1. Conduid
  2. Blockchain
  3. LangfuseMCP
MCP server · Blockchain

LangfuseMCP

by · github.com/DrishtantKaushal/LangfuseMCP

Langfuse MCP server with built-in analytics. 34 tools — traces, observations, sessions, scores, prompts, datasets + accuracy metrics, failure detection, token percentiles, cost breakdowns, latency analysis, context breach scanning. Works with Claude Code, Cursor, Codex.

Unclaimed last commit 6 months ago ai-agentsclaude-codecursorlangfuselangfuse-mcpllm-analyticsllm-observabilitymcpmodel-context-protocoltrace-analysis
InstallView source
34Low

Scored a month ago · breakdown

About LangfuseMCP

LangfuseMCP is an MCP server published by DrishtantKaushal in the Blockchain category: langfuse MCP server with built-in analytics. 34 tools — traces, observations, sessions, scores, prompts, datasets + accuracy metrics, failure detection, token percentiles, cost breakdowns, latency analysis, context breach scanning. Works with Claude Code, Cursor, Codex.

The repository has 2 stars and 0 forks, with the last commit 6 months ago. Six months or more without a commit doesn't mean the server is broken, but check the open issues before depending on it in production.

Install

From source
git clone https://github.com/DrishtantKaushal/LangfuseMCP

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Tools (9)

aggregate_by_groupAggregate trace metrics by user group. Returns per-group: trace count, unique sessions, unique users, accuracy rate, average latency, total cost.

Parameters not published.

analyze_latencyAnalyze latency distribution at trace level and optionally per LLM generation. Identifies which model is the bottleneck.

Parameters not published.

analyze_sessionsAnalyze multi-turn session behavior. Returns session count, depth distribution (single vs multi-turn), engagement metrics, and session-level cost/latency.

Parameters not published.

compute_accuracyCompute accuracy from feedback scores. Accuracy = correct / (correct + incorrect). Supports grouping and time bucketing for trend analysis.

Parameters not published.

compute_token_percentilesCompute token usage percentiles (TP50/TP90/TP95/TP99) at trace level. Fetches generation observations for accurate per-trace token counts.

Parameters not published.

detect_context_breachesScan for traces where any single generation exceeds a token threshold. Catches context window overflow causing degraded LLM performance or silent truncation.

Parameters not published.

detect_failuresDetect LLM output quality failures using pattern matching ("unable to", "I can't", etc.) and negative feedback scores. NOT Python exceptions — use `find_exceptions` for those.

Parameters not published.

estimate_costsCompute cost breakdown using Langfuse's built-in `totalCost` field (model-aware, computed by Langfuse). Groups by user, agent, or time bucket.

Parameters not published.

score_tracesWrite scores back to Langfuse. Use after analysis to annotate traces with findings — tag failures for review, mark high-quality traces for dataset creation.

Parameters not published.

Ask AI

✦

Ask AI about LangfuseMCP

Powered by Claude · Grounded in docs

I know everything about LangfuseMCP. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

6 checks have not been run yet.

Questions

About LangfuseMCP

How do I install LangfuseMCP?

No package has been published for this server, so install it from source: clone the repository and follow its README.

Is LangfuseMCP safe to use with an AI agent?

Its trust score is 34 out of 100 (low). Conduid hasn't run static security checks on this repository yet, so review the source yourself before granting it credentials. It has no ConduID identity yet, so agent calls to it are not receipted.

Is LangfuseMCP still maintained?

The last commit was 6 months ago. That's long enough that you should check whether the maintainer is responding to issues before depending on it.