How to Use the Honeycomb MCP in Google ADK

Q: How do I configure Honeycomb with the Google ADK?

Install the google-adk package. Set up a McpToolset pointing to your MCP Server URL and pass it to your LlmAgent. You can filter tools if you only want read access.

Q: Can Gemini automatically write Honeycomb queries for me?

Yes. The agent uses listdatasetcolumns to learn your schema. Then it formats a valid JSON payload for createqueryspecification.

Q: Can I restrict which Honeycomb datasets the agent sees?

The integration itself exposes all datasets via listdatasets. You would need to use Google ADK's toolnames filter or scope your API key to limit access.

Feed your Honeycomb telemetry directly into Gemini's massive context window using the Google ADK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Honeycomb MCP to Google ADK

Create your Vinkius account to connect Honeycomb 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 Honeycomb with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Dump entire schemas into Gemini

Working with massive distributed systems means dealing with thousands of span attributes. The Google ADK agent pulls your entire environment using `list_dataset_columns` and shoves it straight into Gemini. The million-token context window swallows it whole. You stop wasting time chunking schemas. The agent grabs `list_datasets` and `get_dataset_details` in one shot. It actually understands your entire observability footprint before writing a single query.

Execute trace analysis via the MCP Server

Your agent builds the exact JSON payload needed for `create_query_specification`. It fires that off to `run_query` to start the execution engine. You get a result ID back instantly. Then it polls `get_query_result` to pull the actual telemetry. Because this runs on Google Cloud, your agent can take those query results and cross-reference them against logs you already store in BigQuery.

Track deployments and active alerts

Spikes in error rates usually tie back to a bad push. Your agent calls `list_markers` to see exactly when code went out. If it detects a new release, it can drop its own annotation using `create_marker`. It also pulls active alert configurations via `list_triggers`. This gives your agent the exact thresholds that tripped the page. You get a complete picture of the incident without leaving your cloud console.

Setup guide

Set up Honeycomb 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 Honeycomb 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="Honeycomb_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Honeycomb 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 Honeycomb. 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 Honeycomb 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 Honeycomb MCP in Google ADK

Install the `google-adk` package. Set up a `McpToolset` pointing to your MCP Server URL and pass it to your `LlmAgent`. You can filter tools if you only want read access.

Yes. The agent uses `list_dataset_columns` to learn your schema. Then it formats a valid JSON payload for `create_query_specification`.

The MCP Server separates execution from retrieval. The agent triggers `run_query` first. It then uses the returned ID to poll `get_query_result` until the data is ready.

The integration itself exposes all datasets via `list_datasets`. You would need to use Google ADK's `tool_names` filter or scope your API key to limit access.

The integration pulls raw span attributes and query aggregates into your Google Cloud environment. Vinkius handles the transport through a zero-trust architecture, so your API keys are never exposed to the LLM directly.

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