How to Use the Fuzzy Match Search MCP in Google ADK

Q: Can I use this to find the right Google Cloud resource from a partial name?

Absolutely. Give the fuzzymatch tool the partial name and a list of full resource names from a gcloud command. It will return the best matches, which your agent can then use to perform its next action.

Q: What happens to the BigQuery data, like customer names, that I send to Fuzzy Match Search through my Google ADK agent?

Vinkius processes your query and target strings inside a zero-trust, ephemeral environment. The data exists only in memory to calculate the match score and is immediately discarded. Nothing is written to disk or logged.

Connect Gemini to your BigQuery data, even with messy user input. Fix typos with Google ADK before they become failed queries.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Fuzzy Match Search MCP to Google ADK

Create your Vinkius account to connect Fuzzy Match Search 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 Fuzzy Match Search with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Clean Up Data Before It Hits BigQuery

Your agent needs to query BigQuery, but the user misspelled a project name. Instead of sending a bad query, your Google ADK agent first calls the `fuzzy_match` tool. It passes the user's input and a list of valid project names pulled from a config table. The tool returns the correct name, and your agent constructs a valid BigQuery SQL statement. No more `NOT_FOUND` errors from simple input mistakes. Your queries just work.

A Simple Toolset for Your Google ADK Agent

Adding typo correction to your agent is straightforward. You instantiate the `McpToolset` with this server's URL, and the `fuzzy_match` tool becomes available to your Gemini-powered agent instantly. This MCP Server handles all the matching logic, so your agent's context window stays free for complex reasoning. You can focus on your core business logic in Vertex AI, not on writing string-distance algorithms.

Disambiguate Entities in Long Conversations

Gemini's huge context window lets agents track complex, multi-turn conversations. But what happens when a user refers to 'the Anderson account' and there are three Anderson accounts in your system? Your agent can use `fuzzy_match` to compare the conversational context against the account names. It can identify the most likely match—'Anderson Inc.' vs 'J. Anderson'—based on other details mentioned, preventing it from acting on the wrong entity.

Setup guide

Set up Fuzzy Match Search 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 Fuzzy Match Search 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="Fuzzy Match Search_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Fuzzy Match Search 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 Fuzzysort Engine. 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 Fuzzy Match Search 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 Fuzzy Match Search MCP in Google ADK

It acts as a pre-processing step. Before your agent builds a SQL query, use `fuzzy_match` to correct misspelled entity names from user input, ensuring the query hits the right data in BigQuery the first time.

Absolutely. Give the `fuzzy_match` tool the partial name and a list of full resource names from a `gcloud` command. It will return the best matches, which your agent can then use to perform its next action.

No, the matching operation runs on a separate, optimized Vinkius server. Your Google Cloud resources are only involved in sending the small request and receiving the corrected string, not performing the heavy computation.

A common pattern is to run a preliminary, broader query against BigQuery to get a candidate set of strings. Then, you pass that smaller set to the `fuzzy_match` tool to pinpoint the exact match.

Vinkius processes your `query` and `target` strings inside a zero-trust, ephemeral environment. The data exists only in memory to calculate the match score and is immediately discarded. Nothing is written to disk or logged.

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