How to Use the AI Token Counter MCP in Google ADK

Control long-context reasoning with the AI Token Counter MCP for Google ADK. Optimize your enterprise agent infrastructure today.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AI Token Counter MCP to Google ADK

Create your Vinkius account to connect AI Token Counter 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 AI Token Counter with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Accurate context window monitoring

Your Google ADK agent tracks input size with the `count_tokens` tool. This provides a reliable metric to manage large data feeds from BigQuery. Precise counting ensures you stay within the model limits during complex reasoning tasks. It eliminates the risk of silent failures when processing massive documents.

Automated pipeline optimization

Build logic that adjusts your agent strategy based on real-time token counts. You can use the output to decide if a query needs summarization before processing. This keeps your agent pipelines efficient and predictable. It turns variable context sizes into a managed, observable metric.

Enterprise-ready token telemetry

Get clear visibility into how your agents consume resources. Every call via the MCP produces a signed audit trail for your records. This provides the technical oversight required for enterprise deployments. You see exactly what your agent is doing and how it handles data.

Setup guide

Set up AI Token Counter 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 AI Token Counter 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="AI Token Counter_agent",
    model="gemini-2.0-flash",
    instruction="You have access to AI Token Counter 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 GPT Tokenizer. 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.