Supabase announced new tools for coding agents to diagnose and fix production problems, and new controls to manage agent permissions. These tools provide agents with raw access to project logs via SQL, more advisor checks, and autonomy to test fixes in their own environment.
Key facts
| Fact | Detail | The source says |
|---|---|---|
| New MCP tool | gives agents raw access to project logs via SQL | “We’ve introduced a new MCP tool that gives your agents raw access to your project logs via SQL, which enables more in-depth and precise…” |
| More advisor checks | help agents monitor common signals | “a living document of common health, security, performance, and resource signals your agent should watch for and how to monitor those…” |
| Autonomy | allows agents to test fixes in their own environment | “This is an important upgrade for the observing → detection → resolving loop: it lets agents test and validate proposed fixes in their own…” |
What happened
Today at Supabase Select, the company announced new tools for coding agents to diagnose and fix production problems, and new controls to manage agent permissions. Previously, agents were limited in what logs they could access via the MCP. Supabase has introduced a new MCP tool that gives agents raw access to project logs via SQL, enabling more in-depth and precise investigations. Additionally, Supabase has added more advisor checks to help agents monitor common health, security, performance, and resource signals. The company also announced improvements to how Supabase projects are expressed as code, allowing agents to test and validate proposed fixes in their own environment before opening a PR.
In the Fathom Layer index
- Supabase — Developer Tools
FAQ
What new MCP tool does Supabase offer?
Supabase offers a new MCP tool that gives agents raw access to project logs via SQL.
What are more advisor checks?
More advisor checks are a living document of common health, security, performance, and resource signals your agent should watch for and how to monitor those signals.
How does autonomy work for agents?
Autonomy allows agents to test and validate proposed fixes in their own environment before opening a PR.
Source: Supabase