Supabase MCP for AI Agents. Query, modify, and manage your entire database from conversation.

Q: Can I use Supabase MCP to count rows in a table?

Yes, you can run dbcount to get the total number of records in any specified database table. This is useful for quick pagination checks or analytics counts.

Q: Is Supabase MCP safe for deleting data?

The tools like dbdelete and deleteauthuser are irreversible actions, so always confirm the target rows or users with your agent before authorizing deletion. The system is designed to alert you to these risks.

Q: What if I need to run a complex business process?

Use dbrpc (Remote Procedure Call). This lets your agent execute pre-compiled, complex PostgreSQL functions that handle the entire logic flow for you.

Q: Does Supabase MCP help with file management?

Yes. You can use liststoragebuckets to see all configured storage areas and liststoragefiles to inspect what files are inside them.

Supabase MCP connects your AI directly to a live PostgreSQL database instance. It lets you run complex queries, manage user accounts, and modify data structures using plain conversation. Forget writing boilerplate SQL; just tell your agent what records you need or what changes need making.

Claude

ChatGPT

Cursor

Gemini

Windsurf

VS Code

JetBrains

Vercel

See Vinkius in Action

Give Claude and any AI agent real-world access

Querying database records

Your agent can pull specific data subsets by querying any table using natural language commands.

Modifying and adding data

You instruct the AI to insert new rows or update existing information, directly altering your database state.

Executing custom backend logic

The AI can invoke complex pre-written PostgreSQL functions using specific procedures (RPCs).

Managing user authentication

You audit the system by listing all registered users or fetching detailed profiles for specific accounts.

Diagnosing file storage

The agent can list and check configurations for object storage buckets and files within them.

Ask an AI about this

Waiting for input…

AI Agent

What AI agents can do with Supabase MCP: 13 Database Tools

These tools allow your agent to perform every major database action—from reading records to running complex functions—directly from your chat interface.

Make your AI actually useful.

Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.

Start using Supabase MCP

Delete Auth User

Permanently removes an authenticated user account from the system.

Create Storage Bucket

Creates a new container in your object storage, optionally making it readable by...

Delete Storage File

Deletes specific files from a configured storage bucket using a list of paths.

Get Auth User

Retrieves detailed profile information for one specific, known authenticated user.

List Auth Users

Shows a complete list of all registered users within the Supabase Authentication...

Db Count

Counts how many rows exist in any given database table, useful for simple analytics and pagination checks.

Db Delete

Permanently removes specified rows from a database table; you must specify which rows to delete.

Db Insert

Adds one or more new records into a target database table using a JSON payload.

Db Rpc

Runs custom, pre-compiled backend functions (stored procedures) in Postgres with...

Db Select

Queries and retrieves records from any database table using advanced filtering...

Db Update

Changes existing data in a specific set of rows, requiring you to target them...

List Storage Buckets

Retrieves a list of all configured object storage containers available for use.

List Storage Files

Lists the specific files located inside a chosen storage bucket.

Security and governance baked right in.

Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.

Claude AI

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL:

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.

Start a conversation

Open a new chat. The Supabase integration is available immediately — no restart needed.

Antigravity

Configure Agent Environment

Open your Antigravity agent's workspace configuration or mcp-servers.json file.

Bind the Endpoint

Add the Vinkius endpoint URL to your agent's MCP connections list:

"mcp_servers": {
  "supabase": {
    "serverUrl": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
  }
}

Provide your secure token in place of [YOUR_TOKEN_HERE] to ensure your agent requests are authenticated.

Execute

Start your Antigravity session. The agent will autonomously discover and utilize the Supabase tools with full Vinkius guardrails applied.

VS Code Copilot

⚡

One-Click Install (Recommended)

In your Vinkius Dashboard, simply click the Add to VS Code button for this server. We'll automatically configure your local workspace.

Or configure manually

Open MCP Settings

Open VS Code, press Ctrl/Cmd + Shift + P, and search for GitHub Copilot: MCP Servers.

Add Server Config

Add the Vinkius endpoint configuration to your mcp-servers.json file:

"supabase": {
  "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
}

Ensure you replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.

LangChain

Install Dependencies

Install the LangChain MCP adapters for your environment:

pip install langchain-mcp-adapters

Connect the Server

Use the SSEClient in LangChain to connect to the Vinkius managed endpoint:

from langchain_mcp_adapters.client import SSEClient

# Connect to Vinkius
client = SSEClient(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
tools = client.get_tools()

CrewAI

Define the Tool

Load the Vinkius MCP tools into your CrewAI agents:

from crewai import Agent
from mcp_crewai import MCPTool

# Connect securely to Vinkius
vinkius_tools = MCPTool(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

# Assign to Agent
researcher = Agent(
    role='Data Researcher',
    tools=vinkius_tools.get_all()
)

Execute Task

Run your CrewAI process. The agent will autonomously route tasks to the Vinkius managed server.

Choose How to Get Started

Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.

Build Your Own

Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.

Import from OpenAPI, Swagger, or YAML specs
Create Agent Skills with progressive disclosure
Deploy to edge with MCPFusion framework
Built in DLP, auth, and compliance on each call
Real time usage dashboard and cost metering
Publish to catalog or keep private

Start building

Make Your AI Do More

Start with Supabase, then connect any of our 5,200+ other servers whenever your AI needs more. One click, no limits.

Use this MCP plus 5,200+ others, all in one place
Add new capabilities to your AI anytime you want
Connections are secured and governed automatically
Track usage and costs across all your servers
Works with Claude, ChatGPT, Cursor, and more
New servers added to the catalog weekly

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Supabase. 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.

VINKIUS INFRASTRUCTURE

Cloud Hosted

Managed infra

V8 Isolated

Sandboxed per request

Zero-Trust Proxy

No stored credentials

DLP Enforced

Policy on each call

GDPR Compliant

EU data residency

Token Compression

~60% cost reduction

Your data is protected. See how we built it.

The headache of jumping between tools just to check data Solved with Vinkius AI Gateway

Today, checking a single data point means switching tabs: you jump from the dashboard UI to the SQL client. You copy table names into your agent's prompt, then manually write `SELECT * FROM table WHERE condition = 'value'` and hit run. If you need three different tables, that's three separate copy-pasting sessions.

With this MCP connected through Vinkius, all of that stops. Your AI client handles the database interaction internally. You simply ask: "What are the top five products sold last month?". The agent executes the necessary complex query and returns the clean answer—no copy-pasting required.

Supabase MCP delivers instant, full-stack data control

Gone are the days of having to write repetitive scripts just to mock user insertions or check permissions. You can tell your agent to add a test user profile using `db_insert` and then immediately check that account's status with `get_auth_user`, all without ever opening an external terminal.

This gives you total control over your development cycle. Instead of spending time writing boilerplate code, you focus on the problem itself—and get immediate verification from the live database.

Support 24/7 support@vinkius.com ↗

Security Vinkius Trust Center ↗

SLA Service Level Agreement ↗

Report Listing Send Report ↗

postgresql

backend-as-a-service

database-management

api-generation

row-level-security

What your AI can actually do with this

Need to work with a backend without leaving your chat window? This MCP gives your AI client direct access to the full power of Supabase's database infrastructure. You operate as if you were a fully privileged administrator, bypassing normal security restrictions so your agent can run any query necessary for debugging or development.

This means you don't have to copy-paste queries into a separate SQL tool every time. Instead, you speak naturally: "Find all active users who haven't logged in this month." Your AI client handles the complex database logic and returns clean results instantly. You can check user rosters by running an account list, count records with db_count, or even change data using functions like db_insert and db_update.

When you integrate this through Vinkius, your entire team gets access to these capabilities from one spot in their preferred AI client.

Built · Hosted · Managed by Vinkius Supabase MCP - Query and Manage PostgreSQL Data via AI

Server ID 019d760e-ec68-71c0-8d3d-bf79f9b615cb

Vinkius Inspector

Compliance Grade A+

Score 100/100

Report View Report ↗

What Changes When You Connect

You instantly run complex queries that would normally require writing db_select statements. Instead of remembering syntax, you just describe the data set you need.

Need to make changes? You can use db_insert, db_update, or db_delete commands through natural language, automating tasks like adding new user records or correcting bad data entries.

The MCP lets your agent execute custom backend code using db_rpc. This means you can trigger complex business logic—like restocking inventory—without ever touching a stored procedure file.

It simplifies auditing. Use list_auth_users to instantly see who is logged in and check the status of every user account without navigating through multiple admin panels.

You get full visibility over your files and structure. By running list_storage_buckets, you can verify that all necessary object storage areas are configured before deployment.

See it in action

01 01

Auditing user access after a security incident

A DBA needs to know who accessed the system recently. They ask their agent, and it immediately runs list_auth_users to generate a clean roster of all active accounts for review.

02 02

Mocking data for front-end testing

A full-stack engineer needs 50 sample records to test a new feature. They use the MCP to execute db_select on a staging table, pulling exactly the right amount of mock data without polluting the real database.

03 03

Fixing product inventory in bulk

The operations team discovers 15 items are out of stock. They prompt their agent to trigger the db_rpc function 'restock_items' for those specific IDs, completing a critical database workflow instantly.

04 04

Checking if file uploads worked

A developer asks the MCP to list all files in the 'profiles' storage bucket. The agent uses list_storage_files and confirms that all user avatars were successfully uploaded.

The honest tradeoffs

What to watch out for, and the recommended way to handle each one.

Trying to query data without specifying filters

Avoid

The developer just asks, "Show me the products." The database returns thousands of rows, causing confusion and requiring manual filtering in a spreadsheet.

Instead

Instead, tell your agent exactly what you need. Use natural language phrasing that translates into a precise query, like 'Use db_select to find all records from the inventory table where status equals out-of-stock.' This focuses the results immediately.

Attempting irreversible changes without confirmation

Avoid

The agent deletes users after being told to clean up, but no safety check was run. The wrong accounts are gone permanently.

Instead

Always verify deletions first. Use list_auth_users and then specifically ask the agent to confirm which user IDs should be deleted before authorizing any delete_auth_user action.

Forgetting to run stored procedures when needed

Avoid

The team needs to calculate a complex metric, but they only know how to query raw data. They miss the critical step of running the pre-built calculation logic.

Instead

If a process is defined in Postgres, use db_rpc. Tell your agent to execute the specific function name with all necessary JSON arguments, guaranteeing the business logic runs correctly.

When It Fits, When It Doesn't

Use this MCP if your workflow requires executing multiple types of backend actions—querying data, modifying records, and triggering custom functions—all within a single chat session. It’s perfect for debugging environments or rapid prototyping where you need immediate feedback on database state.

Don't use it if your only goal is simple read-only reporting. If all you ever do is look at dashboards, a dedicated Business Intelligence tool is better. Also, don't rely on this for complex data modeling; the MCP executes what you tell it to run via db_select and db_rpc, but it doesn't help you design the schema itself. Use this if your pain point is execution, not design. If you only need to delete users, delete_auth_user works great, but remember that every destructive action requires careful instruction.

Questions you might have

How does Supabase MCP handle authentication? +

The MCP uses a service role key to authenticate, giving your agent full database administrator privileges. This lets it bypass normal row-level security constraints when running queries.

Can I use Supabase MCP to count rows in a table? +

Yes, you can run db_count to get the total number of records in any specified database table. This is useful for quick pagination checks or analytics counts.

Is Supabase MCP safe for deleting data? +

The tools like db_delete and delete_auth_user are irreversible actions, so always confirm the target rows or users with your agent before authorizing deletion. The system is designed to alert you to these risks.

What if I need to run a complex business process? +

Use db_rpc (Remote Procedure Call). This lets your agent execute pre-compiled, complex PostgreSQL functions that handle the entire logic flow for you.

Does Supabase MCP help with file management? +

Yes. You can use list_storage_buckets to see all configured storage areas and list_storage_files to inspect what files are inside them.

Give Claude and any AI agent real-world access

What AI agents can do with Supabase MCP: 13 Database Tools

Delete Auth User

Permanently removes an authenticated user account from the system.

Create Storage Bucket

Creates a new container in your object storage, optionally making it readable by...

Delete Storage File

Deletes specific files from a configured storage bucket using a list of paths.

Get Auth User

Retrieves detailed profile information for one specific, known authenticated user.

List Auth Users

Shows a complete list of all registered users within the Supabase Authentication...

Db Count

Counts how many rows exist in any given database table, useful for simple analytics and pagination checks.

Db Delete

Permanently removes specified rows from a database table; you must specify which rows to delete.

Db Insert

Adds one or more new records into a target database table using a JSON payload.

Db Rpc

Runs custom, pre-compiled backend functions (stored procedures) in Postgres with...

Db Select

Queries and retrieves records from any database table using advanced filtering...

Db Update

Changes existing data in a specific set of rows, requiring you to target them...

List Storage Buckets

Retrieves a list of all configured object storage containers available for use.

List Storage Files

Lists the specific files located inside a chosen storage bucket.

Security and governance baked right in.

Claude AI

Open Claude Settings

Add Custom Connector

Start a conversation

Claude Code

Open your terminal

Add the MCP Server

Start coding

Cursor

One-Click Install (Recommended)

Open Cursor Settings

Add New Server

Use in Composer

Antigravity

Configure Agent Environment

Bind the Endpoint

Execute

VS Code Copilot

One-Click Install (Recommended)

Open MCP Settings

Add Server Config

Windsurf

One-Click Install (Recommended)

Open Windsurf Settings

Add Server Endpoint

LangChain

Install Dependencies

Connect the Server

CrewAI

Define the Tool

Execute Task

Choose How to Get Started

Build Your Own

Make Your AI Do More

The headache of jumping between tools just to check data Solved with Vinkius AI Gateway

Supabase MCP delivers instant, full-stack data control

postgresql

backend-as-a-service

database-management

api-generation

row-level-security

What your AI can actually do with this

Here's how it actually works

Who is this actually for?

What Changes When You Connect

Auditing user access after a security incident

Mocking data for front-end testing

Fixing product inventory in bulk

Checking if file uploads worked

The honest tradeoffs

Trying to query data without specifying filters