How to Use the MongoDB Atlas Vector Search MCP in Google ADK

Q: How do I connect Google ADK to my MongoDB Atlas Vector Search instance?

Use McpToolset from the google-adk package, passing the HTTP endpoint of the server. Then, register this toolset in your LlmAgent initialization block to expose the vector search tools.

Q: Can I limit which Google ADK tools can access MongoDB Atlas Vector Search?

Yes, you can pass a specific list of tool names to the McpToolset constructor to restrict the agent to read-only operations like find and search while blocking indexing tools.

Feed high-dimensional vector search results from this MCP Server into Google ADK agents to ground reasoning with Gemini.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MongoDB Atlas Vector Search MCP to Google ADK

Create your Vinkius account to connect MongoDB Atlas Vector 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 MongoDB Atlas Vector Search with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Ground Gemini models with real-time vector search

Stop relying on static context windows when your database is constantly changing. This MCP Server gives your Google ADK agent direct access to the `search` tool, letting it run real-time similarity queries using `$vectorSearch` to pull fresh documents into Gemini's massive context window. This setup works natively with your existing Google Cloud infrastructure. You can feed raw vectors from Vertex AI or BigQuery pipelines directly into MongoDB Atlas, allowing the agent to combine cloud analytics with live vector indexing.

Manage your vector indexes directly from Google ADK

Building and maintaining search indexes shouldn't require manual database administration. This MCP utility lets your agent run `create_index` to configure vector dimensions and similarity metrics, and use `list_collections` to verify which collections are ready for query traffic. By exposing these tools to the `LlmAgent`, you can build automation scripts that monitor index performance and adjust configurations dynamically as your embedding models evolve.

Keep database collections clean and updated

Agents need a way to manage the life cycle of the documents they reason about. The server exposes the `insert` tool for adding newly generated embeddings and the `delete` tool for removing obsolete data points that might skew search results. If you need to verify specific document contents without running a full vector query, the agent can use `find` to run standard MQL queries, ensuring your data remains accurate and structured.

Setup guide

Set up MongoDB Atlas Vector 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 MongoDB Atlas Vector 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="MongoDB Atlas Vector Search_agent",
    model="gemini-2.0-flash",
    instruction="You have access to MongoDB Atlas Vector 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 MongoDB Atlas Vector Search. 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 MongoDB Atlas Vector 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 MongoDB Atlas Vector Search MCP in Google ADK

Use `McpToolset` from the `google-adk` package, passing the HTTP endpoint of the server. Then, register this toolset in your `LlmAgent` initialization block to expose the vector search tools.

Yes, you can pass a specific list of tool names to the `McpToolset` constructor to restrict the agent to read-only operations like `find` and `search` while blocking indexing tools.

The agent retrieves raw document structures and vector embeddings, which fit easily within the large context window of Gemini models, allowing the agent to reason over multiple search results simultaneously.

This integration supports both Stdio and Streamable HTTP transports, allowing you to run the MCP Server locally during development or host it securely on Vinkius for production deployments.

All query embeddings and document metadata are processed inside ephemeral, zero-trust V8 isolates. No search history or database payloads are cached on Vinkius servers, keeping your proprietary enterprise data completely isolated.

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