How to Use the Axiom MCP in Google ADK

Q: How do I add Axiom to Google ADK?

Install google-adk via pip and configure a McpToolset pointing to your Vinkius URL. Assign that toolset to the tools array in your LlmAgent setup. The framework supports both Stdio and HTTP transports natively.

Q: Can Google ADK restrict which Axiom tools the agent uses?

You can pass a toolnames list when setting up the toolset. This prevents the Gemini model from accessing destructive actions like deletedashboard while still allowing read-only commands like listdatasets.

Q: How does Axiom work with Google ADK for alerting?

The agent uses listmonitors to check your existing alert rules. If it detects a missing threshold for a new service, it triggers createmonitor and attaches a notification channel via createnotifier.

Connect Axiom to Google ADK and let Gemini's massive context window analyze millions of log lines directly from your enterprise agent.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Axiom MCP to Google ADK

Create your Vinkius account to connect Axiom 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 Axiom with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Deep Log Analysis with Google ADK

Gemini models can hold over a million tokens in their context window. Connecting the Axiom MCP Server means your agent can pull massive blocks of telemetry using `run_query` and actually remember the entire sequence of events. It spots patterns across weeks of data that standard models forget. You initialize this by passing a `McpToolset` configured with `StreamableHttpServerParameters` to your `LlmAgent`. If you only want the agent reading data and not changing infrastructure, apply a `tool_names` filter to expose just the query tools.

Automated Telemetry Routing

Enterprise environments spin up new microservices constantly. Your Google Cloud agent can detect a new service deployment and instantly run `create_dataset` to give it a dedicated log destination. It then uses `ingest_data` to push initial validation events. If an old service gets deprecated, the agent cleans up the storage by executing `delete_dataset`. Everything stays organized without manual ticket requests.

Contextual Incident Annotations

Tracking when a deployment or outage occurred helps correlate spikes in error rates. The agent can monitor your CI/CD pipeline and fire off `create_annotation` to mark exactly when a new build went live. Engineers looking at the charts later see these markers overlaid on the metrics. If a rollback happens, the agent can call `update_annotation` to append the failure reason directly into the Axiom timeline.

Setup guide

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

Install `google-adk` via pip and configure a `McpToolset` pointing to your Vinkius URL. Assign that toolset to the `tools` array in your `LlmAgent` setup. The framework supports both Stdio and HTTP transports natively.

You can pass a `tool_names` list when setting up the toolset. This prevents the Gemini model from accessing destructive actions like `delete_dashboard` while still allowing read-only commands like `list_datasets`.

The agent uses `list_monitors` to check your existing alert rules. If it detects a missing threshold for a new service, it triggers `create_monitor` and attaches a notification channel via `create_notifier`.

Gemini understands Axiom Processing Language remarkably well. It will construct the correct syntax, pass it to `run_query`, and analyze the returned JSON against your existing BigQuery data if needed.

The MCP architecture ensures your API tokens and raw event logs never leak into public training sets. Vinkius brokers the connection through a zero-trust sandbox that requires a single endpoint token. Once the query finishes, the execution environment dissolves completely.

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