Can I perform a semantic similarity search using my agent?

Yes. Use the `vector_search` tool by providing the target Table name and a JSON array of floating-point numbers representing your query embedding. Your agent will return the k-nearest rows from LanceDB based on semantic similarity.

How do I create a new table with a specific Apache Arrow schema?

The `create_table` tool allows your agent to initialize a new columnar vector table. You just need to provide the desired Table name and a valid Apache Arrow schema mapping in JSON format defining dimensions and scalar fields.

Can my agent insert new embeddings directly into a LanceDB table?

Absolutely. Use the `insert_rows` tool to persist new data rows containing native embeddings and arbitrary JSON metadata. Your agent will handle the payload delivery, and LanceDB will automatically update its ANN index.

LanceDB (Serverless Vector DB) MCP Server for Google ADK 6 tools — connect in under 2 minutes

Name: LanceDB (Serverless Vector DB)
Availability: InStock
Author: Vinkius

google.github.io/adk-docs/tools/mcp-tools

Built by Vinkius GDPR 6 Tools SDK

Google Agent Development Kit (ADK) is Google's framework for building production AI agents. Add LanceDB (Serverless Vector DB) as an MCP tool provider through Vinkius and your ADK agents can call every tool with full schema introspection.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

from google.adk.agents import Agent
from google.adk.tools.mcp_tool import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import (
    StreamableHTTPConnectionParams,
)

# Your Vinkius token. get it at cloud.vinkius.com
mcp_tools = McpToolset(
    connection_params=StreamableHTTPConnectionParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    )
)

agent = Agent(
    model="gemini-2.5-pro",
    name="lancedb_serverless_vector_db_agent",
    instruction=(
        "You help users interact with LanceDB (Serverless Vector DB) "
        "using 6 available tools."
    ),
    tools=[mcp_tools],
)

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About LanceDB (Serverless Vector DB) MCP Server

Connect your LanceDB Cloud account to any AI agent and take full control of your serverless vector storage and RAG infrastructure through natural conversation.

Google ADK natively supports LanceDB (Serverless Vector DB) as an MCP tool provider. declare Vinkius Edge URL and the framework handles discovery, validation, and execution automatically. Combine 6 tools with Gemini's long-context reasoning for complex multi-tool workflows, with production-ready session management and evaluation built in.

What you can do

Vector Orchestration — List all vectorized tables and retrieve precise schema metadata, including tensor dimensions and vector topologies directly from your agent
Similarity Search — Execute highly-optimized KNN (K-Nearest Neighbor) lookups to retrieve semantically related rows based on embedding array similarity
Dynamic Ingestion — Insert new structured row payloads and vectors into existing tables, updating the underlying ANN index in real-time
Table Management — Provision new columnar vector tables declaring specific Apache Arrow schemas and multi-dimensional layouts required for AI workloads
Database Audit — Discover active table boundaries and verify storage configurations assigned to your serverless database instance securely
Resource Cleanup — Irreversibly delete entire vector tables to maintain a clean and optimized data environment for your AI applications

The LanceDB (Serverless Vector DB) MCP Server exposes 6 tools through the Vinkius. Connect it to Google ADK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect LanceDB (Serverless Vector DB) to Google ADK via MCP

Follow these steps to integrate the LanceDB (Serverless Vector DB) MCP Server with Google ADK.

Install Google ADK

Run pip install google-adk

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Create the agent

Save the code above and integrate into your ADK workflow

Explore tools

The agent will discover 6 tools from LanceDB (Serverless Vector DB) via MCP

Why Use Google ADK with the LanceDB (Serverless Vector DB) MCP Server

Google ADK provides unique advantages when paired with LanceDB (Serverless Vector DB) through the Model Context Protocol.

Google ADK natively supports MCP tool servers. declare a tool provider and the framework handles discovery, validation, and execution

Built on Gemini models, ADK provides long-context reasoning ideal for complex multi-tool workflows with LanceDB (Serverless Vector DB)

Production-ready features like session management, evaluation, and deployment come built-in. not bolted on

Seamless integration with Google Cloud services means you can combine LanceDB (Serverless Vector DB) tools with BigQuery, Vertex AI, and Cloud Functions

LanceDB (Serverless Vector DB) + Google ADK Use Cases

Practical scenarios where Google ADK combined with the LanceDB (Serverless Vector DB) MCP Server delivers measurable value.

Enterprise data agents: ADK agents query LanceDB (Serverless Vector DB) and cross-reference results with internal databases for comprehensive analysis

Multi-modal workflows: combine LanceDB (Serverless Vector DB) tool responses with Gemini's vision and language capabilities in a single agent

Automated compliance checks: schedule ADK agents to query LanceDB (Serverless Vector DB) regularly and flag policy violations or configuration drift

Internal tool platforms: build self-service agent platforms where teams connect their own MCP servers including LanceDB (Serverless Vector DB)

LanceDB (Serverless Vector DB) MCP Tools for Google ADK (6)

These 6 tools become available when you connect LanceDB (Serverless Vector DB) to Google ADK via MCP:

create_table

Provision a new LanceDB table with a strict schema

delete_table

Irreversibly vaporize an entire LanceDB vector table

get_table

Get precise schema and metadata for a specific LanceDB table

insert_rows

Data dynamically updates the underlying ANN index. Insert structured row payloads and vectors into a table

list_tables

List all vectorized tables residing in LanceDB

vector_search

Perform a highly-optimized KNN Vector similarity search

Example Prompts for LanceDB (Serverless Vector DB) in Google ADK

Ready-to-use prompts you can give your Google ADK agent to start working with LanceDB (Serverless Vector DB) immediately.

"List all active tables in my LanceDB instance"

"Perform a vector search in 'product_embeddings' for this vector: [0.1, 0.2, ...]"

"Show me the schema for the 'support_kb' table"

Troubleshooting LanceDB (Serverless Vector DB) MCP Server with Google ADK

Common issues when connecting LanceDB (Serverless Vector DB) to Google ADK through the Vinkius, and how to resolve them.

McpToolset not found

Update: pip install --upgrade google-adk

LanceDB (Serverless Vector DB) + Google ADK FAQ

Common questions about integrating LanceDB (Serverless Vector DB) MCP Server with Google ADK.

How does Google ADK connect to MCP servers?

Import the MCP toolset class and pass the server URL. ADK discovers and registers all tools automatically, making them available to your agent's tool-use loop.

Can ADK agents use multiple MCP servers?

Yes. Declare multiple MCP tool providers in your agent configuration. ADK merges all tool schemas and the agent can call tools from any server in a single turn.

Which Gemini models work best with MCP tools?

Gemini 2.0 Flash and Pro models both support function calling required for MCP tools. Flash is recommended for latency-sensitive use cases, Pro for complex reasoning.