The Read-Only SQL Query Tool
Run a governed, read-only SQL query against a connected database so an agent can answer questions from live data — with no possibility of writes, and every query logged.
The data holds the answer — nobody has time to dig
Spreadsheets, databases, and documents are full of answers that stay locked because pulling them out is slow, manual, and skill-bound. And the data is exactly what can’t be handed to a hosted assistant.
Manual analysis
Profiling and querying data by hand doesn’t scale.
Skill bottleneck
Answers wait on the few people who can write the query.
Locked in documents
Tables trapped in files stay out of reach.
Sensitive data
Business data can’t be sent to a third-party service.
Read-Only SQL Query, without the risk
Capability
What it does
Query your database safely, read-only.
it executes a read-only SQL query against a connected database and returns the rows.
Assignable to any agent
How it works
Predictable, inspectable behavior
Designed to be reliable.
queries run under a strictly read-only role with row limits and logging, so an agent can explore data without any ability to modify it — safe by construction.
Every call logged
Governance
Private, governed, on-premise
Runs inside your perimeter.
Analysis runs inside your perimeter, scoped per tenant with audit logging, so an agent can profile, query, and transform sensitive business data without any of it leaving your environment.
Per-tenant, logged
Parameters
The sql_query_readonly tool accepts these inputs when an agent calls it. Required inputs are flagged.
default: 1000 Optional Maximum rows to return.
How the Read-Only SQL Query tool works in practice
Read-Only SQL Query is a data & analytics tool you assign to a VDF AI agent. It executes a read-only SQL query against a connected database and returns the rows. Its hallmarks — SQL, Read-only, Governed — let an agent rely on it as a dependable step in a larger task rather than a brittle one-off script.
Under the hood, queries run under a strictly read-only role with row limits and logging, so an agent can explore data without any ability to modify it — safe by construction. It expects query as required input, so calls are explicit and easy to audit. Every call is scoped to the requesting tenant and written to an audit log, so the capability is safe to run inside a regulated, on-premise environment — the same governance model behind every VDF AI tool.
Teams reach for Read-Only SQL Query when they need to handle ad-hoc answers, reporting, and grounded analytics. It rarely works alone — pair it with Data Profiler, Statistics Tool, and Chart Generator to build a complete, governed workflow, then compose those steps into an on-premise VDF AI Network.
Where Read-Only SQL Query pays back
Ad-hoc answers
Answer a business question from the database.
Reporting
Pull the rows behind a report.
Grounded analytics
Feed real data into an agent’s analysis.
Self-serve
Let non-analysts query via an agent, safely.
Assigned to agents, orchestrated as networks
On VDF AI, an industry’s use cases map to agents, and you assign tools like this one to those agents. Compose multiple agents into a governed, on-premise network.
What changes after you assign it
Questions about the Read-Only SQL Query tool
What is the Read-Only SQL Query tool?
It executes a read-only SQL query against a connected database and returns the rows. Assigned to a VDF AI agent, it runs under role-based policy with full audit logging so the capability is safe to use in production.
Can it change data?
No. It runs under a read-only role, so only SELECT-style queries succeed — writes are impossible.
Is there a row limit?
Yes. Results are capped by max_rows to keep queries safe and responsive.
What inputs does the Read-Only SQL Query tool need?
It requires query, and optionally accepts database and max_rows. Each parameter is validated when an agent calls the tool, and the full call is logged for audit.
Which tools pair well with Read-Only SQL Query?
Read-Only SQL Query is commonly assigned alongside Data Profiler, Statistics Tool, and Chart Generator. On VDF AI you compose several tools and agents into a single governed, on-premise network.
Does it run on-premise?
Yes. Like every VDF AI tool, it can run on-premise or in your sovereign cloud, scoped per user and audit-logged, so your data never leaves your perimeter.
How do agents use it?
You assign the tool to an agent under a role-based policy; the agent calls it as one step in a task, and several agents and tools can be orchestrated together as a governed VDF AI Network.
Assign Read-Only SQL Query to these agents
These VDF AI agents can be assigned this tool. Open an agent to see the full toolkit it can run.
Tools that work well alongside this one
Where this tool delivers value
Put Read-Only SQL Query to work
See the Read-Only SQL Query tool assigned to an agent and orchestrated in a governed, on-premise network.