Supabase MCP | OAuth 2.1 Supabase agent connector

Tools your DevOps agent reaches for on Supabase MCP, scoped per user.

CALL ANY TOOL

Database ops through Supabase's MCP server: run SQL, apply migrations, manage branches and edge functions, and read project logs.

supabasemcp_apply_migration

Apply migration

Applies a migration to the database. Use this when executing DDL operations. Do not hardcode references to generated IDs in data migrations.

Parameters

Name

Type

Required

Description

name

string

Required

Name for the new resource.

project_id

string

Required

Supabase project ID. Get it from list_projects.

query

string

Required

SQL query to execute against the project database.

supabasemcp_confirm_cost

Confirm cost

supabasemcp_create_branch

Create branch

supabasemcp_create_project

Create project

supabasemcp_delete_branch

Delete branch

supabasemcp_deploy_edge_function

Deploy edge function

supabasemcp_execute_sql

Execute sql

supabasemcp_generate_typescript_types

Generate typescript types

supabasemcp_get_advisors

Get advisors

supabasemcp_get_cost

Get cost

supabasemcp_get_edge_function

Get edge function

supabasemcp_get_organization

Get organization

supabasemcp_get_project

Get project

supabasemcp_get_project_url

Get project url

supabasemcp_get_publishable_keys

Get publishable keys

supabasemcp_list_branches

List branches

supabasemcp_list_edge_functions

List edge functions

supabasemcp_list_extensions

List extensions

supabasemcp_list_migrations

List migrations

supabasemcp_list_organizations

List organizations

supabasemcp_list_projects

List projects

supabasemcp_list_tables

List tables

supabasemcp_merge_branch

Merge branch

supabasemcp_pause_project

Pause project

supabasemcp_query_logs

Query logs

supabasemcp_rebase_branch

Rebase branch

supabasemcp_reset_branch

Reset branch

supabasemcp_restore_project

Restore project

supabasemcp_search_docs

Search docs

Build your Agent

Drop the toolkit in, point it at the user, and your DevOps agent can use Supabase from the first run.

import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// Supabase MCP tools, scoped to the signed-in user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["supabasemcp"], toolNames: [
    "supabasemcp_apply_migration",
    "supabasemcp_confirm_cost",
    "supabasemcp_create_branch"
  ] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Which migrations are pending on the staging branch?" }] });

import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// Supabase MCP tools, scoped to the signed-in user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["supabasemcp"], toolNames: [
    "supabasemcp_apply_migration",
    "supabasemcp_confirm_cost",
    "supabasemcp_create_branch"
  ] },
  pageSize: 100,
});

const openai = new OpenAI();
const res = await openai.responses.create({
  model: "gpt-5",
  tools: tools.map((t) => t.openai),
  input: "Which migrations are pending on the staging branch?",
});

import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// Supabase MCP tools, scoped to the signed-in user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["supabasemcp"], toolNames: [
    "supabasemcp_apply_migration",
    "supabasemcp_confirm_cost",
    "supabasemcp_create_branch"
  ] },
  pageSize: 100,
});

const anthropic = new Anthropic();
const msg = await anthropic.messages.create({
  model: "claude-opus-4-6",
  max_tokens: 1024,
  tools: tools.map((t) => t.anthropic),
  messages: [{ role: "user", content: "Which migrations are pending on the staging branch?" }],
});

import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// Supabase MCP tools, scoped to the signed-in user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["supabasemcp"], toolNames: [
    "supabasemcp_apply_migration",
    "supabasemcp_confirm_cost",
    "supabasemcp_create_branch"
  ] },
  pageSize: 100,
});

const agent = new Agent({
  name: "supabasemcp_agent",
  model: "gemini-2.5-pro",
  instruction: "Act as the DevOps agent for the signed-in user.",
  tools,
});
await agent.run("Which migrations are pending on the staging branch?");

Try these prompts

Paste any prompt into your agent to start using Supabase.

Schema work

Copy the prompt

Copied

Which migrations are pending on staging?

Copy the prompt

Copied

Show the columns on the orders table.

Copy the prompt

Copied

Draft a migration that adds an index on orders.tenant_id.

Debugging

Copy the prompt

Copied

Fetch the last 50 error log lines for the api project.

Copy the prompt

Copied

Which edge functions failed in the past hour?

Copy the prompt

Copied

Run a count of rows added to events today.

Environments

Copy the prompt

Copied

Create a preview branch for the billing rewrite.

Copy the prompt

Copied

Compare table counts between main and staging.

Copy the prompt

Copied

List the project's edge functions and their last deploy time.

SEE HOW AUTH WORKS

Users authorize Supabase once. Their credentials stay vaulted, every call is checked, and every action is logged.

Authorize

Your user connects

Supabase MCP

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

Store

Their

Supabase MCP

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

Resolve

When your agent calls a

Supabase MCP

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

Audit

Every

Supabase MCP

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

Same per-user auth pattern across other agents and MCP connectors. Working code, live demos, fork what fits.

Engineering Teams

DevOps assistant agent

Polls GitHub for failing checks and stale PRs, opens Linear issues for the ones that need work, and posts a daily digest to Slack. It acts as the engineer, not a shared service account.

Engineering Teams

Engineering standup agent

Pulls commits from GitHub and GitLab, tracks issue movement in Jira, and posts a per-engineer standup brief to Slack. Each engineer's activity is read on their own delegated OAuth.

Engineering Teams

Auto release notes agent

Reads merged GitHub PRs, groups them into structured release notes, publishes the page to Notion, and announces the release in Slack. Every call runs on the engineer's own delegated OAuth.

Engineering Teams

Slack triage

Polls Slack for new messages, classifies bugs and support requests with a LangGraph router, files GitHub issues or Zendesk tickets, and confirms in the thread.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared token looks fine in a demo. In production every call looks like a service account. Scalekit resolves the real user credential so attribution, audit, and scope stay accurate.

// shared token
audit → bot_service_account
user_filter → broken

// scalekit
audit → user_abc
scope → enforced ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Supabase today. Others tomorrow.

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does the agent access Supabase as the user or as a shared key?

As the user. Each member authorizes once and Scalekit resolves their credential at request time. Audit logs attribute every action to that user, not a shared service account.

Where is the Supabase oauth 2.1 credential stored?

In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Credentials never appear in prompts, logs, or LLM context.

Can I limit what the agent is allowed to do in Supabase?

Yes. Pass a tool name filter to listScopedTools so the DevOps agent only sees the subset you authorize. Pre-API-call scope checks block out-of-policy actions before the request reaches Supabase.

What happens when a user revokes Supabase access?

The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.

Can the agent run destructive SQL against production?

Only if you allow it. Pass a tool name filter to listScopedTools so the DevOps agent sees read and migration tools but not arbitrary SQL execution, and scope checks run before the request reaches Supabase. Read-only agents stay read-only.

On this page

Tool and actions Framework Compatibility Starter Prompt Auth Lifecycle Try Other Agents Why Scalekit