Make your AI work with Supabase Vector
Connect your account once and let the AI you already use work with it, without building another integration or switching to a different AI. Manage pgvector embeddings and relational data through a conversational interface.
7 live capabilities. One account. Your AI. Real work.
- Step 01
Connect
Link your account through Vinkius.
- Step 02
Authorize
You decide what your AI can access.
- Step 03
Pick your AI
Use it with the AI application you already use.
- Step 04
Get things done
Ask your AI to work with your connected account.
-
Works with
-
Waiting for input…
Why people use Supabase Vector
Supabase Vector for pgvector Semantic Search
This Connector puts your entire Supabase Vector instance into the hands of your AI client. You can ask your agent to list your tables, query specific rows, or run similarity searches just by describing what you want to find. It turns a multi-step database management workflow into a single conversation, giving you a much faster way to iterate on your RAG stack.
What Vinkius changes
That you get a conversational interface for your entire Supabase Vector database.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 7,800+ Connectors
- Real-world use case 01
Debugging RAG
An engineer asks the agent to find the top 3 matches for a query and then uses call_postgres_function to trigger a review.
- Real-world use case 02
Data Cleanup
A developer tells the agent to find all rows in 'test_embeddings' and use delete_table_rows to clear out the junk.
- Real-world use case 03
Schema Exploration
A new team member asks the agent to list all tables and then query the 'documents' table to see the current structure.
Complete set · 7capabilities
The complete Supabase Vector capability set.
These are the exact actions your AI can choose when you ask it to work with Supabase Vector.
01—04
4 capabilities in this set.
Part of 7 available through Supabase Vector.
- 01 Capability
Get table row
Fetches a single row from a table when you provide a specific column value.
- 02 Capability
Insert table rows
Adds new data to a table using a JSON array of objects.
- 03 Capability
List tables
Shows a list of all available tables in your Supabase project.
- 04 Capability
Match vectors
Runs a similarity search using a vector RPC and an embedding array.
05—07
3 capabilities in this set.
Part of 7 available through Supabase Vector.
- 05 Capability
Query table rows
Pulls rows from a table with optional filters or limits.
- 06 Capability
Call postgres function
Executes a custom Postgres RPC function with your specific parameters.
- 07 Capability
Delete table rows
Removes specific rows from a table based on a column value.
Where the request belongs
Work Supabase Vector can move forward.
This is for the engineer who is tired of copy-pasting IDs between a spreadsheet and a SQL console, or the data scientist who needs to see if their embeddings actually make sense without building a full frontend.
AI Engineer
Testing embedding models and RAG accuracy without leaving the chat window.
Database Administrator
Managing schema changes and data integrity for vector-enabled apps.
Backend Developer
Quickly debugging production data and verifying RPC functions.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse Connectorspgvector (Vector Database)
Run vector similarity searches, manage embedding tables, and build AI-powered retrieval pipelines. all directly inside your existing PostgreSQL database.
MongoDB Atlas Vector Search
Manage vector storage via MongoDB Atlas. perform similarity searches, query MQL documents, and audit collections.
Baserow
Build no-code databases, create custom views, and collaborate on structured data with an open-source Airtable alternative.
Vertex AI Vector Search
Bring Google's massive vector matching power to your AI agent. Search billions of semantic embeddings and administer Vertex Index endpoints directly in chat.
LanceDB (Serverless Vector DB)
Manage vectorized data via LanceDB. perform similarity searches, create tables, and manage multi-modal embeddings.
DataStax Astra DB Vector
Manage Astra DB collections, documents, and perform vector similarity searches via DataStax directly from your AI agent.
Bring your own AI
Change the model, client or framework. Keep Supabase Vector connected.
-
Claude -
ChatGPT -
Gemini -
Cursor -
VS Code -
Windsurf -
ZCode -
Cline -
Zed -
Continue -
Kiro -
Roo Code -
Zencoder -
Goose -
Void -
Augment Code -
Amp -
Qodo -
Tabnine -
Pieces -
Sourcegraph Cody -
JetBrains -
Warp -
Amazon Q -
Antigravity -
BoltAI -
Raycast -
Jan -
LM Studio -
AnythingLLM -
Open WebUI -
Msty -
Cherry Studio -
LibreChat -
TypingMind -
Chorus -
5ire -
n8n -
LangChain -
LlamaIndex -
CrewAI -
Vercel AI SDK
Before you connect
Questions about Supabase Vector.
The practical details behind the request, access and result.
Can the Supabase Vector MCP help me build a RAG system?
Yes, it connects your AI client directly to your vector database, making it easy to perform similarity searches and retrieve relevant context for your agent.
Does the Supabase Vector MCP allow me to delete data?
It can delete specific rows from your tables based on a value you provide, which is great for cleaning up test data or removing old records.
Can I run my own custom functions with the Supabase Vector MCP?
Yes, you can call any Postgres RPC functions you've already configured in your Supabase backend directly through your AI client.
Is this Connector only for vector searches?
No, while it's great for pgvector similarity searches, it also lets your agent perform standard relational queries and manage your regular database tables.
Do I need to know SQL to use the Supabase Vector MCP?
You don't need to write SQL; you just tell your AI client what you want to do in plain English, and it uses the Connector capabilities to execute the commands.
How does the Supabase Vector MCP handle my database security?
It uses your service role key to operate as an administrator, so it can bypass row-level security to perform the actions you request.
Are embedding arrays processed efficiently during intensive vector similarity matching?
The integration specifically manages large semantic arrays seamlessly by calling lightweight Postgres RPC configurations locally natively internally securely.
How is risk managed securely when manipulating and clearing root analytical vectors?
Executing delete_table_rows operates systematically relying inherently on exactly structured string conditions implicitly naturally precisely eliminating ambiguity securely effectively actively strictly smoothly securely precisely correctly reliably locally dynamically successfully effortlessly intelligently gracefully elegantly safely accurately directly comprehensively natively.
Which distance metrics does the vector search support?
pgvector supports cosine similarity, inner product, and L2 (Euclidean) distance. The metric used depends on how your RPC function and index are configured in PostgreSQL. the AI passes arguments accordingly.
One connection away
Give your agent a direct line to Supabase Vector.
Connect Supabase Vector once. Keep it beside 7,800+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available