# Run Fieldproxy from Claude, ChatGPT or your own AI agent

> Fieldproxy's official MCP server lets an AI assistant read your workspace, answer with live numbers and propose changes that a person confirms. Setup takes about two minutes.

Source: https://www.fieldproxy.ai/developers/guides/ask-with-claude-or-chatgpt

## 1. Switch it on

A workspace administrator switches on AI assistant access in Settings, AI assistant (it is off by default). Your MCP address is `https://<api-host>/mcp`, for example `https://api-india-1.fieldproxy.ai/mcp` or `https://api-us-east-1.fieldproxy.ai/mcp`.

## 2. Connect your client

Sign in with OAuth from Claude, ChatGPT or Copilot Studio, or create a key under Settings, AI assistant, New key and send it as `Authorization: Bearer fpmcp.…`.

Claude Code:

```bash
claude mcp add --transport http fieldproxy https://api-india-1.fieldproxy.ai/mcp \
  --header "Authorization: Bearer fpmcp.YOUR_KEY"
```

Cursor and other MCP clients:

```json
{
  "mcpServers": {
    "fieldproxy": {
      "url": "https://api-india-1.fieldproxy.ai/mcp",
      "headers": { "Authorization": "Bearer fpmcp.YOUR_KEY" }
    }
  }
}
```

## 3. Ask

first prompt:

```text
Call describe_schema, then tell me which jobs were completed last week
with no invoice, grouped by technician.
```

## Changes wait for a person

Every write is proposed first with a preview of the rows it would change, applied only after a person confirms, and comes back with an undo id. More than 5 rows needs bulk permission and more than 1,000 is refused.

propose, confirm, undo:

```text
// 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> })
```

Every tool is listed in the [MCP tools reference](https://www.fieldproxy.ai/developers/docs/mcp-tools).

## Questions

### Does Fieldproxy work with Claude and ChatGPT?

Yes. Fieldproxy has an official MCP server that Claude, ChatGPT, Microsoft 365 Copilot, Cursor, Claude Code and any MCP client can connect to, with OAuth or a scoped key.

### Can an AI agent change data in Fieldproxy?

Yes, with a person in the loop. Every write is proposed with a preview, applied only after someone confirms, and can be undone.

### Does the Fieldproxy MCP server cost extra?

No. API access and the MCP server are included on every Fieldproxy plan.

## This is one way, not the only way

This guide shows one common way to do it. A Fieldproxy workspace can be reached from every side, and anything in it can be read, changed or automated:

- REST API: read, insert, update and delete on any table the key allows ([REST API reference](https://www.fieldproxy.ai/developers/docs/rest-api)).
- 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](https://www.fieldproxy.ai/developers/docs/mcp-tools)).
- Automations: 15 trigger types and about 50 step types, with webhooks in and signed webhooks and HTTP calls out ([Webhooks and automations](https://www.fieldproxy.ai/developers/docs/webhooks-automations)).
- Public forms, record links and customer portals for people outside the company ([Public forms and links](https://www.fieldproxy.ai/developers/docs/public-forms)).
- Apps as JSON: new screens, fields, tables and workflows ([Apps as JSON](https://www.fieldproxy.ai/developers/docs/apps-as-json)).
- Voice and text agents that work from the same data ([Voice and text agents](https://www.fieldproxy.ai/developers/docs/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](https://www.fieldproxy.ai/book-demo?source=dev-guides).

More: [REST API reference](https://www.fieldproxy.ai/developers/docs/rest-api) · [OpenAPI](https://www.fieldproxy.ai/developers/openapi.json) · [All guides](https://www.fieldproxy.ai/developers/guides)