Querying your data

Give an agent read-only SQL access and schema introspection

SQLTools connects an agent to a database. Point it at a read-only connection and the agent can introspect the schema and run queries.

from agno.agent import Agent
from agno.db.postgres import PostgresDb
from agno.models.openai import OpenAIResponses
from agno.tools.sql import SQLTools

agent = Agent(
    model=OpenAIResponses(id="gpt-5.5"),
    db=PostgresDb(db_url="postgresql+psycopg://ai:ai@localhost:5532/ai"),
    tools=[
        SQLTools(db_url="postgresql+psycopg://readonly@warehouse/analytics")
    ],
    instructions=(
        "Introspect the schema before writing SQL. Answer with the numbers "
        "and the exact query you ran. Never guess a column name."
    ),
)

agent.print_response("How many active subscriptions are on the Pro plan?")

The agent’s db and the SQLTools connection are separate. db stores the agent’s own sessions and learnings. SQLTools points at the warehouse you are answering questions about. Keep them distinct.

Introspect before generating

A data agent that guesses column names is wrong confidently. SQLTools ships list_tables and describe_table so the agent grounds SQL in the real schema. The instruction to introspect first is what makes it reliable.

Tool	Use
list_tables	Discover what exists before querying
describe_table	Get exact column names and types
run_sql_query	Execute the generated SQL

Scope the connection

The cleanest boundary is the connection itself. The readonly Postgres role has no write grant, so the connection physically cannot write, regardless of what the model is prompted to do. For the full read vs write split, see Safe data access.

Next steps

Task	Guide
Ground SQL in business rules	Grounding in context
Stop repeating query errors	Self-correcting agents
Allow controlled writes	Safe data access

Developer Resources

• SQL tools cookbook
• Dash: the multi-agent data team