How to Use the Supabase Vector MCP in LlamaIndex

Q: How does LlamaIndex best use Supabase Vector for its knowledge base?

LlamaIndex runs matchvectors when it needs to find relevant context. The tool returns data that the application then ingests and indexes, allowing you to query past API results.

Q: Can LlamaIndex perform direct database queries against Supabase Vector?

Yes, you can use querytablerows directly. This is useful for running validation checks or retrieving specific data points that need to be added to the overall knowledge index.

Q: What is the best practice for LlamaIndex to manage embeddings and Supabase Vector?

First, use listtables to confirm all necessary tables are visible. Then, write data using inserttablerows, ensuring that new vector embeddings are added before you try to search against them.

Q: Does LlamaIndex support advanced querying with Supabase Vector?

Yes, besides simple lookups, you can use querytablerows for more complex selection criteria, giving your indexed knowledge a solid relational foundation.

Build RAG apps with LlamaIndex: Index Supabase Vector data into a searchable knowledge base.

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 LlamaIndex

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Indexing search results for the LlamaIndex framework

LlamaIndex uses `match_vectors` to perform semantic searches against your live database. The output of this tool becomes part of a searchable knowledge base, which is its unique power. It lets you build RAG applications where API data from Supabase Vector gets combined with document chunks, giving answers grounded in actual records.

Reading and writing data via the MCP Server

You can use `get_table_row` to retrieve specific records by a column value. This is crucial for fetching initial context or validation points. Need to add new knowledge? Call `insert_table_rows`, passing in a JSON array of row objects that LlamaIndex can then index and query later.

Listing tables before querying with LlamaIndex

Before running any query, run `list_tables` to see what data is available on the MCP Server. This prevents errors when defining a table name for subsequent calls. After mapping out your schema, you can use `query_table_rows` to get initial structured results that feed into the indexer.

Setup guide

Set up Supabase Vector MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Supabase Vector MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Supabase Vector tools.",
)
response = await agent.run("List recent Supabase Vector data")

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 LlamaIndex

LlamaIndex runs `match_vectors` when it needs to find relevant context. The tool returns data that the application then ingests and indexes, allowing you to query past API results.

Yes, you can use `query_table_rows` directly. This is useful for running validation checks or retrieving specific data points that need to be added to the overall knowledge index.

First, use `list_tables` to confirm all necessary tables are visible. Then, write data using `insert_table_rows`, ensuring that new vector embeddings are added before you try to search against them.

The MCP Server handles structured JSON row objects and associated vector embeddings. The tool definition for `delete_table_rows` shows the ability to permanently remove these core data types.

Yes, besides simple lookups, you can use `query_table_rows` for more complex selection criteria, giving your indexed knowledge a solid relational foundation.

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