Download PDFMarkdown Version
ClaudeChatGPTPerplexityGeminiMicrosoft CopilotRaycastMeta AIGrokZ.aiQwenKimi
DeepSeekMistralCursorVS CodeWindsurfJetBrainsClineLovableVercel AI SDKLangChain

Use Langfuse with your AI.

Connect your account once and let the AI you already use work with it, without building another integration. Extract trace IDs and construct observability URLs from Langfuse payloads.

Included with plan

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.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Complete set · 3 capabilities

The complete Langfuse capability set.

These are the exact actions your AI can choose when you ask it to work with Langfuse.

Capability set01 / 01

01-03

3 capabilities in this set.

Part of 3 available through Langfuse.

  1. 01

    Extract trace identifiers

    Extracts trace and project IDs from a Langfuse payload JSON

  2. 02

    Validate payload schema

    Validates if a JSON payload contains required Langfuse fields

  3. 03

    Construct langfuse URL

    Constructs a direct Langfuse trace URL

Observed, not estimated

605ms average. Fast in production.

Langfuse is checked daily against the live service.

Daily averagePeak 783ms
Aug 24Today
Fastest day
511ms
Slowest day
783ms
14-day trend
Slowing+6%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 3 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_mORUNaxsxJKt0DhLvO9C2dXdcem9Xgcsp3iXkEJx/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Langfuse capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "langfuse-trace-url-extractor-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_mORUNaxsxJKt0DhLvO9C2dXdcem9Xgcsp3iXkEJx/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

FAQ

Questions Langfuse owners ask.

  • 01

    What does extract_trace_identifiers do?

    It parses a Langfuse payload JSON to extract the root id and project_id fields.

  • 02

    How do I generate a clickable link?

    Use the construct_langfuse_url capability with the extracted trace ID and project ID.

  • 03

    Can I verify if a payload is valid before processing?

    Yes, the validate_payload_schema capability checks for the presence of required keys.

Explore

More in Developer Tools

Suggestions