Limits and safety
Read-only SQL
- run_sql runs one SELECT (or WITH … SELECT): at most 500 rows and 5 seconds.
- Reads run as a read-only database role, one statement at a time.
- Only tables and columns describe_schema lists are readable; hidden columns are removed from every result.
- Row limits on a key are applied by Postgres, and the signed-in person's own access is the ceiling.
Writes: propose, confirm, undo
// 1. The agent proposes; nothing is saved
propose_write({
"summary": "Mark job 1042 as completed",
"sql": "UPDATE jobs SET status = 'completed' WHERE id = 1042"
})
// => rows it would affect, sample before -> after values, and a pending_id
// 2. A person agrees, then the agent applies it
confirm_write({ "pending_id": <pending_id> })
// => the rows changed and an undo_id
// 3. Changed your mind?
undo_write({ "undo_id": <undo_id> })- A proposal must be confirmed within 30 minutes; a new proposal cancels an earlier unconfirmed one.
- More than 5 rows needs allow_bulk on confirm; more than 1,000 rows is refused.
- Only tables and columns marked writable can change, and tables behind an approval gate are not writable by AI.
- A workspace's own actions carry its checks and validations, so an AI should use them instead of raw SQL when one fits.
Messages
- Email and SMS are drafted first and sent only by confirm_send after a person has read them.
- Email goes only from the person's own connected mailbox, at most 20 sends an hour per key, inside the workspace's quiet hours.
- Opted-out numbers are skipped, and inbound STOP, UNSUBSCRIBE and START are applied on every workspace.
- A sandbox never sends email, texts or calls.
Builds
- Apps save as drafts and are checked (lint, SQL against the real database, navigation) before saving; publishing is a separate step.
- New automations, agents and workspace tools are saved switched off.
- Builds only ever add: tables and columns can be dropped only if they were created through MCP.
- Public apps are never created or changed.
Import and export
- import_records prepares up to 1,000 rows from CSV, tab-separated text or a stored spreadsheet, shows what would be added or updated, and applies on confirm_write.
- export_csv saves up to 10,000 rows from one SELECT; the link is public to anyone who has it.
- In the web app, screens can import xlsx, xls and csv files and export CSV or Excel.
Audit and oversight
Every AI tool call is logged with the tool, key, person and outcome. Administrators can review it (ai_activity_log, ai_usage_summary), see the full workspace activity trail, set alerts on bulk deletes, off-hours activity or sensitive field changes, and revoke any key or connected app with effect on the next request. See the MCP overview for the full security model.
Questions
Is it safe to let an AI agent work in Fieldproxy?
Yes, and that is what makes it easy to try: reads are read-only, every write is proposed, confirmed by a person and undoable, messages are drafted before they are sent, and every tool call is logged.
Can I test changes without touching live data?
Yes. A sandbox copies the workspace for building and testing, never sends email, texts or calls, and promotes apps, automations and agents to live when you are ready.
How much data can an agent read or change at once?
run_sql returns up to 500 rows, export_csv up to 10,000, imports take up to 1,000 rows with a dry run first, and confirmed writes up to 1,000 rows, with more than 5 needing bulk permission.
Everything else you can connect
This page covers one part of Fieldproxy. Every other way in works on the same data, and there are step-by-step guides with working code:
- REST API: read, insert, update and delete on any table the key allows (REST API reference).
- MCP server: 170+ tools for Claude, ChatGPT, Copilot, Cursor and your own agents, including read-only SQL, proposed writes, automations and app building (MCP tools).
- Automations: 15 trigger types and about 50 step types, with webhooks in and signed webhooks and HTTP calls out (Webhooks and automations).
- Public forms, record links and customer portals for people outside the company (Public forms and links).
- Apps as JSON: new screens, fields, tables and workflows (Apps as JSON).
- Voice and text agents that work from the same data (Voice and text agents).
- Not listed here? Fieldproxy's team builds integrations with the other systems you use as part of setting up your workspace. Tell us what you need.
Checked against the Fieldproxy platform reference on October 18, 2026.
Get your own custom field service management within a day. Tailored to your workflows.
We set up a workspace on your own data and connect your AI or your systems on the call.
Get Demo