to inspect the error payload for the failed trace?

Show me the instructions for the 'customer-support-v3' prompt

Retrieving 'customer-support-v3'… The system instruction is: 'You are a helpful support agent for TechCorp. Answer queries based on the provided documentation…'. It expects variables: 'customer_name' and 'query_text'. Would you like to see the previous versions?

What was our total LLM spending for today?

Your total LLM spending for today is $12.45 across 45,200 total tokens. The average latency is 1.8s. The most expensive model remains 'gpt-4-turbo' with $8.20 in costs. I can provide a breakdown by provider if needed.

Yes. Use the `list_prompts` tool to browse your managed templates. Your agent can retrieve the exact text and variables for any deployed prompt version, making it easy to audit AI logic through natural conversation.

Related Connectors

Inworld AI

Inworld AI MCP

19 tools Official

Power your AI agents with Inworld's lifelike voices, voice cloning, and advanced character orchestration routers.

A+ View details →
Token Count Estimator

Token Count Estimator MCP

3 tools Official

Deterministic LLM token estimation using character-based heuristics.

A+ View details →
JSON Schema Function Call Validator

JSON Schema Function Call Validator MCP

3 tools Official

Validates raw LLM text outputs against JSON Schemas to detect missing parameters, type mismismatches, and hallucinations.

A+ View details →
AI Memory Cost Analyzer

AI Memory Cost Analyzer MCP

4 tools Official

Estimate and optimize the economic impact of AI conversation memory architectures.

A+ View details →