How to Use the Supabase Vector MCP in Google ADK

Q: How do I run a vector search with Supabase Vector and Google ADK?

Use matchvectors via the MCP toolset. You pass in your embedding array, and the agent runs the RPC function on the backend. It's built for enterprise scale.

Q: What is the best way to manage data with Supabase Vector and Google ADK?

You can use inserttablerows for bulk writes or gettablerow for single-record lookups. The agent handles these CRUD operations, ensuring your pipeline stays clean.

Q: How does Supabase Vector integrate with Google ADK?

The MCP toolset exposes the full range of tools—from listtables to vector search—directly to your Gemini-powered agents. It acts as a single, managed data source.

Q: Can Supabase Vector handle deletions with Google ADK?

Yes, the agent can invoke deletetablerows. Just be aware this is irreversible; use it only when your BigQuery integration confirms the need to remove data permanently.

Execute enterprise vector searches and data pipelines with Google ADK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Supabase Vector MCP to Google ADK

Create your Vinkius account to connect Supabase Vector to Google ADK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Supabase Vector with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Perform scalable semantic search via `match_vectors`

Your agent calls the `match_vectors` tool, executing a high-performance similarity search across Supabase Vector. This function is designed for large-scale data sets, helping you find relevance beyond simple keyword matches. It requires an embedding array and specific RPC details, making it perfect for integrating into BigQuery-backed enterprise pipelines.

Execute custom database logic with `call_postgres_function`

Need complex business logic? Use `call_postgres_function` to trigger a dedicated Postgres RPC. This lets you run stored procedures that combine vector results with relational data, all through the Google ADK. It keeps your core database operations centralized and callable by your Gemini-powered agents.

Query specific records using `query_table_rows`

The agent can read data from a target table using `query_table_rows`. You just need to specify the table name and whether you want limits or selected columns. This straightforward mechanism is excellent for validation steps, confirming that the results of your vector search are what you expected.

Setup guide

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

Use `match_vectors` via the MCP toolset. You pass in your embedding array, and the agent runs the RPC function on the backend. It's built for enterprise scale.

You can use `insert_table_rows` for bulk writes or `get_table_row` for single-record lookups. The agent handles these CRUD operations, ensuring your pipeline stays clean.

The MCP toolset exposes the full range of tools—from `list_tables` to vector search—directly to your Gemini-powered agents. It acts as a single, managed data source.

Yes, the agent can invoke `delete_table_rows`. Just be aware this is irreversible; use it only when your BigQuery integration confirms the need to remove data permanently.

Yes. You can query or manipulate multiple schemas using various tools, giving your agents visibility across the entire Supabase project structure.

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