Give LLM agents webcam access: capture photos and record short videos over MCP.
Runs on your machine from its package; the steps are below.

At most: only reads or looks up information.
Odel charges nothing per call. The publisher may charge for its own service.
Runs locally over stdio
This server isn't hosted — your MCP client launches it from a package registry. Use one of the commands below, or drop the config into your client (e.g. Claude Desktop).
Distributed as an MCP bundle (`https://github.com/1019666077-bit/webcam_mcp/releases/download/v0.2.1/botbridge-webcam.mcpb`) — download it and import the bundle in your MCP client.
Fork notice. This is
botbridge-webcam-mcp, a fork of pavel-kirienko/webcam_mcp (MIT), maintained by 1019666077-bit. It adds an MCP Apps panel (webcam_panel). Install this distribution asbotbridge-webcam-mcp; the upstream distribution on PyPI is namedwebcam-mcp. The Python import package iswebcam_mcp.
Webcam MCP is a Model Context Protocol (MCP) server that gives LLM agents direct access to your webcam. It enables autonomous agents to capture photos and record video sequences, making it possible to debug cyberphysical systems, monitor environments, and interact with the physical world without human intervention.

Features:
webcam_panel): Free in-chat buttons (拍一张 / 再拍 / 关掉); Pro placeholders onlyInstall:
pip install botbridge-webcam-mcp
Start the MCP server:
webcam-mcp
The server starts on http://127.0.0.1:8000/sse by default (loopback only).
You can test the server using any MCP client, e.g., MCP Inspector (install via npx @modelcontextprotocol/inspector).
| Option | Type | Default | Description |
|---|---|---|---|
--host | string | 127.0.0.1 | Server host address |
--port | integer | 8000 | Server port |
--camera-index | integer | 0 | Webcam device index |
--photo-width | integer | 1920 | Default photo width in pixels |
--photo-height | integer | 1080 | Default photo height in pixels |
--video-width | integer | 640 | Default video frame width in pixels |
--video-height | integer | 480 | Default video frame height in pixels |
--version | - | - | Show version and exit |
# Start on custom port
webcam-mcp --port 9000
# Use different camera (e.g., external USB webcam)
webcam-mcp --camera-index 1
# Custom photo resolution
webcam-mcp --photo-width 1280 --photo-height 720
# Opt-in LAN exposure (unauthenticated! see Security below)
WEBCAM_MCP_ALLOW_LAN=1 webcam-mcp --host 0.0.0.0
The SSE transport has no authentication. Anyone who can reach the SSE endpoint can trigger your webcam to take photos and record video.
127.0.0.1, the default).--host to a non-loopback address (e.g. 0.0.0.0 or a LAN IP)
prints a loud warning at startup and is refused unless you set
WEBCAM_MCP_ALLOW_LAN=1.Add to your claude_desktop_config.json:
{
"mcpServers": {
"webcam": {
"url": "http://localhost:8000/sse"
}
}
}
Location of config file:
~/Library/Application Support/Claude/claude_desktop_config.json%APPDATA%\Claude\claude_desktop_config.json~/.config/Claude/claude_desktop_config.jsonAny MCP client supporting SSE transport can connect to:
http://<host>:<port>/sse
take_photoCaptures a single high-resolution photo from the webcam.
Parameters: None
Returns: JPEG image
Example usage in Claude:
Can you take a photo and describe what you see?
record_videoRecords video frames over a specified duration.
Parameters:
duration_seconds (float, optional): Recording duration in seconds
Returns: List of JPEG frames
Example usage in Claude:
Record a 10-second video and analyze any movement you detect.
On macOS, you need to grant camera permissions:
If you see "Camera unavailable" errors:
webcam-mcp is runningwebcam-mcp --camera-index 1To find available cameras:
import cv2
for i in range(10):
cap = cv2.VideoCapture(i)
if cap.isOpened():
print(f"Camera {i}: Available")
cap.release()
else:
print(f"Camera {i}: Not available")
Then use --camera-index with the correct number.
If your camera doesn't support the requested resolution, the server will:
Check logs for messages like:
WARNING: Requested resolution 1920x1080, but camera provided 1280x720
# Install in editable mode with dev dependencies
pip install -e ".[dev]"
# Run all tests
pytest
# Run with verbose output
pytest -v
# Run specific test file
pytest tests/test_camera.py
All tests use mocked camera hardware, so no physical webcam is required for testing.
To tag and release a new version, push a new commit to main with a new __version__ string.
This will trigger a new tag and a new release push to PyPI.