Describe the columns of a table in the Supabase database.
AI agents call supabase_describe_table to retrieve information from Integrations MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves structural information about a database table (column definitions, types, constraints, etc.) without querying data rows, modifying data, executing arbitrary code, or deleting anything. It is a passive metadata inspection operation, making it a Read category risk with low severity.
From the tool's definition Tool name 'supabase_describe_table' and description 'Describe the columns of a table in the Supabase database' indicate a read-only query operation that retrieves schema metadata without modifying data.
Attacks that exploit this kind of access
Describe the columns of a table in the Supabase database. It is categorised as a Read tool in the Integrations MCP MCP Server, which means it retrieves data without modifying state.
Register the Integrations MCP server in PolicyLayer and add a rule for supabase_describe_table: 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 Integrations MCP. Nothing to install.
supabase_describe_table 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_describe_table 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_describe_table. 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_describe_table is provided by the Integrations MCP server (shriram-vasudevan/integrations-mcp). 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 →