MCP server
Supabase MCP server
Supabase's official hosted MCP server lets AI work with your Supabase projects: tables, SQL, migrations, edge functions, branches and docs.
- Official server
- Databases
At a glance
- Maintained by
- Supabase
- Tools exposed
- 10 listed below
- Reviewed
- September 24, 2026
Why it matters
What it does and why it matters
Supabase gives many startups and product teams a Postgres database, authentication, storage and edge functions in one platform. Its official MCP server is hosted by Supabase and connects with your Supabase account through a browser sign-in. An assistant can list tables, run SQL, apply migrations, generate TypeScript types, deploy edge functions and search the Supabase docs.
For developers, that makes a coding assistant far more useful: it can check the real schema before writing code and create a branch to test a change.
Two settings make it safer. The read-only option runs queries as a read-only Postgres user, and the project option limits the server to a single project. We use both by default and keep write access for development branches, never for production data.
Use cases
Best business use cases
Schema-aware coding
Safe experiments
Type generation
Data questions
Docs lookup
Tools
Available tools
Tool names as published by the maintainer at review time. Versions change, so check the repository for the current list.
Read and write: Read and write across database, functions, branches and projects; read_only=true runs queries as a read-only Postgres user and project_ref limits it to one project.
-
list_tablesLists tables in the chosen schemas.
-
execute_sqlRuns raw SQL on the database.
-
apply_migrationApplies a SQL migration and tracks it.
-
list_migrationsLists migrations in the project.
-
get_advisorsReturns security and performance advisor notices.
-
generate_typescript_typesGenerates TypeScript types from the schema.
-
deploy_edge_functionDeploys an Edge Function.
-
search_docsSearches the Supabase documentation.
-
list_projectsLists Supabase projects on the account.
-
create_branchCreates a development branch.
Workflows
Example workflows
Add a feature with a migration
-
1
Connect the server scoped to the development project.
-
2
Ask the assistant to propose a table for the new feature.
-
3
It creates a branch and applies the migration there.
-
4
It generates updated TypeScript types.
-
5
A developer reviews and merges the change.
Product usage check
-
1
Connect in read-only mode to the production project.
-
2
Ask how many active users used a feature last week.
-
3
The assistant writes and runs the SQL.
-
4
It returns the count with the query shown.
-
5
No data is changed.
Prompts
Example prompts
“List the tables in this project and describe how they relate.”
“Create a branch and add a table for customer feedback with a migration.”
“How many users logged in during the last seven days?”
Setup
Installation and configuration
Examples for Claude Desktop and Claude Code. Replace the placeholder values with your own keys, and store secrets outside version control.
Claude Desktop: claude_desktop_config.json
{
"mcpServers": {
"supabase": {
"type": "http",
"url": "https://mcp.supabase.com/mcp"
}
}
}Claude Code: terminal
claude mcp add --scope project --transport http supabase "https://mcp.supabase.com/mcp"- Hosted server: https://mcp.supabase.com/mcp (OAuth). Optional query params: read_only=true, project_ref=<id>.
- Local server: npm: @supabase/mcp-server-supabase (mainly for self-hosted setups).
- Needs: Supabase account login via OAuth 2.1 (browser) for the hosted server; Personal access token for self-hosted or local setups.
Security
Security considerations
-
Read-only by default
Turn on the read-only option for anything touching real data.
-
One project
Scope the server to a single project.
-
Use branches
Test migrations on a branch, not on production.
-
Not for production writes
Keep write access to development projects only.
Related servers
Servers that pair well with it
PostgreSQL
Lets AI assistants explore a PostgreSQL database, run SQL in a restricted read-only mode and check query performance and database health.
GitHub
GitHub's official MCP server lets AI read repositories, search code, manage issues and pull requests and, when allowed, change files.
Vercel
Vercel's official MCP server lets AI search Vercel docs, list teams, projects and deployments, read build and runtime logs and deploy with confirmation.
Keep exploring
Solutions and services that use it
Related services
View all related services- MCP integration Connect AI assistants to your CRM, files, databases and tools through Model Context Protocol servers, with safe permissions.
- Database design Data models that stay fast and correct as your business grows, with backups and access rules in place.
- Multi-tenant architecture One product serving many customer accounts, with each account's data kept separate and secure.
- Product scaling Keep a growing product fast and stable as users, data and features increase.
- Web applications Custom browser-based software for the work your team does every day, from booking tools to operations systems.
- Dashboards and reporting Dashboards that pull numbers from the systems you already use and show what matters without a spreadsheet.
Solutions
View all solutions- Automated reporting Reports that build themselves from your systems on schedule, with a plain-language summary of what changed.
- Knowledge assistant (RAG) Ask a question in plain words and get an answer from your own documents, with links to the sources.
- Forecasting dashboards Forecast demand from your sales history and seasonality, and flag items to reorder before they run out.
- Payroll automation Turn pay rules, attendance and leave into tested software so the monthly run becomes a review and payslips go out in one batch.
- AI automation and integrations Connect the tools you already use so data moves once, correctly, and AI reads the parts that arrive as text or documents.
Industries
View all industries- SaaS and startups MVPs, subscription billing, AI features, multi-tenant platforms and scaling support for founders and product teams.
- Logistics and transportation Driver apps, order and shipment tracking, document processing and integrations for logistics and delivery companies.
- Manufacturing Quality inspection, production dashboards, quoting tools, knowledge assistants and legacy system modernization for manufacturers.
Case studies
View all case studiesGuides and articles
View all guides and articles- How to connect AI to your database safely Let staff ask questions of your data in plain English without risking production systems or sensitive records.
- PostgreSQL vs MySQL The two most popular open-source databases compared for business applications.
- How to automate reporting with AI and MCP Build reports that assemble themselves from your systems through MCP, with a written summary people can trust.
- How to set up automated reporting Replace manual weekly and monthly reports with dashboards and summaries that update themselves.
AI models
View all ai models- text-embedding-3-large OpenAI's most capable embedding model for search and retrieval, with 3,072-dimension vectors and support for English and other languages.
- text-embedding-3-small OpenAI's efficient, lowest-cost embedding model, with 1,536-dimension vectors for search, retrieval and similarity at scale.
- Cohere Embed v4 Cohere's multimodal embedding model for enterprise search, embedding text, images and mixed documents, with flexible vector sizes and long inputs.
- Voyage 4 Voyage AI's current embedding series, now part of MongoDB, with large, standard and lite models that share one embedding space.
- Embeddings Models that turn text into vectors for search, retrieval, clustering and recommendations.
Glossary terms
View all glossary terms- Database A database is an organized store of data that software can search, update and keep consistent, such as customers, orders or bookings.
- SaaS SaaS, or software as a service, is software delivered over the internet on a subscription, rather than installed and owned by each customer.
- Multi-tenant Multi-tenant describes software where one application and database serve many customers, called tenants, while keeping each customer's data separate.
- Vector database A vector database stores embeddings, lists of numbers that represent meaning, and quickly finds the ones most similar to a query.
- Backend The backend is the part of an application that runs on servers, storing data, applying business rules and serving the frontend through APIs.
- Cloud hosting Cloud hosting runs websites and applications on servers rented from a provider, which can grow or shrink with demand.
FAQ
Questions people ask us
Have a question that is not here? Ask us directly.
Yes. It is maintained and hosted by Supabase.
The hosted server uses your Supabase account through a browser sign-in. Local setups can use a personal access token.
Yes. The read-only option runs queries as a read-only Postgres user.