Discover all existing data tables with sample data and columns. Uses OpenAPI schema discovery internally, then enriches with actual table data. Categorizes tables automatically (user, content, ecommerce, etc). Only shows tables accessible via PostgREST.
AI agents call supabase_discover_tables to retrieve information from Supabase MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries database schema and sample data without any side effects. It is a read-only discovery mechanism that provides metadata and sample records. The blast radius of misuse is minimal—an AI agent could learn about database structure but cannot modify, delete, or execute operations. Classified as Read with low severity.
From the tool's definition Tool 'discovers' and 'shows' existing data tables with sample data and columns; uses OpenAPI schema discovery and retrieves actual table data for categorization. No creation, modification, deletion, or execution is performed.
Attacks that exploit this kind of access
Discover all existing data tables with sample data and columns. Uses OpenAPI schema discovery internally, then enriches with actual table data. Categorizes tables automatically (user, content, ecommerce, etc). Only shows tables accessible via PostgREST. It is categorised as a Read tool in the Supabase MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Supabase MCP Server MCP server in PolicyLayer and add a rule for supabase_discover_tables: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Supabase MCP Server. Nothing to install.
supabase_discover_tables is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the supabase_discover_tables rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for supabase_discover_tables. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
supabase_discover_tables is provided by the Supabase MCP Server MCP server (sweir1/supabase-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →