How to Configure Windsurf Supabase MCP Server
To set up a windsurf supabase mcp server, add the server entry to your editor settings. Then pass your project database credentials so the Cascade agent can query your tables. Cognition renamed Windsurf to Devin Desktop on June 2, 2026, keeping the same IDE features. Many teams start by giving the local agent the default project password to test fast. When a role is too broad, an agent prompt can change or read production rows. How the windsurf supabase mcp server workflow operates In Devin D
Kubernetes API Server Access + End-to-End Encryption: the complete guide
Architecture patterns, implementation strategies, and security best practices. Delivered to your inbox.
To set up a windsurf supabase mcp server, add the server entry to your editor settings. Then pass your project database credentials so the Cascade agent can query your tables. Cognition renamed Windsurf to Devin Desktop on June 2, 2026, keeping the same IDE features. Many teams start by giving the local agent the default project password to test fast. When a role is too broad, an agent prompt can change or read production rows.
How the windsurf supabase mcp server workflow operates
In Devin Desktop, the Cascade agent links to external tools through Model Context Protocol servers. You define these servers in the local MCP settings file on your machine. The agent can also run terminal commands on its own with user permission. Those commands run in a dedicated shell that loads your local profile and variables. When you ask the agent about your data, it calls the MCP server tool. The MCP server then opens a database session using the credentials from your local setup.
Every Supabase project starts with a default postgres role that holds admin privileges. Supabase does not grant full superuser status because that allows destructive database operations. Even so, the default postgres role has wide admin rights across your project tables. The password you set at project creation belongs to this default admin role. Supabase advises teams not to give that admin password to external tools or services. Instead, the vendor docs say you should create a separate database user for each service.
What native roles solve and where gaps remain
Creating a dedicated Postgres role for your MCP server limits what the agent can touch. You can grant read rights on specific schemas and block changes to core system tables. Supabase also provides built-in roles like anon, authenticated, and service_role for app traffic. Using a scoped database user stops the agent from running admin commands by mistake. It also lets you rotate or revoke the agent key without breaking other services.
Still, native database roles only check who logs in at the start of a session. Once the session starts, the database allows any query that matches the table grants. A read-only role can still pull raw emails, phone numbers, or card numbers into prompts. Because the local shell loads your profile variables, secret keys sit on developer laptops. Native grants cannot inspect individual SQL statements in flight or pause risky table scans. Teams need a way to check queries and rewrite matched fields in results before models read them.
Kubernetes API Server Access + End-to-End Encryption: architecture patterns and best practices
Continue reading? Get the full guide.
Free. No spam. Unsubscribe anytime.
Steps to scope your local agent database setup
Start by creating a fresh Postgres role inside your Supabase project just for coding tasks. Grant that role select permissions only on the non-sensitive tables your developer needs to inspect. Do not reuse the project creation password or the web dashboard admin role for agents. Next, place the scoped connection details into your local Devin Desktop MCP settings file. Test the setup by asking Cascade to list tables and check that restricted tables fail. Finally, review your shell profile to make sure extra admin keys are not sitting in plain text.
Add query and result controls beside Postgres
Grants and pools govern who logs into PostgreSQL. Yet every query in an open session still runs with that role's full scope. In practice, hoop.dev sits inline in the wire protocol beside your database as a sidecar for your Postgres. For every plain or prepared query an agent or human runs against production, hoop.dev decides to pass, mask, block, or escalate it for review.
When a tool or agent sends SQL, hoop.dev Postgres controls block banned statements before execution or hold risky ones for human approval via an AI Analyzer you configure. Matched sensitive columns in result rows are masked in memory before they reach the caller. Each query and decision is logged per listener, which generates evidence for SOC 2, HIPAA, and GDPR audits. View the binary on GitHub.
Frequently asked questions
Did Windsurf change its name to Devin Desktop?
Yes, Cognition announced on June 2, 2026 that Windsurf is now called Devin Desktop. It keeps the same IDE features and uses the Cascade agent for MCP servers.
Should I use the default postgres role for my MCP server?
No, the default postgres role has admin privileges across your project database. Supabase recommends creating a separate database user with narrow permissions for every external service.
Can the Cascade agent read local shell variables?
Yes, the agent runs commands in a dedicated terminal that loads your user shell profile. Any database keys stored in your shell profile are available to that terminal session.
Related guides
In this post