How to Use the Supabase Vector MCP in LangChain

Q: How does LangChain use Supabase Vector for its search queries?

LangChain calls the matchvectors tool when reasoning requires external data. The agent passes embeddings to this tool, which executes a Postgres RPC and returns relevant, context-grounded results.

Q: Can LangChain perform general database queries against Supabase Vector?

Yep. You can use querytablerows to run standard SQL SELECT statements on any table. This works alongside vector search, letting you combine structured data checks with semantic retrieval.

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

Start by running listtables to map out your schema. Then, use gettablerow or inserttablerows to ensure the source data—including new vector embeddings—is correctly placed before querying.

Q: Does LangChain support multi-server aggregation for Supabase Vector?

Yes. Because you're using the MultiServerMCPClient, your agent can connect to and aggregate tools from multiple MCP Servers, making it flexible for complex workflows.

Build multi-step data pipelines with LangChain: Run Supabase Vector queries directly from your agent.

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 LangChain

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Execute complex vector searches for the LangChain Agent

The `match_vectors` tool lets your agent perform semantic similarity checks. It takes an embedding array and runs a Postgres RPC, giving you back relevant data from Supabase Vector. This means your ReAct agent can decide *when* it needs to search for context rather than just making guesses. You'll build chains that dynamically query the database based on intermediate results.

Manage and read relational records via MCP Server

Need to check a specific record? Use `get_table_row` to fetch data by matching a column value. This is fast for getting targeted information without listing everything. Conversely, you can run `list_tables` first to see what's available in the project before deciding which table needs reading.

Handle full database lifecycle with LangChain

The MCP Server lets your agent write and delete data. Use `insert_table_rows` when you need to add a batch of new records, passing in a JSON array of objects. This is how you populate the source data. You can also run `delete_table_rows`. Remember this action is irreversible—it wipes out rows based on column values.

Setup guide

Set up Supabase Vector MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Supabase Vector tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "supabase-vector-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Supabase Vector transactions"
    })
    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 LangChain

LangChain calls the `match_vectors` tool when reasoning requires external data. The agent passes embeddings to this tool, which executes a Postgres RPC and returns relevant, context-grounded results.

Yep. You can use `query_table_rows` to run standard SQL SELECT statements on any table. This works alongside vector search, letting you combine structured data checks with semantic retrieval.

Start by running `list_tables` to map out your schema. Then, use `get_table_row` or `insert_table_rows` to ensure the source data—including new vector embeddings—is correctly placed before querying.

The MCP Server touches structured JSON row objects and associated vector embeddings. Always manage access tokens carefully, as the server allows reading, writing, and deleting these core data types.

Yes. Because you're using the `MultiServerMCPClient`, your agent can connect to and aggregate tools from multiple MCP Servers, making it flexible for complex workflows.

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