Skip to main content
Glama
Sign In
MCPg - Production-grade PostgreSQL MCP Server

MCPg - Production-grade PostgreSQL MCP Server

by devopam
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

Generate Drizzle schema

generate_drizzle_schema
Read-only

Convert a PostgreSQL schema into a Drizzle ORM TypeScript schema string, covering tables, columns, keys, indexes, defaults, and enums for ORM setup.

Instructions

Read a PostgreSQL schema and emit a Drizzle ORM TypeScript schema string (drizzle-orm/pg-core). Covers tables, columns with PG-native types, primary/foreign keys, unique constraints, indexes, defaults, and enums. Single-column FKs emit column-level .references(); composite FKs are a documented v1 gap. Views, foreign tables, partitions, triggers, and functions are out of scope. Returns the rendered TypeScript schema.ts source as a single string. Schema/table/column names must be plain identifiers ([A-Za-z_][A-Za-z0-9_]*); delimited names (hyphens, spaces, mixed-case-only) are not supported here because they become source identifiers in generated code — use SQL tools (export_table, dump_database) for those objects. See docs/identifier-policy.md.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "schema": "<schema>"
    },
    "name": "generate_drizzle_schema"
  }
}

Input Schema

NameRequiredDescriptionDefault
schemaYes
databaseNoOptional: a database id from list_databases, to target a configured secondary (read-only) database; omit for the primary. Database names that are not configured ids are rejected.

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.8.4
    • changedInput schema / properties / database / description
      Previous value: -"Optional: target a configured secondary (read-only) database by name; omit for the primary. Call list_databases to see the configured ids."New value: +"Optional: a database id from list_databases, to target a configured secondary (read-only) database; omit for the primary. Database names that are not configured ids are rejected."
  2. First observedv0.6.8

TDQS

A4.3/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered; the description still adds genuinely new behavioral facts — that a single rendered `schema.ts` string is returned, that composite FKs are an acknowledged limitation, and that identifier restrictions stem from generated source code being identifiers. It stops short of saying anything about size/limits of the emitted output for very large schemas.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core action and output format, then limitations, then the name restriction with alternatives — a logical order with no filler. The trailing doc pointer is acceptable but the identifier-policy rationale is stated twice (rule plus 'because they become source identifiers'), slightly over-explained.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers the reading scope, the emitted artifact, the unsupported object classes, the v1 FK gap, and the identifier constraint — more than enough for a read-only generator; the output schema also carries the return type. The one omission is clarifying the `schema` argument's meaning, which matters for a tool whose whole input is a schema name.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 50%: `database` is already fully documented in the schema (including the list_databases id constraint), and the description adds nothing to it. The required `schema` parameter is only implicitly characterized by 'Read a PostgreSQL schema', leaving whether it is a single namespace name unstated in the description. Baseline 3 for a half-covered two-parameter tool with partial compensation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Specific verb+resource: 'Read a PostgreSQL schema and emit a Drizzle ORM TypeScript schema string (drizzle-orm/pg-core)', then enumerates exactly what constructs are covered (tables, columns, PK/FK, unique, indexes, defaults, enums). This clearly separates it from siblings like generate_prisma_schema, generate_diesel_schema, or the plain SQL DDL tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit when-not guidance: views, foreign tables, partitions, triggers, and functions are out of scope, and objects with delimited names should go to SQL tools (`export_table`, `dump_database`). It also flags the composite-FK v1 gap up front so an agent knows when the output will be incomplete rather than discovering it after the call.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools