How many rows can it import at once?

Up to 1,000 rows per confirmed change, so a larger file goes in as several batches, each dry-run and confirmed.

Can it add a field my data needs?

Yes, for an administrator on a workspace with build switched on: it adds the column first, then imports into it.

Can an import be undone?

Yes. The import is one applied change with an undo, and deleted records can be restored.

Imports and data migration · Fieldproxy MCP

Bring the spreadsheet in, by asking

From Claude, ChatGPT or Copilot in Teams, on your live field service data, with a confirm step before anything changes.

Book a demo How it connects

Reply to Claude...

Fieldproxy

ClaudeChatGPTCopilot in Microsoft Teams

Illustration of Fieldproxy's MCP tools inside Claude, ChatGPT and Copilot. Names and data are examples.

Short answer

Imports and data migration from ChatGPT, Claude or Copilot: how does it work?

Through Fieldproxy's MCP server, Claude, ChatGPT or Copilot can read an export or spreadsheet, match its columns to your tables, add a field where the data needs one, and import the rows. The import is dry-run first, showing what would be added, what would be updated and which rows it flagged; where the table has an import profile, existing rows are updated instead of duplicated. It is applied only when you confirm and can be undone. Up to 1,000 rows go in per confirmed change.

Last verified September 27, 2026

Real requests

What people ask, and the tools it calls

You ask	Fieldproxy tools	You get
“Import this spreadsheet of 400 new sites for Northwind”	describe_schema, import_records, confirm_write	The rows mapped to your sites table, imported on confirm
“Here is our Jobber client export, bring the customers and properties in”	describe_schema, import_records, confirm_write	Customers and properties mapped and imported, matched rows updated instead of duplicated
“The export has a gate code column we don't have, add it and fill it in”	add_column, import_records	A new field, filled from the file
“Which of the imported customers have no email or phone?”	run_sql	The gaps to fix before you go live
“Restore the 12 jobs someone deleted this morning”	list_deleted_records, restore_deleted_records	The jobs back, on confirm
“Export every open job to CSV for the auditor”	export_csv	A CSV file

The part nobody else does

Your AI can change the software, not just the data

Every other field service connector we checked (September 27, 2026) reads records and, at most, edits a few of them. Fieldproxy's MCP server can also build: new fields, screens, tables, automations and agents, made in a sandbox copy of your workspace and live only when you approve.

Add a field

"Add a warranty expiry date to every job." The column, the form field and the list column, in one ask.

Build a screen

"Build a subcontractor compliance screen that flags missing insurance." A new screen on your real data.

Wire an automation

"Email the service manager 30 days before a warranty runs out." Saved switched off until you turn it on.

Create an agent

Voice and text agents: validate, simulate against test conversations, then enable.

Add your own tools

Saved SQL tools such as "a customer's overdue invoices", which every AI connection in the workspace can then call by name.

Roll back anything

Every build is checked against your database before it saves, promoted from the sandbox when you approve, and can be rolled back.

Guardrails

Your AI proposes. A person confirms.

Built for operations with branches, teams and an IT review, not a single login.

Nothing changes on one call

Every write, send or action is a proposal the user confirms within 30 minutes. Writes can be undone. More than 5 rows needs bulk permission, and more than 1,000 is refused.

Keys scoped like API keys

Limit a key to certain tables, certain rows ("only the North region's jobs"), hidden columns, insert/update/delete, and an expiry from 1 hour to 90 days. Postgres enforces the row limits.

Builds save as drafts

Apps and automations are checked against the database before they save, new automations and agents are saved switched off, and public apps are never changed.

Sends are limited

Email goes only from the user's own mailbox, at most 20 sends an hour per key, inside the workspace's quiet hours. A sandbox never sends.

Everything is logged

Every call is written to an audit log with the tool, key, person and outcome. Administrators see every key and connected app, and revoking one applies on the next request.

FAQ

Questions

How many rows can it import at once?: Up to 1,000 rows per confirmed change, so a larger file goes in as several batches, each dry-run and confirmed.
Can it add a field my data needs?: Yes, for an administrator on a workspace with build switched on: it adds the column first, then imports into it.
Can an import be undone?: Yes. The import is one applied change with an undo, and deleted records can be restored.

Imports and data migration, from the chat

Book a demo