---
title: "Connect Felt to AI Engine - APIANT.ai"
description: "When \"New or updated map\" fires in Felt, your agent runs \"Add facial repository\" in AI Engine."
canonical: "https://apiant.ai/connect/felt-to-ai-engine"
---

# Connect Felt to AI Engine

When **New or updated map** fires in [Felt](https://apiant.ai/connections/felt), your agent runs **Add facial repository** in [AI Engine](https://apiant.ai/connections/ai-engine). Describe the whole flow and it is built, tested on every scenario and kept running.

Felt **1** trigger AI Engine **8** actions

What the catalog holds today. Ask for anything missing and your agent reads the API documentation and adds it.

## What do you want Felt and AI Engine to do together?

Give your AI client this address.

`https://mcp.apiant.ai`

One connection does both: ask your client to act in an app once, or have it build an automation that keeps running. Any client that takes a remote MCP server. Nothing to install. Create your free account, then sign in once in your browser.

### Set it up in your client

### Claude Code

Run this in the directory you want to work in.

`claude mcp add --transport http -s project apiant-ai https://mcp.apiant.ai`

Start Claude Code there, approve the server, and sign in in the browser page it opens.

[Claude Code guide (opens in a new tab)](https://apiant.ai/docs/mcp/claude-code)

### Claude, web and desktop

Open Customize, then Connectors, then Add custom connector, and paste the address. On Team and Enterprise an owner adds it first.

[Setup guide (opens in a new tab)](https://apiant.ai/docs/mcp)

### Cursor

Add the address to your MCP configuration as a server URL. Cursor signs you in in your browser.

[Setup guide (opens in a new tab)](https://apiant.ai/docs/mcp)

### Zed

Open Settings, then AI, then MCP Servers, then Add Server, then Add Remote Server.

[Setup guide (opens in a new tab)](https://apiant.ai/docs/mcp)

### Codex and the ChatGPT desktop app

Open Settings, then MCP servers, then Add server, and choose Streamable HTTP. From the terminal, Codex takes the address with its own add command and then signs you in.

[Setup guide (opens in a new tab)](https://apiant.ai/docs/mcp)

### Any other MCP client

Paste the address where the client asks for a remote MCP server URL, and name the server apiant-ai where it lets you. APIANT's skills reach the client over the same connection.

[Setup guide (opens in a new tab)](https://apiant.ai/docs/mcp)

Example flows

## What Felt can start in AI Engine

- When **New or updated map** in Felt then **Add facial repository** in AI Engine
- When **New or updated map** in Felt then **Analyze faces** in AI Engine

Starting points drawn from the triggers and actions in the catalog today. Describe the flow you need, at any depth, and your agent builds it and tests every scenario before it ships.

Everything your agent can do with Felt and AI Engine

## Triggers and actions 1 trigger · 8 actions

- Trigger

**New or updated map**

Fires when a map is created or edited (annotations drawn/edited, layers updated, comments added/resolved). Delivered via Felt's map:update webhook, attached per-map and created in Felt workspace settings UI (no REST endpoint to register it); verify the felt-signature HMAC header. See /rest-api/listening-to-updates-using-webhooks.

- Action

**Add facial repository**

Creates a new facial repository for storing and searching faces.

- Action

**Analyze faces**

Analyzes the faces in an image and returns attributes such as estimated age, gender and emotions.

- Action

**Compare faces**

Compares the face in a source image with the faces in a target image and returns how similar they are.

- Action

**Detect labels**

Detects and categorizes the content of an image, returning labels with confidence scores.

- Action

**Detect objects**

Detects and locates objects in an image, returning their labels, confidence scores and bounding boxes.

- Action

**Detect unsafe content**

Checks an image for explicit or unsafe content and returns the moderation labels with confidence scores.

- Action

**Extract text from image**

Extracts the text found in an image (OCR), including handwriting, receipts and complex layouts in 100+ languages.

- Action

**Extract text from PDF**

Extracts the text from a PDF document, optionally limited to a range of pages.

## Each app on its own

- [ **Felt** Cloud-based GIS platform for creating interactive maps and dashboards from geospatial and database data.](https://apiant.ai/connections/felt)
- [ **AI Engine** 36+ AI endpoints: OCR, face detection, background removal, object detection, NSFW moderation, face swap...](https://apiant.ai/connections/ai-engine)

Reviews

## What our customers say

## More from Felt

- [ **Felt to capture** capture is a service that is your AI's long-term memory.](https://apiant.ai/connect/felt-to-capture)
- [ **Felt to Mapbox** Mapping and geolocation platform offering interactive maps, geocoding, routing, and navigation APIs.](https://apiant.ai/connect/felt-to-mapbox)
- [ **Felt to HubSpot** HubSpot is your all-in-one stop for all of your marketing software needs.](https://apiant.ai/connect/felt-to-hubspot)
- [ **Felt to Salesforce** Salesforce is a leading enterprise customer relationship management (CRM) platform.](https://apiant.ai/connect/felt-to-salesforce)
- [ **Felt to Slack** Slack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...](https://apiant.ai/connect/felt-to-slack)
- [ **Felt to Google Sheets** Google Sheets](https://apiant.ai/connect/felt-to-google-sheets)

## More into AI Engine

- [ **HubSpot to AI Engine** HubSpot is your all-in-one stop for all of your marketing software needs.](https://apiant.ai/connect/hubspot-to-ai-engine)
- [ **Salesforce to AI Engine** Salesforce is a leading enterprise customer relationship management (CRM) platform.](https://apiant.ai/connect/salesforce-to-ai-engine)
- [ **Slack to AI Engine** Slack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...](https://apiant.ai/connect/slack-to-ai-engine)
- [ **Google Sheets to AI Engine** Google Sheets](https://apiant.ai/connect/google-sheets-to-ai-engine)
- [ **Gmail to AI Engine** Gmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...](https://apiant.ai/connect/gmail-to-ai-engine)
- [ **Google Calendar to AI Engine** Google Calendar is a time management tool providing scheduling features, event reminders, and integration...](https://apiant.ai/connect/google-calendar-to-ai-engine)

Questions

## Felt and AI Engine, answered

###

### What can start an automation from Felt?

Any of Felt's 1 trigger in the catalog, including New or updated map. Describe the moment in plain language and your agent picks the right one.

###

### What can your agent do in AI Engine when something happens in Felt?

Any of AI Engine's 8 actions, including Add facial repository, Analyze faces, Compare faces and Detect labels. Your agent maps the data both ways and tests every scenario before it ships.

###

### Can it also run from AI Engine to Felt?

AI Engine has no triggers in the catalog today, so automations start in Felt. If you need the other direction, ask: your agent reads AI Engine's API documentation and adds it.

###

### Do I have to build a connector for Felt or AI Engine?

No. Both are in the catalog with their triggers and actions. You describe the automation; your agent builds it, tests every scenario and keeps it running.

###

### Can my AI client use Felt and AI Engine without building an automation?

Yes. With your AI client connected to APIANT, ask it to do something in AI Engine once and it runs that action on the spot. Ask for an automation and your agent builds it, tests every scenario and keeps it running. One connection covers both.

###

### What happens when something fails?

Your agent works that out for you. It plans the failure paths along with the happy path, then tests every scenario before it ships.

###

### Is there a free plan?

Yes. Every plan includes the agent, including free, and building from your own AI client spends no assistant credits.
