How do I find my Honeycomb API Key?

Log in to Honeycomb, go to **Team Settings**, and navigate to the **API Keys** section. You will be able to generate and copy your Team API Key from there. Ensure you also note your account's region.

Which region should I select?

If your browser URL starts with `ui.eu1.honeycomb.io`, select **EU**. Otherwise, select **US**. Using the correct region is required for the integration to connect to the right API cluster.

Can I run a query and get the data back?

Yes! Use the `run_query` tool with a valid query ID. It will return a result ID, which you can then pass to the `get_query_result` tool once the analysis is complete.

Is the integration secure for telemetry data?

Absolutely. The integration uses official Honeycomb Team API keys over HTTPS. Your credentials and queried data are encrypted and stored securely within the Vinkius Cloud infrastructure.

Honeycomb MCP Server for Google ADK 12 tools — connect in under 2 minutes

Name: Honeycomb
Availability: InStock
Author: Vinkius

google.github.io/adk-docs/tools/mcp-tools

Built by Vinkius GDPR 12 Tools SDK

Google Agent Development Kit (ADK) is Google's framework for building production AI agents. Add Honeycomb as an MCP tool provider through the Vinkius and your ADK agents can call every tool with full schema introspection.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

from google.adk.agents import Agent
from google.adk.tools.mcp_tool import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import (
    StreamableHTTPConnectionParams,
)

# Your Vinkius token — get it at cloud.vinkius.com
mcp_tools = McpToolset(
    connection_params=StreamableHTTPConnectionParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    )
)

agent = Agent(
    model="gemini-2.5-pro",
    name="honeycomb_agent",
    instruction=(
        "You help users interact with Honeycomb "
        "using 12 available tools."
    ),
    tools=[mcp_tools],
)

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Honeycomb MCP Server

Connect your Honeycomb.io observability platform to any AI agent and take full control of your telemetry data, query specifications, and incident markers through natural conversation.

Google ADK natively supports Honeycomb as an MCP tool provider — declare the Vinkius Edge URL and the framework handles discovery, validation, and execution automatically. Combine 12 tools with Gemini's long-context reasoning for complex multi-tool workflows, with production-ready session management and evaluation built in.

What you can do

Dataset Oversight — List all event sources, retrieve detailed metadata, and monitor last access times for your datasets.
Query Management — Define new query specifications and execute them to retrieve granular performance insights.
Marker Automation — Create timeline annotations (e.g., for deployments or outages) to contextualize your data visualization.
Schema Insights — List and inspect columns within specific datasets to understand your event structure.
Team Collaboration — Access shared boards and retrieve information about your Honeycomb team configuration.
Incident Analysis — Use AI to run complex queries and retrieve results for rapid troubleshooting and RCA.

The Honeycomb MCP Server exposes 12 tools through the Vinkius. Connect it to Google ADK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Honeycomb to Google ADK via MCP

Follow these steps to integrate the Honeycomb MCP Server with Google ADK.

Install Google ADK

Run pip install google-adk

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Create the agent

Save the code above and integrate into your ADK workflow

Explore tools

The agent will discover 12 tools from Honeycomb via MCP

Why Use Google ADK with the Honeycomb MCP Server

Google ADK provides unique advantages when paired with Honeycomb through the Model Context Protocol.

Google ADK natively supports MCP tool servers — declare a tool provider and the framework handles discovery, validation, and execution

Built on Gemini models, ADK provides long-context reasoning ideal for complex multi-tool workflows with Honeycomb

Production-ready features like session management, evaluation, and deployment come built-in — not bolted on

Seamless integration with Google Cloud services means you can combine Honeycomb tools with BigQuery, Vertex AI, and Cloud Functions

Honeycomb + Google ADK Use Cases

Practical scenarios where Google ADK combined with the Honeycomb MCP Server delivers measurable value.

Enterprise data agents: ADK agents query Honeycomb and cross-reference results with internal databases for comprehensive analysis

Multi-modal workflows: combine Honeycomb tool responses with Gemini's vision and language capabilities in a single agent

Automated compliance checks: schedule ADK agents to query Honeycomb regularly and flag policy violations or configuration drift

Internal tool platforms: build self-service agent platforms where teams connect their own MCP servers including Honeycomb

Honeycomb MCP Tools for Google ADK (12)

These 12 tools become available when you connect Honeycomb to Google ADK via MCP:

create_marker

Pass details as a JSON string in "body_json" (requires message). Use "__all__" for team-wide markers. Create a new marker (e.g., deploy, maintenance) on a dataset timeline

create_query_specification

Pass the specification as a JSON string in "query_json". Returns a query ID for execution. Create a new query specification for a dataset

get_dataset_details

Get metadata for a specific dataset

get_query_result

Retrieve the results of an executed query

get_team_details

Retrieve information about the Honeycomb team

list_dataset_columns

List all columns (fields) defined in a specific dataset

list_datasets

Use this to find the "slug" required for markers and queries. List all datasets in your Honeycomb team

list_honeycomb_boards

List all boards (dashboards) shared with the team

list_markers

List markers (annotations) for a dataset

list_queries

List query specifications for a specific dataset

list_triggers

List triggers (alerts) defined for a dataset

run_query

Poll for results using "get_query_result" with the returned result ID. Execute a query specification and return a result ID

Example Prompts for Honeycomb in Google ADK

Ready-to-use prompts you can give your Google ADK agent to start working with Honeycomb immediately.

"List all datasets and find one related to 'payment-gateway'."

"Create a marker on all datasets: 'Deploy v2.4.0 started'."

"Execute query ID 'q_99283' for the 'main-api' dataset."

Troubleshooting Honeycomb MCP Server with Google ADK

Common issues when connecting Honeycomb to Google ADK through the Vinkius, and how to resolve them.

McpToolset not found

Update: pip install --upgrade google-adk

Honeycomb + Google ADK FAQ

Common questions about integrating Honeycomb MCP Server with Google ADK.

How does Google ADK connect to MCP servers?

Import the MCP toolset class and pass the server URL. ADK discovers and registers all tools automatically, making them available to your agent's tool-use loop.

Can ADK agents use multiple MCP servers?

Yes. Declare multiple MCP tool providers in your agent configuration. ADK merges all tool schemas and the agent can call tools from any server in a single turn.

Which Gemini models work best with MCP tools?

Gemini 2.0 Flash and Pro models both support function calling required for MCP tools. Flash is recommended for latency-sensitive use cases, Pro for complex reasoning.