How do I connect my Langfuse data to my AI client?

You subscribe to the MCP on Vinkius and enter your Langfuse API credentials. Once connected, your AI client can immediately access your Langfuse project data.

Which AI clients can use this MCP?

This MCP works with any compatible client, including Claude, Cursor, and Windsurf.

Can I see how much money I am spending on LLMs?

Yes. You can ask your agent to generate daily reports on USD costs and token usage.

Can I manage my prompt templates through this MCP?

Yes. You can list prompt templates and inspect the specific instructions and variables for different versions.

Vinkius hosts the MCP and manages your credentials securely, allowing your agent to interact with your Langfuse data via authorized API keys.

Can I see the exact system instruction for a specific prompt version?

Yes. Use the list_prompts capability 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.

How do I log human feedback for a specific trace?

Use the create_score capability by providing the Trace ID and a JSON payload defining the score name (e.g. 'user-satisfaction') and value. Your agent will attach this structured data directly to the Langfuse record.

Can my agent report on my LLM spending for the current day?

Absolutely. The get_daily_metrics capability retrieves aggregated USD costs and average latency metrics from Langfuse. Your agent can summarize these statistics to help you monitor your infrastructure budget in real-time.

An astronaut overseeing a futuristic data hub

Download PDF Markdown Version

Connect Langfuse LLM Tracing Evals to ChatGPT and Claude

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Debug traces and manage prompts through natural conversation.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 10 capabilities

We ship only the actions that matter.

Capability set01 / 03

01-04

4 capabilities in this set.

Part of 10 available through Langfuse.

01
List sessions
This capability retrieves high-level user sessions that group multiple related traces together.
02
Create observation
Use this to add a new span, event, or generation inside an existing trace.
03
Create score
This capability attaches human feedback or automated metrics to a specific trace or observation.
04
Get trace
This capability pulls the complete telemetry and nested graph for a single specific trace.

Capability set02 / 03

05-07

3 capabilities in this set.

Part of 10 available through Langfuse.

05
List traces
This capability provides a list of all traces currently tracking your LLM API sessions.
06
Get daily metrics
Use this to get rolled-up statistics for daily USD costs and aggregated latency.
07
List prompts
This capability extracts your actively managed prompt templates and their various versions.

Capability set03 / 03

08-10

3 capabilities in this set.

Part of 10 available through Langfuse.

08
Get observation
This capability retrieves the specific context for a single span or generation within a trace.
09
List observations
This capability lists raw observation objects across your different traces.
10
List scores
This capability pulls all explicit scores used for quality or cost algorithms.

Real work

What teams actually run

Debugging Failed Chains

When an agent fails, you ask for the specific trace to inspect the exact payload and error.

Prompt Iteration

Compare the instructions of different prompt versions to see how they affect output.

Budget Management

Check daily USD spending to ensure your LLM usage stays within project limits.

Performance Tuning

Analyze latency metrics to identify which parts of your LLM pipeline are slowing down.

Automate a task

Put Langfuse to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Langfuse works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

Building your own app? The connector is yours to use.

You don't need a client to put Langfuse to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

937ms average. Fast in production.

Langfuse is checked daily against the live service.

Daily averagePeak 1261ms

Oct 3Today

Fastest day: 766ms
Slowest day: 1261ms
14-day trend: Slowing+18%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 10 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Langfuse, so you can see the experience inside your AI.

It does not authenticate your account with Langfuse. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Langfuse Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_sTXOynCd5hRTA7WbjY0nBUsTjmjwRIVY989VA7VU/mcp

Claude Desktop

Follow the steps below to connect in seconds.

1In Claude Desktop, open Settings → Connectors.
2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
3Click Add and start a new chat — Langfuse capabilities are ready to use.

Configuration · claude_desktop_config.jsonCopy

{
  "mcpServers": {
    "langfuse-llm-tracing-evals-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_sTXOynCd5hRTA7WbjY0nBUsTjmjwRIVY989VA7VU/mcp"
    }
  }
}

Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Langfuse in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Langfuse owners hand off.

This MCP is built for technical teams managing production LLM applications who need immediate access to observability data.

01
LLM Engineers
They use the agent to debug complex AI chains and measure token latencies without opening a dashboard.
02
Product Owners
They monitor daily AI costs and user satisfaction scores across production environments.
03
Data Scientists
They manage prompt templates and audit evaluation metrics to improve model grounding.

FAQ

Questions Langfuse owners ask.

01
How do I connect my Langfuse data to my AI client?
You subscribe to the MCP on Vinkius and enter your Langfuse API credentials. Once connected, your AI client can immediately access your Langfuse project data.
02
Which AI clients can use this MCP?
This MCP works with any compatible client, including Claude, Cursor, and Windsurf.
03
Can I see how much money I am spending on LLMs?
Yes. You can ask your agent to generate daily reports on USD costs and token usage.
04
Can I manage my prompt templates through this MCP?
Yes. You can list prompt templates and inspect the specific instructions and variables for different versions.
05
Is my data secure?
Vinkius hosts the MCP and manages your credentials securely, allowing your agent to interact with your Langfuse data via authorized API keys.
06
Can I see the exact system instruction for a specific prompt version?
Yes. Use the list_prompts capability 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.
07
How do I log human feedback for a specific trace?
Use the create_score capability by providing the Trace ID and a JSON payload defining the score name (e.g. 'user-satisfaction') and value. Your agent will attach this structured data directly to the Langfuse record.
08
Can my agent report on my LLM spending for the current day?
Absolutely. The get_daily_metrics capability retrieves aggregated USD costs and average latency metrics from Langfuse. Your agent can summarize these statistics to help you monitor your infrastructure budget in real-time.

Explore

More in Friends

Connect Langfuse to Claude, Cursor, ChatGPT & more

Your AI does the work. We keep it safe and sound.

Each Connector runs inside its own sealed environment.

One switch stops every agent. Instantly.

Spending limits that pause instead of surprise.

We ship only the actions that matter.

01-04

List sessions

Create observation

Create score

Get trace

05-07

List traces

Get daily metrics

List prompts

08-10

Get observation

List observations

List scores

What teams actually run

Debugging Failed Chains

Prompt Iteration

Budget Management

Performance Tuning

Building your own app? The connector is yours to use.

Langfuse Connector

Claude Desktop

LLM Engineers

Product Owners

Data Scientists

How do I connect my Langfuse data to my AI client?

Which AI clients can use this MCP?

Can I see how much money I am spending on LLMs?

Can I manage my prompt templates through this MCP?

Is my data secure?

Can I see the exact system instruction for a specific prompt version?

How do I log human feedback for a specific trace?

Can my agent report on my LLM spending for the current day?

LangSmith (LLM Observability & Hub) AI Connector

Humanloop (LLM Prompt Management API) AI Connector

Prompt Template Reuse Analyzer AI Connector

Claude Prompt Caching Optimizer AI Connector

Suggestions

Datadog AI (LLM Observability) AI Connector

New Relic AI (LLM Observability) AI Connector

Prompt Token Analyzer AI Connector

Helicone (LLM Observability) AI Connector