Supabase connector for AI agents

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

CALL ANY TOOL

Database ops on the Management API: projects, branches, migrations, SQL queries, edge functions, secrets, and custom domains. Each call carries the user's own OAuth token.

supabase_accept_invite_external_jit_access

Accept invite external jit access

Accept a pending invitation for just-in-time (JIT) database access on a Supabase project, activating the roles that were granted with Invite External JIT Access. Requires the project ref, the invited email address, and the invite token.

Parameters

Name

Type

Required

Description

string

Required

Email address the invite was sent to.

ref

string

Required

The 20-character project reference ID (lowercase letters only). Found in the project's Supabase dashboard URL or Settings > General.

token

string

Required

The invite token to accept.

supabase_authorize_jit_access

Authorize jit access

supabase_bulk_create_secrets

Bulk create secrets

supabase_bulk_delete_secrets

Bulk delete secrets

supabase_bulk_update_functions

Bulk update functions

supabase_cancel_project_restoration

Cancel project restoration

supabase_create_project_api_key

Create project api key

supabase_delete_login_roles

Delete login roles

supabase_diff_branch

Diff branch

supabase_get_action_run

Run get action

supabase_get_database_disk

Get database disk

supabase_get_jit_access_config

Get jit access config

supabase_get_performance_advisors

Get performance advisors

supabase_get_project

Get project

supabase_get_project_signing_key

Get project signing key

supabase_get_restore_point

Get restore point

supabase_list_action_runs

List action runs

supabase_list_jit_access

List jit access

supabase_list_project_addons

List project addons

supabase_merge_branch

Merge branch

supabase_patch_migration

Patch migration

supabase_read_only_query

Query read only

supabase_remove_project_addon

Remove project addon

supabase_remove_read_replica

Remove read replica

supabase_restart_project

Restart project

supabase_rollback_migrations

Rollback migrations

supabase_update_database_password

Update database password

supabase_update_network_restrictions

Update network restrictions

supabase_update_project_api_key

Update project api key

supabase_upsert_migration

Upsert migration

For more tools, view docs.

Build your Agent

Drop the toolkit in, point it at the user, and your agent can inspect projects and apply migrations from the first run.

import { ScalekitClient } from "@scalekit-sdk/node";
import { DynamicStructuredTool } from "@langchain/core/tools";
import { createReactAgent } from "@langchain/langgraph/prebuilt";
import { z } from "zod";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["supabase"], toolNames: ["supabase_list_projects", "supabase_run_query", "supabase_apply_migration"] },
  pageSize: 100,
});

const lcTools = tools.map((t) => new DynamicStructuredTool({
  name: t.tool.definition.name,
  description: t.tool.definition.description,
  schema: z.object({}).passthrough(),
  func: async (args) => {
    const { data } = await sk.tools.executeTool({
      toolName: t.tool.definition.name,
      identifier: "user_123",
      params: args,
    });
    return JSON.stringify(data);
  },
}));

const agent = createReactAgent({ llm, tools: lcTools });

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

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["supabase"], toolNames: ["supabase_list_projects", "supabase_run_query", "supabase_apply_migration"] },
  pageSize: 100,
});

const llmTools = tools.map((t) => ({
  type: "function",
  function: {
    name: t.tool.definition.name,
    description: t.tool.definition.description,
    parameters: t.tool.definition.input_schema,
  },
}));

const resp = await openai.responses.create({
  model: "gpt-4o", input: prompt, tools: llmTools,
});

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

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["supabase"], toolNames: ["supabase_list_projects", "supabase_run_query", "supabase_apply_migration"] },
  pageSize: 100,
});

const llmTools = tools.map((t) => ({
  name: t.tool.definition.name,
  description: t.tool.definition.description,
  input_schema: t.tool.definition.input_schema,
}));

const msg = await anthropic.messages.create({
  model: "claude-sonnet-4-6", max_tokens: 1024,
  tools: llmTools,
  messages: [{ role: "user", content: prompt }],
});

import { Agent } from "@google/adk/agents";
import {
  MCPToolset, StreamableHTTPConnectionParams,
} from "@google/adk/tools/mcp";

const toolset = new MCPToolset({
  connectionParams: new StreamableHTTPConnectionParams({
    url: "https://mcp.scalekit.com/supabase",
    headers: { Authorization: `Bearer ${userScopedToken}` },
  }),
});

const agent = new Agent({
  name: "agent", model: "gemini-2.0-flash",
  tools: await toolset.getTools(),
});

Try these prompts

Paste any prompt into your agent to start running Supabase project operations from your workflows.

Project operations

Copy the prompt

Copied

List all projects in org [org_id] with region, plan, and database size.

Copy the prompt

Copied

Create a preview branch off [project_ref] named review-1428.

Copy the prompt

Copied

Pause [project_ref] and confirm when it is fully paused.

Schema and data

Copy the prompt

Copied

Run this query on [project_ref] and summarize the result set.

Copy the prompt

Copied

Apply the pending migration to the review-1428 branch, then diff it against production.

Copy the prompt

Copied

List every table in [project_ref] with row counts.

Access and secrets

Copy the prompt

Copied

Rotate the anon API key for [project_ref] and report the new key id only.

Copy the prompt

Copied

List secrets set on [project_ref] without printing their values.

Copy the prompt

Copied

Show current network restrictions for [project_ref].

SEE HOW AUTH WORKS

Your users connect once. Their Supabase credentials stay vaulted, every call is scope-checked, and every action is logged.

Authorize

Your user connects

Supabase

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

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

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

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

See the same per-user auth pattern across other connectors.

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 workspace 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 token stored?

In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Tokens 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 on a production project?

Only the tools you expose. Migration, delete, and secret tools are separate from the read tools, so a review agent can be limited to list and query while a release agent keeps write access. Scalekit checks the scope before the Management API call, and every statement is attributed to the authorizing user.

On this page

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