MCP servers · abhijatsaxena

UVC PTZ Camera: MCP server for USB pan/tilt/zoom cameras

MCP server for USB (UVC) pan/tilt/zoom cameras that confirms each move by comparing camera frames before and after it.

This text was machine-translated from the publisher's own information and has not been checked by a human editor. The publisher's original text is the reference.

This resource was imported automatically from the sources listed below and has not been reviewed by the AI Gate team yet. The description is the publisher's own, as published. Check the repository before installing.

What it does

The server lets an agent aim, nudge, sweep and zoom a USB (UVC) pan/tilt/zoom camera and capture frames from it. Whether a move happened is decided from the picture, not from the device's own position report, which is returned only as a labelled hint. A move that produces no visible change is reported as an error after a bounded retry. The plan_shot tool previews a shot's steps, per-axis travel and duration without moving the camera, and run_shot executes it. The track_start tool keeps a detected face near the centre of the frame in bounded steps, and track_status lists each iteration with its measured offset and applied step.

It suits agents that need to frame a sequence of shots on a USB camera and check that each move actually happened, or that need a camera to follow a person. A simulator backend lets the same tools run without hardware; every result is marked as simulated or not. The motion-change threshold was calibrated on frames from a DJI Osmo Pocket 4P in webcam mode, and the repository keeps the measurements rather than any camera images.

Running it needs one camera connected over USB and no account, cloud service or vendor SDK. The backend can be set to auto, dshow or simulator, and a device can be chosen by part of its name. Configuration goes into the host's MCP settings as arguments or environment variables. A real camera on Windows also needs the DirectShow extras. Face detection uses the optional tracking extra, which bundles OpenCV's face cascade.

Limitations and requirements

A real camera on Windows requires the DirectShow extras. Follow mode is optional and requires the tracking extra. Follow mode has not been run on real hardware; the publisher describes it as the least proven part of the server. Gain and invert must be set to match the camera mount. Each tracking iteration is capped at 25 degrees. Face detection only follows faces, not other subjects. Without hardware, the server runs in simulator mode, which models the camera rather than driving it.

Safety

Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.

  • Runs code or changes an assistant's behaviour

Sources

  • Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
    UVC PTZ Camera

    Control a USB (UVC) pan/tilt/zoom camera, with every move confirmed from the picture.

    v0.2.0
    As shown on registry.modelcontextprotocol.io when we last read it
MCP servers
docker

Docker Hub MCP Server

Docker's MCP server that helps an AI assistant find and compare container images on Docker Hub and, with your token, manage your own repositories and tags.

171 GitHub starsCloud & DevOpsSoftware development
Updated 13 Nov 2026
MCP servers
awslabs

MCP servers for AWS (AWS Labs)

A large open-source collection of MCP servers from AWS Labs for building and operating on AWS: documentation, infrastructure, databases, AI services, cost and more.

9.9K GitHub starsCloud & DevOpsData & databases
Updated 17 Nov 2026
MCP servers
firecrawl

Firecrawl MCP Server (web search and scraping)

Firecrawl's MCP server that lets an AI assistant search the web, turn pages and PDFs into clean Markdown, crawl sites and interact with dynamic pages.

7.8K GitHub starsWeb, search & browserProductivity & automation
Updated 17 Nov 2026
MCP servers
microsoft

Playwright MCP (browser automation)

Microsoft's MCP server that lets an AI assistant open web pages, click, type and read them through a real browser, using the page structure instead of screenshots.

39.6K GitHub starsTesting & QAWeb, search & browser
Updated 17 Nov 2026