How to Use the Helicone (LLM Observability) MCP in Google ADK

Q: How do I configure the Helicone (LLM Observability) MCP Server within Google ADK?

Install google-adk and define an McpToolset pointing to your Vinkius HTTP URL. Pass this toolset directly to your LlmAgent constructor so your Gemini models can access the tools.

Q: Can my Google ADK agent query Helicone (LLM Observability) to check its own token usage?

Yes, your agent can call querycosts to retrieve real-time token spend metrics. This is especially useful for monitoring Gemini's large context windows during complex reasoning tasks.

Q: How does Helicone (LLM Observability) handle prompt versioning for Google ADK agents?

Your agents can use getpromptversions to fetch the latest prompt templates managed in Helicone. This keeps your Gemini system instructions consistent without requiring manual redeployments.

Monitor Gemini token usage and latency across your Google ADK pipelines using this dedicated MCP server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Helicone (LLM Observability) MCP to Google ADK

Create your Vinkius account to connect Helicone (LLM Observability) 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 Helicone (LLM Observability) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Track massive Gemini contexts in Google ADK

Gemini's million-token context window is powerful, but it makes cost tracking critical for Google ADK enterprise workflows. This MCP Server lets your agents call `query_costs` and `query_sessions` to monitor token usage across these massive context runs. Your agents can query Helicone metrics to see if long-context reasoning is actually driving up costs unnecessarily. This keeps your BigQuery and Vertex AI pipelines running efficiently without blowing through your budget.

Connect Google ADK with live feedback loops

Enterprise agents need constant tuning, and this integration bridges the gap between user action and prompt optimization. Your Google ADK agents can use `log_feedback` and `query_feedback` to capture user ratings and store them directly alongside execution logs. By connecting these feedback tools to your Gemini workflows, your agents can inspect `list_properties` to analyze which metadata tags correlate with high user satisfaction. This gives your platform team clear, actionable data to refine system prompts.

Diagnose latency bottlenecks in Google ADK

Enterprise pipelines involving Vertex AI and BigQuery can introduce complex latency profiles. This MCP Server enables your agents to run `query_latency` and `query_requests` to isolate delays down to the specific database query or model call. With these metrics, your Google ADK agent can dynamically decide to switch to smaller models or cached prompts when latency spikes. This ensures your user-facing tools remain highly responsive even under heavy loads.

Setup guide

Set up Helicone (LLM Observability) 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 Helicone (LLM Observability) 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="Helicone (LLM Observability)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Helicone (LLM Observability) 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 Helicone. 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 Helicone (LLM Observability) 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 Helicone (LLM Observability) MCP in Google ADK

Install `google-adk` and define an `McpToolset` pointing to your Vinkius HTTP URL. Pass this toolset directly to your `LlmAgent` constructor so your Gemini models can access the tools.

Yes, your agent can call `query_costs` to retrieve real-time token spend metrics. This is especially useful for monitoring Gemini's large context windows during complex reasoning tasks.

Your agents can use `get_prompt_versions` to fetch the latest prompt templates managed in Helicone. This keeps your Gemini system instructions consistent without requiring manual redeployments.

Yes, you can track and filter your metrics by passing session identifiers to `query_sessions`. This allows you to group latency and cost data for specific user interactions.

The server only processes metrics, latency logs, and cost metadata, keeping raw prompt text protected. All data transit occurs within Vinkius's ephemeral, zero-trust sandbox to prevent leaks.

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