How to Use the Keywords AI MCP in Google ADK

Q: How do I connect the Keywords AI MCP Server to my Google ADK agent?

You initialize the connection using McpToolset with the HTTP endpoint of the server. Your Google ADK agent immediately gains access to all 11 tools, including listmodels and getanalytics.

Q: Can Google ADK agents check LLM credit balances on Keywords AI?

Yes, your Google ADK agent can call getcredits to monitor your current financial balance. This prevents your enterprise pipelines from failing due to unpaid API invoices.

Q: How does Google ADK handle model routing with Keywords AI?

Your agent uses listmodels to check which LLMs are available through the gateway. The Google ADK agent then selects the most cost-effective model based on the live data retrieved.

Q: Can I restrict which tools my Gemini agent can access?

Yes, you can pass a specific list of tool names to the McpToolset constructor. This limits your agent to only calling read-only tools like getusagestats while blocking administrative tools.

Let your Google ADK agents monitor token costs and query LLM request logs using this 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 Keywords AI MCP to Google ADK

Create your Vinkius account to connect Keywords AI 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 Keywords AI with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Track enterprise LLM metrics inside Google ADK

`get_analytics` feeds your Google ADK agent with real-time latency and cost metrics across all active LLM deployments. This tool allows your enterprise agents to correlate their BigQuery data pipelines with live API performance. The agent also runs `get_usage_stats` to aggregate token consumption over specific timeframes. This helps you track operational costs directly within your Google Cloud console without manually compiling spreadsheets.

Inspect request history using this MCP Server

`list_requests` exposes the complete log of LLM interactions directly to your Google ADK agent. Your Gemini models can parse these logs to analyze prompt effectiveness or audit system decisions over millions of tokens. With `get_request`, your agent pulls the exact payload of a specific transaction. This is useful when debugging complex multi-turn reasoning steps that failed inside a Vertex AI pipeline.

Track team usage and active alerts

`list_alerts` lets your Google ADK agent monitor system anomalies, such as sudden spikes in error rates or latency. The agent can catch these alerts and write them to BigQuery or trigger Google Cloud Pub/Sub topics for instant remediation. You can also call `list_users` and `get_user` to monitor team activity on the gateway. This ensures your enterprise agents can verify which team members initiated specific LLM workloads.

Setup guide

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

You initialize the connection using `McpToolset` with the HTTP endpoint of the server. Your Google ADK agent immediately gains access to all 11 tools, including `list_models` and `get_analytics`.

Yes, your Google ADK agent can call `get_credits` to monitor your current financial balance. This prevents your enterprise pipelines from failing due to unpaid API invoices.

Your agent uses `list_models` to check which LLMs are available through the gateway. The Google ADK agent then selects the most cost-effective model based on the live data retrieved.

Yes, you can pass a specific list of tool names to the `McpToolset` constructor. This limits your agent to only calling read-only tools like `get_usage_stats` while blocking administrative tools.

This server runs inside an isolated, zero-trust V8 sandbox on Vinkius. Your LLM token metrics, latency logs, and gateway credentials never touch persistent storage, keeping your Google ADK workflow secure.

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