PostgreSQL integration

Databases · 10 actions · Custom auth

PostgreSQL database integration for executing SQL queries, managing tables, and performing CRUD operations. Uses the asyncpg driver.

Put PostgreSQL to work View PostgreSQL integration docs

Overview

The ModuleX PostgreSQL integration lets a ModuleX agent operate PostgreSQL on your behalf — running create, update and remove actions across raw queries, rows and query with conditions — directly from a plain-English request, using your organization's own PostgreSQL credentials. No pre-built workflow is required: the agent picks the right PostgreSQL action for the task.

PostgreSQL is a databases platform. ModuleX adds the agent layer: ask for an outcome and it selects and runs the right PostgreSQL action — or, when you want a repeatable process, the composer assembles a PostgreSQL workflow for you, streaming the nodes onto the canvas as it builds.

Ask the assistant

Drive PostgreSQL in plain English

Type what you want. A ModuleX agent picks the right PostgreSQL action — or chains several — and runs it. No workflow to build.

INSERT a new row, returning the inserted record
resolves tocreate_row
Find the row I describe and remove it
resolves tofind_rowdelete_row
UPDATE rows matching a WHERE condition (returns updated rows)
resolves toupdate_row
Show me the schemas that match what I describe
resolves tolist_schemas

Use cases

What you can automate with PostgreSQL

Find the right row and remove it in one promptfind_rowdelete_row
Run a raw query from a plain-English requestexecute_raw_query
Pull a list of schemas for a reportlist_schemas

At a glance

PostgreSQL integration at a glance

VendorPostgreSQL

CategoryDatabases

Actions available10

AuthenticationCustom

Uses your own credentialsYes

Works with the assistantYes

Works in the composerYes

Multi-step / tool-chainingYes

Technical referenceView docs

Integration version1.0.0

Last updatedJun 2026

Reference

All 10 PostgreSQL actions

Raw Queries1

execute_raw_query

Execute a raw SQL statement (SELECT/INSERT/UPDATE/DELETE/DDL). Use $1, $2, ... placeholders for parameterized queries.

Rows5

create_row

INSERT a new row, returning the inserted record

delete_row

DELETE rows matching a WHERE condition (returns deleted rows)

update_row

UPDATE rows matching a WHERE condition (returns updated rows)

upsert_row

INSERT … ON CONFLICT (conflict_target) DO UPDATE …

find_row

SELECT * FROM table WHERE column <op> value

Query with Conditions1

execute_query_with_condition

SELECT * FROM table WHERE <condition>

Schemas1

list_schemas

List all user-visible schemas (excludes pg_catalog etc.)

Tables2

list_tables

List all tables and views in a schema

describe_table

Return column metadata + primary keys for a table

See full parameters and response schemas in the PostgreSQL integration docs

Two ways

Two ways to use PostgreSQL in ModuleX

Ask the assistantType what you want done and a ModuleX agent picks the right PostgreSQL action and runs it — no workflow to build.

Compose a workflowNeed it to happen every time? Describe the process and the composer wires PostgreSQL into a repeatable workflow you can run on a schedule, from chat, or as an API.

Security

Connecting PostgreSQL

CustomPostgreSQL uses a custom authentication flow. ModuleX encrypts whatever credentials you supply and scopes them to your organization.

Step-by-step setup in the PostgreSQL docs

Pairs well with PostgreSQL

Agents often chain PostgreSQL with these — connect them once and the agent can use all of them in a single task.

MySQL9 actions

Snowflake9 actions

Supabase8 actions

Microsoft SQL Server4 actions

FAQ

PostgreSQL + ModuleX FAQ

A ModuleX agent can run any of PostgreSQL's 10 actions — across raw queries, rows, query with conditions and schemas — from a plain-English request, using your organization's own PostgreSQL credentials.

No. The agent selects the right PostgreSQL action from your prompt. A workflow is only needed when you want a repeatable process — and the composer builds that for you from a description.

Through a secure PostgreSQL connection; your credentials are stored encrypted and scoped to your organization.

10, spanning raw queries, rows, query with conditions and schemas.

PostgreSQL runs on your own credentials, so any PostgreSQL usage is billed by PostgreSQL directly. ModuleX meters the agent run — and if you connect your own model keys, there's no ModuleX markup on model usage.

Put PostgreSQL to work in ModuleX.

Connect PostgreSQL once with your own credentials and let your agent run all 10 actions on demand.

Put PostgreSQL to work View technical docs

Last updated: Jun 2026Browse all 175 integrations →