How to Use the Langfuse (LLM Tracing & Evals) MCP in Google ADK

Q: How do I configure Langfuse (LLM Tracing & Evals) with Google ADK?

Run pip install google-adk and initialize an McpToolset using StreamableHttpServerParameters. Pass this MCP toolset to your LlmAgent constructor. You can use the toolnames filter to expose only specific endpoints.

Q: Can my agent track costs with Langfuse (LLM Tracing & Evals)?

Yes. The getdailymetrics tool returns rolled-up USD costs and latency stats. Your agent can read this data to monitor its own cloud consumption.

Q: How does Google ADK handle Langfuse (LLM Tracing & Evals) user sessions?

The framework calls listsessions to group multiple traces under a single user entity. This helps you track long-running interactions across different enterprise applications.

Q: Can I log custom evaluation scores through the MCP Server?

The createscore tool handles this. Your agent can evaluate its own SQL generation and attach a quality metric to the trace.

Feed Langfuse (LLM Tracing & Evals) telemetry into your Google ADK pipelines using this MCP Server to analyze enterprise agent performance.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Langfuse (LLM Tracing & Evals) MCP to Google ADK

Create your Vinkius account to connect Langfuse (LLM Tracing & Evals) to Google ADK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Langfuse (LLM Tracing & Evals) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze Execution Traces

`get_trace` and `list_traces` extract complex interaction logs for your long-context models. Agents running on enterprise cloud infrastructure generate massive context windows. Pulling this telemetry allows your system to understand exactly how those millions of tokens were processed. Enterprise workloads demand deep visibility. You can cross-reference these traces with data stored in your data warehouse. The agent uses this historical context to refine its future queries against your corporate datasets.

Manage Prompt Versions via Google ADK

`list_prompts` extracts your actively managed templates directly into the agent runtime. Hardcoding prompts into cloud deployments creates maintenance nightmares. Fetching them dynamically via the MCP Server ensures your models always use the latest approved instructions. Version control is handled upstream. Your agent simply asks for the current template and executes. This separation of concerns keeps your Python codebase strictly focused on orchestration.

Record and Retrieve Observations

`create_observation` logs a new span or event inside an existing trace. When your agent executes a complex SQL query, it records the exact string and latency. You can then pull that specific context later using `get_observation`. Granular logging prevents blind spots in your architecture. If an API call fails, the exact generation context is preserved. Your team spends less time guessing why an agent hallucinated and more time fixing the root cause.

Setup guide

Set up Langfuse (LLM Tracing & Evals) MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Langfuse (LLM Tracing & Evals) tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Langfuse (LLM Tracing & Evals)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Langfuse (LLM Tracing & Evals) tools via MCP.",
    tools=mcp_tools,
)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Langfuse. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Langfuse (LLM Tracing & Evals) now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Langfuse (LLM Tracing & Evals) MCP in Google ADK

Run `pip install google-adk` and initialize an `McpToolset` using `StreamableHttpServerParameters`. Pass this MCP toolset to your `LlmAgent` constructor. You can use the `tool_names` filter to expose only specific endpoints.

Yes. The `get_daily_metrics` tool returns rolled-up USD costs and latency stats. Your agent can read this data to monitor its own cloud consumption.

The framework calls `list_sessions` to group multiple traces under a single user entity. This helps you track long-running interactions across different enterprise applications.

The `create_score` tool handles this. Your agent can evaluate its own SQL generation and attach a quality metric to the trace.

Vinkius manages this MCP integration inside an ephemeral sandbox. Your prompt templates, generation texts, and evaluation metrics are never stored at rest by the connector. The zero-trust architecture relies entirely on your endpoint token.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript