// MCP TOOL REFERENCE

POSTGREST TOOLS

10 tools from the Postgrest MCP Server, categorised by risk level.

View the Postgrest policy → Token cost: 1,730 tokens →

// ALL 10 POSTGREST TOOLS

READ 5 tools

Read pg_call_function Call a PostgreSQL function/procedure via RPC. Use POST (default) for volatile functions, GET for immutable/... Read pg_count_records Count records in a table/view matching optional filters. Returns count using exact (precise but slower), pl... Read pg_describe_table Get detailed column information for a table/view — column names, types, formats, required fields, defaults,... Read pg_get_schema Get the PostgREST OpenAPI schema — lists all available tables, views, functions, and their columns/types. U... Read pg_list_records List records from a table/view with filtering, column selection, ordering, and pagination. Filter syntax (...

WRITE 4 tools

Write pg_insert_records Insert one or more records into a table. Pass a single object or array of objects. Use return="representati... Write pg_replace_record Full replace (PUT) a single record matching a filter. All columns must be specified including the primary k... Write pg_update_records Update records matching a filter. IMPORTANT: filter is required to prevent accidental full-table updates. U... Write pg_upsert_records Insert or update records (upsert). Uses "merge-duplicates" (update existing) or "ignore-duplicates" (skip e...

DESTRUCTIVE 1 tools

Destructive pg_delete_records Delete records matching a filter. IMPORTANT: filter is required to prevent accidental full-table deletion. ...

// RUNNING THIS SERVER

The managed route: connect Postgrest through the PolicyLayer gateway — every tool call above is checked against your policy before it runs, with a full audit log.

DIRECT INSTALL (UNMANAGED) npx -y @supabase/mcp-server-postgrest

// FAQ

How many tools does the Postgrest MCP server have? +

The Postgrest MCP server exposes 10 tools across 3 categories: Read, Write, Destructive.

How do I enforce policies on Postgrest tools? +

Route the Postgrest server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard — they are enforced on every call before it reaches the server.

What risk categories do Postgrest tools fall into? +

Postgrest tools are categorised as Read (5), Write (4), Destructive (1). Each category has a recommended default policy.

Let agents act without letting them run wild.

Route your MCP servers through PolicyLayer and every tool call is checked against your policy before it runs — allow, deny, or require approval. Per-identity grants. Full audit log. Live in minutes.

SECURE YOUR MCP →

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.