How to Use the LanceDB (Serverless Vector DB) MCP in Google ADK

Q: How do I register LanceDB (Serverless Vector DB) tools in Google ADK using this MCP Server?

Initialize McpToolset with your Vinkius HTTP endpoint URL and pass it to the LlmAgent tool list. Your Gemini-powered Google ADK agent will automatically detect tools like vectorsearch and insertrows.

Q: Can my Google ADK agent limit access to specific database tools?

Yes, you can use the optional toolnames filter in the Google ADK setup to restrict access. For example, you can expose vectorsearch while blocking destructive tools like deletetable from your Google agent.

Q: How does LanceDB (Serverless Vector DB) handle large vector payloads from Google ADK?

The insertrows tool handles high-dimensional embeddings generated by Vertex AI or Gemini models. Google ADK sends these vectors over a secure HTTP transport directly to the serverless database.

Connect Gemini models to LanceDB (Serverless Vector DB) via Google ADK to query multi-modal embeddings instantly.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect LanceDB (Serverless Vector DB) MCP to Google ADK

Create your Vinkius account to connect LanceDB (Serverless Vector DB) 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 LanceDB (Serverless Vector DB) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Context-Aware Vector Queries for Google ADK

The `vector_search` tool executes fast nearest-neighbor lookups to feed high-dimensional context to your Google ADK agents. Gemini models use these search results to ground long-context reasoning with precise, real-time facts pulled directly from LanceDB. Because Gemini handles up to 1 million tokens, your Google ADK agent can pull larger result sets from `vector_search` without hitting context limits. This allows your enterprise Google ADK agents to process deep document histories alongside raw LanceDB vector distances.

On-the-Fly Table Management via Google ADK

The `create_table` tool provisions structured LanceDB vector tables directly from your Google ADK agent pipelines. This allows your agent to partition incoming data streams from BigQuery into isolated serverless vector spaces without external configuration via this MCP Server. You can monitor these tables using `list_tables` and inspect their structures with `get_table` within your Google ADK workflow. This metadata lets your Google agent verify that the vector dimensions match your Vertex AI embedding model before executing queries.

Dynamic Index Updates and Data Purging

The `insert_rows` tool adds new embeddings and metadata payloads to your active LanceDB tables. The serverless database updates its index in real-time, making new entries searchable by Google ADK agents immediately. When a temporary Google ADK pipeline finishes, the agent invokes `delete_table` to remove the LanceDB vector space. This prevents cloud storage bills from accumulating on abandoned datasets managed by your Google agent.

Setup guide

Set up LanceDB (Serverless Vector DB) 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 LanceDB (Serverless Vector DB) 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="LanceDB (Serverless Vector DB)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to LanceDB (Serverless Vector DB) 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 LanceDB. 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 LanceDB (Serverless Vector DB) 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 LanceDB (Serverless Vector DB) MCP in Google ADK

Initialize `McpToolset` with your Vinkius HTTP endpoint URL and pass it to the `LlmAgent` tool list. Your Gemini-powered Google ADK agent will automatically detect tools like `vector_search` and `insert_rows`.

Yes, you can use the optional `tool_names` filter in the Google ADK setup to restrict access. For example, you can expose `vector_search` while blocking destructive tools like `delete_table` from your Google agent.

The `insert_rows` tool handles high-dimensional embeddings generated by Vertex AI or Gemini models. Google ADK sends these vectors over a secure HTTP transport directly to the serverless database.

Yes, the serverless MCP architecture handles concurrent writes through atomic file updates. Multiple Google ADK instances can write via `insert_rows` simultaneously without corrupting the table index.

Absolutely, all LanceDB vector data and table schemas are processed in ephemeral V8 sandboxes that self-destruct after execution. Vinkius never stores your embeddings or database credentials on persistent shared disks.

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