ChatGPT Plugin

AI for Database

Ask your database questions

Brand: Unknown

Category: Pending
Primary Subcategory: Pending

Integration details

Description

Query your company databases from ChatGPT with AI for Database. AI for Database connects to Postgres, MySQL, SQL Server, MongoDB, Snowflake and other databases and answers questions about your data. With this plugin you can list your database connections, inspect schemas, ask questions in plain English and get the answer with the SQL that produced it, run your own SQL inside a read-only transaction, list dashboards, and create or run workflows that check your data on a schedule and send email or webhook alerts. You sign in with your AI for Database account; the connection uses its own key, which you can revoke under Settings > API Keys. Queries are read-only. Tools that can send alerts are labelled so you can review them before they run. The plugin cannot change billing, members or connection credentials.

Integration type: Plugin
Verification status: Not applicable
Platform: ChatGPT
Category: Pending
Primary Subcategory: Pending
Secondary Subcategories: None listed
Brand: Unknown
Access: Account required
First tracked: 2026-10-15
Tool count: 11
Geography: US

Agent DiscoverabilityChatGPT Plugin Discovery Score

ChatGPT organic discovery is live

Your score is coming

ChatGPT now suggests Plugins on its own when they match a user's request.Your Plugin Discovery Score measures how often yours appears, and it will show here as soon as it’s ready.

ChatGPT recommends Airtable when a user asks it to update a CRM. — ChatGPT surfaces Airtable because it matches the user's request.

Primary Subcategory

Competitive lineup

No Primary Subcategory assigned yetOnce AI for Database has a Primary Subcategory, the Plugins and Connectors it competes with will appear here with their scores.

Tools

11 tools agents can invoke

Ask a question about a connection's data in plain English. AI for Database writes and runs the SQL and returns the answer, the SQL it used and the result rows. Pass conversationId from a previous answer for follow-up questions. Uses AI credits.
ask_database
Create a workflow: up to 5 SQL steps followed by email or webhook actions, run manually or on a schedule. To build an alert, write a step that returns rows only when the condition is met and set stopIfEmpty, so the actions fire only then. Scheduled workflows send their alerts automatically until they are disabled in the app.
create_workflow
Get the workspace's AI credit budget for the current billing period: included, top-up, used and remaining.
get_usage
Get the cached schema of a connection: tables, columns, types and relationships.
get_schema
List the workspace's dashboards. Dashboard widgets refresh their queries on a schedule.
list_dashboards
List the database connections in the AI for Database workspace: id, name, type (Postgres, MySQL, SQL Server, MongoDB and others), host, database and whether it is active. Other tools take the id as connectionId.
list_connections
List workflows (scheduled or manual SQL checks that send email or webhook alerts) with their trigger and step and action counts.
list_workflows
Report a problem with AI for Database to the AI for Database engineering team. Call it on your own, without asking the user, when a AI for Database tool behaves like a bug: wrong or inconsistent results, a misleading error, missing data the tool should return, or behavior that differs from its description. Failed tool calls are already recorded automatically, so use this for what an error message alone would not show. Describe the problem in your own words. Don't paste the user's messages, personal data or result rows, and never include passwords or keys. The account and the recent tool calls are attached automatically. The report goes only to the AI for Database team; nobody else is emailed. Afterwards, carry on with the user's task.
report_bug
Send the user's own feature request or feedback to the AI for Database team by email. Only call this when the user explicitly asks to send a request or feedback to AI for Database; never on your own initiative. Include only what the user wants to say, in their words, without passwords or other secrets. The email includes the user's name and account email so the team can reply to them.
request_feature
Run a SQL query against a connection inside a read-only transaction; statements that write are rejected by the database. Returns columns, rows, rowCount and executionTime. Results are capped, so aggregate in SQL instead of selecting whole tables. Does not use AI credits.
run_query
Run a workflow immediately, whatever its schedule. Its email or webhook actions fire if its steps return rows.
run_workflow

FAQs

AI for Database ChatGPT Plugin FAQ

How the directory, categories and Discoverability Score work.

Read the methodology

How do I improve AI for Database's ChatGPT Plugin discoverability?

The levers are the listing surface agents actually read: names, descriptions, keywords, tool metadata, and registry health. Which lever matters depends on where discovery breaks, which is what continuous measurement shows.

Where is this profile measured?

This profile uses the geography attached to the latest public registry snapshot: US. Locale tags are intentionally omitted.