How to Use the AddSearch MCP in Google ADK

Q: How do I configure AddSearch with Google ADK?

Wrap your endpoint URL in StreamableHttpServerParameters. You then pass that into McpToolset and hand it to your LlmAgent constructor. The HTTP transport handles the connection natively.

Q: Can Google ADK agents paginate AddSearch results?

They do this using the searchpagination tool. Instead of dumping the entire database into memory, your agent requests specific chunks of results to process sequentially.

Q: How does the AddSearch MCP Server handle autocomplete?

The autosuggest tool provides direct access to type-ahead predictions. Your agent queries this endpoint to understand common search variations before committing to a full database lookup.

Q: Can I restrict which AddSearch tools Google ADK sees?

You absolutely can. Pass the toolnames filter when initializing the toolset to expose only harmless operations like listdocuments while hiding destructive ones.

Connect AddSearch to Google ADK to let your enterprise agents index documents and analyze search metrics alongside your BigQuery data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AddSearch MCP to Google ADK

Create your Vinkius account to connect AddSearch 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 AddSearch with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Deep Search for Google ADK Agents

The `search_keyword` tool feeds raw AddSearch results directly into Gemini's massive context window. Google ADK agents can ingest thousands of search hits at once and reason across the entire dataset. Filtering makes this even more precise. Your agent fires `search_filtered` to isolate specific categories, pulling only the relevant indexed content before cross-referencing it with your internal BigQuery tables.

Automated Document Indexing

Pushing new content happens through the `index_document` tool. Your Google Cloud pipelines can trigger your agent to update the search index the moment a new file hits Cloud Storage. Cleanups are handled just as easily. The agent executes `delete_document` to remove deprecated files, ensuring your search results stay accurate without manual intervention.

AddSearch MCP Server Analytics

Traffic data tells you what your users actually want. By calling `stats_queries`, your agent extracts search volume history and popular keywords straight from the source. Engagement metrics complete the picture. The `stats_clicks` tool reveals which documents get the most attention, letting your Gemini models generate insights on user behavior patterns.

Setup guide

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

Wrap your endpoint URL in `StreamableHttpServerParameters`. You then pass that into `McpToolset` and hand it to your `LlmAgent` constructor. The HTTP transport handles the connection natively.

They do this using the `search_pagination` tool. Instead of dumping the entire database into memory, your agent requests specific chunks of results to process sequentially.

The `autosuggest` tool provides direct access to type-ahead predictions. Your agent queries this endpoint to understand common search variations before committing to a full database lookup.

You absolutely can. Pass the `tool_names` filter when initializing the toolset to expose only harmless operations like `list_documents` while hiding destructive ones.

We process your indexed documents and query analytics inside a zero-trust environment. The connection requires a single endpoint token, and the execution environment vanishes immediately after your agent retrieves the data.

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