Works with the AI Agents you already use
CCTV Guardian for Muse
Control EZVIZ cloud cameras from chat — snapshots, PTZ moves, video recordings, and scheduled motion alerts with AI descriptions. No local network needed, everything goes through the EZVIZ cloud API.
$2
CCTV Guardian for Muse
Example session with this skill installed
Take a snapshot of the terrace camera and then move it slightly to the left to see the entrance.
- Read your context and instructions
- Compiled the cctv guardian
I have successfully accessed the terrace camera and performed the requested actions.
Camera Operations Result
| Action | Camera Alias | Status | Output File |
|---|---|---|---|
| Initial Snapshot | terrace | Success | ~/.cctv-guardian/snapshots/terace_init_20231027.jpg |
| PTZ Move | terrace | Moved Left (2s) | Success |
| Final Snapshot | terrace | Success | ~/.cctv-guardian/snapshots/terace_post_move.jpg |


Next steps
- Check the entrance area in the second image for any obstructions.
- If the angle is still off, I can move it further left or adjust the zoom.
- Use "record the terrace" if you need a short video clip of the entrance.
Connects securely to your tools. The creator never sees your data.
About this skill
Managing EZVIZ security cameras usually requires a proprietary mobile app, locking footage and controls away from your development environment. This skill bridges that gap, allowing you to control cloud-connected cameras and monitor motion alerts directly through a chat interface or automated scripts.
What it does
- Remote Control: Triggers snapshots, video recording, and PTZ (Pan-Tilt-Zoom) movements via the EZVIZ cloud API.
- Automated Monitoring: Runs a "Guardian" script to poll for motion alarms and fetch alarm images.
- Vision Integration: Optional support for describing motion events using OpenAI-compatible vision models.
- Notification Routing: Sends alerts to a custom webhook or prints them to stdout for log processing.
- Session Management: Handles cached logins and Multi-Factor Authentication (MFA) challenges through secure prompts.
How it works
- Onboarding: Run the guided setup to securely collect credentials and map camera serial numbers to aliases in
cameras.json. - Commands: Use natural language or direct tool calls to trigger
snapshot.py,ptz.py, orrecord.py. - Observation: The agent automatically displays the resulting image or video file in the chat.
- Scheduling: Set up a system cron or agent timer to execute
guardian_check.pyevery 10 minutes for automated surveillance.
Frameworks & tools
Python 3.9+, pyezvizapi, and requests. Configuration is managed via .env files and JSON state stores located in a customizable home directory.
Why this beats prompting it yourself
Standard LLM prompts cannot interact with hardware or handle the complex authentication flows required by the EZVIZ cloud. This skill provides the specific Python scaffolding and state management needed to maintain persistent sessions and handle MFA.
Use cases
- Monitor a home or office terrace via chat commands.
- Build an automated security log that describes detected motion using AI vision.
- Integrate physical security status into your existing developer dashboard or notification stream.
Known limitations
Does not support local network RTSP streams. PTZ functions only work on supported hardware and will exit with a specific error on fixed-lens models.
Requires EZVIZ cloud account. PTZ movements are not supported on fixed-lens cameras. Guardian schedule more frequent than 5 minutes may trigger API rate limits.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 4 days ago
Requires