How to Use the N-Gram Frequency Engine MCP in Google ADK

Q: How do I configure the N-Gram Frequency Engine within a Google ADK agent?

Instantiate McpToolset using the StreamableHttpServerParameters pointing to your server URL. Pass this toolset into your LlmAgent constructor to expose the extractngramfrequencies tool to your Gemini model.

Q: Can I restrict my Google ADK agent to only use the N-Gram Frequency Engine?

Yes, you can use the toolnames filter in your toolset configuration to expose only extractngramfrequencies. This keeps your agent focused and prevents it from invoking unnecessary tools during text analysis.

Extract exact phrase frequencies from BigQuery data using Google ADK and Gemini long-context models.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect N-Gram Frequency Engine MCP to Google ADK

Create your Vinkius account to connect N-Gram Frequency Engine 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 N-Gram Frequency Engine with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Deterministic text parsing for Google ADK agents

The `extract_ngram_frequencies` tool provides Gemini-based agents with exact phrase frequencies directly inside your Google Cloud environment. Instead of forcing your model to guess word counts over massive text fields, this tool processes the raw strings deterministically. You initialize the toolset in Python using `McpToolset` with your HTTP server parameters and pass it to your `LlmAgent`. The agent can then call the tool to extract unigrams, bigrams, and trigrams without wasting its 1M+ token context on basic counting loops.

Analyze BigQuery text exports with this MCP Server

The `extract_ngram_frequencies` tool lets your enterprise agent ingest massive text dumps from BigQuery and analyze them. The agent pulls raw strings from your cloud warehouse, runs the deterministic parser, and structures the output into clean JSON. By using this MCP Server, your Google ADK agent avoids the latency of model-based linguistic extraction. It offloads the heavy string hashing to the external engine, keeping your Vertex AI compute costs focused on high-level reasoning rather than simple counting.

Restrict agent tools to optimize execution

The `extract_ngram_frequencies` tool can be isolated using the `tool_names` filter in this MCP Server setup to prevent your agent from getting distracted by unused capabilities. This ensures the model only invokes the exact n-gram parser when analyzing linguistic data. This setup supports both Stdio and HTTP transports, making it easy to run the server as a local container or a cloud-hosted service. Your agent gets a direct pipeline to exact phrase counts, bypassing the need for heavy, third-party Python NLP libraries.

Setup guide

Set up N-Gram Frequency Engine 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 N-Gram Frequency Engine 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="N-Gram Frequency Engine_agent",
    model="gemini-2.0-flash",
    instruction="You have access to N-Gram Frequency Engine 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 natural. 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 N-Gram Frequency Engine 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 N-Gram Frequency Engine MCP in Google ADK

Instantiate `McpToolset` using the `StreamableHttpServerParameters` pointing to your server URL. Pass this toolset into your `LlmAgent` constructor to expose the `extract_ngram_frequencies` tool to your Gemini model.

Yes, you can use the `tool_names` filter in your toolset configuration to expose only `extract_ngram_frequencies`. This keeps your agent focused and prevents it from invoking unnecessary tools during text analysis.

Your agent retrieves the text from BigQuery and passes the raw string to `extract_ngram_frequencies`. The tool processes the string in-memory, returning a clean count of unigrams, bigrams, and trigrams to the agent.

Yes, this MCP Server supports both Stdio and HTTP transports. You can run the server locally as a subprocess or host it on Google Cloud Run and connect via HTTP.

All text payloads are processed ephemerally within isolated, zero-trust sandboxes. The raw text is parsed to generate the n-gram counts and is immediately discarded, ensuring your enterprise data never leaves the temporary execution context.

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