Open-source ESP32-CAM project

Gizmo Camera

An ESP32-CAM Wi-Fi camera that takes a JPEG snapshot on every request, with a web app to set it up from your phone and an MCP server for AI agents.

  • JPEG snapshots up to 1600 × 1200
  • Simple HTTP API
  • MCP server for AI agents
Difficulty
Beginner
Build time
15 min
Soldering
No soldering
The Gizmo Camera in its white and orange printed enclosure on its ball-joint stand, and pulled apart into the shell, the ESP32-CAM on its MB board, the back plate, four M3 screws and the stand.

Project snapshot

A quick overview of the hardware, firmware, and behavior behind this build.

Camera

01

The OV2640 sensor and the white flash LED of the AI Thinker ESP32-CAM, with snapshots from 160 × 120 up to 1600 × 1200 and adjustable JPEG quality.

HTTP API

02

Every snapshot is a GET request to /api/capture that returns a JPEG, with its resolution, quality and flash as options, so browsers, scripts and home automation servers can all use it.

AI agents

03

An MCP server at /mcp lets agents like Claude Code look through the camera with a take_snapshot tool, and a Markdown guide at /llms.txt explains how to use it.

Setup flow

04

Flashed from the browser, then set up from a hotspot on first boot, with local access through gizmo-camera.local on supported networks. No code to edit and no credentials in the firmware.

Overview

Gizmo Camera gives a cheap ESP32-CAM module a proper job: a camera on your network that answers every request with a fresh photo. Point it at a 3D printer, a plant or a door, and anything that can make an HTTP request can see what it sees. AI agents get it as an MCP server, so they can look through it too.

  • JPEG snapshots on request, up to 1600 × 1200 on the OV2640, with the flash LED for dark scenes
  • A web app built into the firmware, to set the camera up and take photos from your phone
  • A small HTTP API that scripts and other devices can call directly
  • An MCP server and a Markdown guide, so AI agents can use the camera on their own

How it works

Every photo, whoever asks for it, follows the same short path.

StepWhat happens
AskThe web app, a script or any HTTP client calls /api/capture with the resolution, the quality and the flash. An AI agent asks the same by calling take_snapshot on the MCP server.
ShootThe firmware applies the options to the sensor, turns on the flash if asked, and takes a fresh frame.
SendThe JPEG is streamed straight from the camera's memory to the client, with its resolution and capture time in the response headers.

The camera takes one photo at a time: a request that arrives while another one is being taken gets a clear busy answer, so it can simply try again a moment later.

Why it is useful

Gizmo Camera turns a few euros of hardware into a camera that people, scripts and AI agents can all use the same way. It is also a compact template for any ESP32 device that should be easy to talk to from code.

  • Check on a print, a plant or a door from your phone, without an app or a cloud account.
  • Grab photos from scripts and home automation with one HTTP request.
  • Give an AI agent eyes on the physical world, on your own network.

The web app

What you see on your phone once the device is on your Wi-Fi.

The camera screen of the web app, with the last snapshot (a test card at 1600 × 1200), its size and capture time, and the buttons to take a new one and save it.
The camera screen before the first photo, with the Take snapshot button and the resolution and quality options.
The Wi-Fi screen, with the current network and the networks in range.

What you need

The parts to get before you start, and what to look for when you buy them.

  • 1×

    AI Thinker ESP32-CAM

    With the OV2640 camera and the 4 MB of PSRAM the firmware needs: every AI Thinker module has both.

  • 1×

    ESP32-CAM-MB USB board

    The USB adapter the ESP32-CAM plugs into, for flashing and power: the ESP32-CAM has no USB port of its own.

  • 1×

    Micro-USB data cable

    A data cable, not a charge-only one, on a good USB port or 5 V supply: the flash LED and the Wi-Fi draw current peaks.

Setup flow

Follow these steps to get the project running, from the first local setup to the initial upload or configuration.

  1. 01

    Step 1

    Plug the ESP32-CAM into its MB board and connect it over USB

    The ESP32-CAM has no USB port of its own: sit it on its ESP32-CAM-MB USB board, and plug that into your computer with a data USB cable. Use Chrome or Edge, so the browser flasher can find its serial port.

  2. 02

    Step 2

    Flash the prebuilt firmware from this page

    Scroll down to the firmware flashing card, start the upload from the browser, and wait for it to complete. If the flasher can't connect, hold IO0 on the MB board, press and release RST, then release IO0 and try again. When it's done, press RST to start the new firmware.

  3. 03

    Step 3

    Connect the camera to your Wi-Fi

    On the first boot, join the Gizmo-Camera hotspot with your phone, and pick your network on the page that opens. The Wi-Fi is saved on the board, never in the firmware.

  4. 04

    Step 4

    Open gizmo-camera.local and take a photo

    Once the camera joins your Wi-Fi, open gizmo-camera.local, or its IP address, choose the resolution, the quality and the flash, and take a snapshot. Save it as a JPEG, or grab one from a script with a plain HTTP request.

    Terminal
    curl -o photo.jpg "http://gizmo-camera.local/api/capture?resolution=SVGA"

Frequently asked questions

A few practical answers about how the project works, how it is configured, and what to expect from the hardware.

Anything you want to check on from time to time: a 3D printer, a plant, a door or a parking spot. It takes a fresh photo whenever something asks for one, from the web app, a script, a home automation server or an AI agent.

Source code

View Gizmo Camera on GitHub

Browse the repository for firmware, hardware notes, and the implementation details behind this build.

Open GitHub
OpenGizmo GitHub project illustration
Open source

See also

More open-source ESP32 builds you can make next.