How to Use the Supabase Vector MCP in AutoGen

Q: How does AutoGen handle Supabase Vector search queries?

AutoGen passes embeddings to the matchvectors tool, which runs a Postgres RPC. The agents then use this returned data as evidence during their deliberation process.

Q: Can AutoGen perform complex database operations with Supabase Vector?

Absolutely. Agents can call querytablerows to get structured results, and they'll debate whether those results confirm or contradict the semantic search findings from matchvectors.

Q: What is the best way for AutoGen to manage embeddings and Supabase Vector?

It’s best to first call listtables to establish context. Then, use inserttablerows when a key piece of information emerges from the debate that needs permanent recording.

Build debate-driven systems with AutoGen: Let multiple agents negotiate Supabase Vector actions.

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 AutoGen

Create your Vinkius account to connect Supabase Vector to AutoGen — 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent data sourcing for the MCP Server

Agents use `match_vectors` to independently search different parts of your database. This tool executes a Postgres RPC, giving each agent relevant context from Supabase Vector. The agents then debate which result set is most accurate or necessary, converging on a single decision based on the evidence retrieved.

Managing state using Supabase Vector tools

Need to persist data during a multi-agent discussion? Use `get_table_row` to check existing records. This ensures agents don't repeat work or act on stale information. If the debate concludes with new facts, use `insert_table_rows` to record the final consensus into the database.

Schema inspection and cleanup via MCP Server

Before any agent starts debating, it should run `list_tables`. This gives all participating agents a unified view of your project's schema. It prevents them from making assumptions about table names. If the conversation requires data deletion, the `delete_table_rows` tool handles that cleanup after consensus is reached.

Setup guide

Set up Supabase Vector MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Supabase Vector tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Supabase Vector_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Supabase Vector data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Supabase Vector_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Supabase Vector data")
    print(result.messages[-1].content)

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 AutoGen

AutoGen passes embeddings to the `match_vectors` tool, which runs a Postgres RPC. The agents then use this returned data as evidence during their deliberation process.

Absolutely. Agents can call `query_table_rows` to get structured results, and they'll debate whether those results confirm or contradict the semantic search findings from `match_vectors`.

It’s best to first call `list_tables` to establish context. Then, use `insert_table_rows` when a key piece of information emerges from the debate that needs permanent recording.

The MCP Server touches structured JSON row objects and associated vector embeddings. Because multiple agents are involved, reviewing the input parameters for `delete_table_rows` is critical to prevent accidental data loss.

The server manages the underlying connection. For moderate scale, running operations like `match_vectors` remains straightforward through the standard MCP Server endpoint.

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