VidXP MCP server
Commit 14 Nov 2026Memungkinkan AI client untuk mengimpor, mengindeks, dan mencari video berdasarkan ucapan, suara, adegan, aksi, dan wajah yang muncul berulang kali dengan bukti yang dapat diperiksa.
Juga dikenal sebagai grayhatdevelopers/vidxp
- Stars
- 59
- Tools
- —
- Unduhan, 30 hari
- —
- Versi terbaru
- —
- Commit terakhir
- 14 Nov 2026
- Lisensi
- MIT
Apa itu VidXP MCP?
VidXP adalah MCP server. Memungkinkan AI client untuk mengimpor, mengindeks, dan mencari video berdasarkan ucapan, suara, adegan, aksi, dan wajah yang muncul berulang kali dengan bukti yang dapat diperiksa.
Ringkasan dibuat dari README proyek
Tentang VidXP MCP server
VidXP memungkinkan developer dan AI agent untuk mencari melalui library video dengan mendeskripsikan momen tertentu. Engine local-first ini memungkinkan pengguna untuk mengindeks koleksi video dan mengambil konten menggunakan query bahasa alami berdasarkan kata-kata yang diucapkan, suara sekitar, adegan visual, atau aksi yang kompleks. Sistem ini dirancang untuk berjalan di Windows, Linux, dan Apple Silicon macOS, memberikan cara untuk menjaga file pribadi atau proyek tetap berada di mesin Anda sendiri.
Developer dapat mengintegrasikan kapabilitas ini ke dalam aplikasi melalui Python package, HTTP API, atau melalui Model Context Protocol. Server ini mendukung berbagai metode deployment termasuk aplikasi desktop, command-line interface menggunakan uv, atau container Docker untuk home server. Setelah diindeks, sistem menyediakan bukti yang dapat diperiksa seperti frame, klip, atau board untuk memverifikasi hasil pencarian. Tool spesifik seperti vidxp search speech, vidxp search sound, dan vidxp search action memungkinkan pengambilan konten media secara presisi berdasarkan makna semantik, bukan sekadar timestamp.
Apa yang bisa Anda lakukan dengannya
- 1Temukan dialog spesifik yang diucapkanTemukan momen dalam video dengan mengetikkan kata-kata tepat yang diucapkan seseorang.
- 2Cari aksi visualIdentifikasi urutan kejadian dengan mendeskripsikan gerakan yang terjadi di layar.
- 3Identifikasi orang yang muncul berulang kaliKelompokkan dan temukan wajah spesifik yang muncul beberapa kali di berbagai file video Anda.
- 4Ambil kejadian audioTemukan suara spesifik seperti gonggongan anjing atau lalu lintas di dalam library media Anda.
Ditulis berdasarkan README proyek. Setiap use case diperiksa terhadap kutipan dari README tersebut.
Pengecekan otomatis
Berjalan 14 Nov 2026Laporan lengkap →Belum diverifikasi. Sebuah server memerlukan skor 80, tidak ada temuan serius, dan data yang cukup untuk kami periksa. Cara kerja checks · Yang perlu diperbaiki untuk menambah poin
- Source repository terhubung dan dapat dijangkaugrayhatdevelopers/vidxp is public and reachablegithub.com/grayhatdevelopers/vidxp ↗Lolos
- Nama paket mencantumkan repositori ini sebagai sumbernyaTidak diperiksa
- Provenance build (atestasi Sigstore)Tidak diperiksa
- Lisensi open source (OSI)MITspdx.org/licenses/MIT.html ↗Lolos
- Ada commit atau release dalam satu tahun terakhirLast commit or release 2026-11-12github.com/grayhatdevelopers/vidxp ↗Lolos
- OpenSSF ScorecardTidak diperiksa
- Nama package tidak mirip dengan package populerTidak diperiksa
- Tidak ada advisory kritis pada paket atau dependensinyaTidak diperiksa
- Tidak ada instruksi tersembunyi untuk model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersLolos
- Tools yang bersifat destruktif telah diberi labelTidak diperiksa
- Endpoint remote merespons handshake MCPTidak diperiksa
README
Lihat di GitHubFind the moment, not the timestamp
VidXP makes one video—or an entire collection—searchable by meaning:
- Speech search: type what you remember someone saying and jump to the matching moments.
- Scene search: describe what appeared on screen and find the closest visual matches.
- Action search: describe something that happens over several seconds.
- Actor matching: find recurring faces within a video and export a highlighted video for a selected group.
Use it to search years of family videos, add video search to an editing workflow, or let an AI agent answer questions using evidence from your own video library. Your videos can stay on your machine.
Start here
Choose the setup that fits how you want to use VidXP.
1. Desktop app
Download the installer for Windows, Apple Silicon macOS, or Linux from GitHub Releases.
Connect an existing VidXP installation or let the desktop app manage an isolated runtime for you. See the Desktop installation instructions for supported setup options.
2. CLI and local AI assistants
For commands, scripts, and local AI assistants, install uv, then run:
# Install the CPU edition
uv tool install --python 3.14 --torch-backend cpu "vidxp[local-worker,mcp]"
# Check FFmpeg, download models, and verify the installation
vidxp init
vidxp prepare
vidxp doctor
# Print the settings for a local MCP client
vidxp mcp-config
Add the browser interface with:
uv tool install --python 3.14 --torch-backend cpu \
"vidxp[local-worker,mcp,frontend]"
vidxp ui
See the installation guide for client-specific MCP configuration, the HTTP API, and remote server setup.
3. Docker for a server
Run the published all-in-one image on a home server or another single machine:
# Download the search models into the persistent volume
docker run --rm -it \
-v vidxp-data:/var/lib/vidxp \
ghcr.io/grayhatdevelopers/vidxp:latest \
vidxp prepare
# Start the browser interface
docker run --rm --init \
-p 8501:8501 \
-v vidxp-data:/var/lib/vidxp \
ghcr.io/grayhatdevelopers/vidxp:latest
For a long-lived server, pin a published version instead of latest. For a
Coolify deployment, use the published -control and -worker images with
compose.coolify.yaml—no repository build is required.
See the Coolify guide for the complete setup.
What you can do today
- Build searchable libraries from individual videos or whole collections.
- Find speech, sound events, visual scenes, and multi-frame actions by description.
- Ask grounded questions and inspect the supporting boards, frames, or clips.
- Group recurring faces and render highlighted actor overlays.
- Keep personal, client, or project libraries separate.
- Use VidXP through the desktop app, browser, CLI, MCP, or HTTP API.
A first search
The browser app guides you through importing and indexing. The same flow from the command line is:
# Add a video
vidxp media import samplevideo.mp4 --json
# Index the returned media ID
vidxp index create <media-id>
# Find a visual moment
vidxp search scene "a yellow taxi on a city street"
# Find an action or event
vidxp search action "a person opens a door and walks outside"
# Find a sound event
vidxp search sound "a dog barking over traffic noise"
# Find something that was said
vidxp search speech "the bread just came out of the oven"
Results include the source video, timestamps, match score, and the evidence
used to find the moment. Add --media-id <media-id> to search only one video.
Run vidxp --help or vidxp <command> --help for the full command reference.
For applications and AI agents
Use the Python package to add selected VidXP capabilities directly to an application, or use the HTTP API when VidXP runs as a service.
MCP lets AI clients add and index videos, search a library, ask grounded questions, and return inspectable evidence such as boards, frames, and clips. A local client can start VidXP as a program on the same computer. A hosted client connects to a deployed VidXP server.
Codex plugin and skills
VidXP is distributed as a Codex plugin through a Git marketplace hosted in this GitHub repository. It includes three reusable workflows:
- install Desktop or the CLI and connect Codex;
- ingest and index videos; and
- find moments and return inspectable evidence.
Paste this into Codex:
Add https://github.com/grayhatdevelopers/vidxp as a Git plugin marketplace, install the VidXP plugin, then use its $vidxp-install skill to set up VidXP on this computer.
VidXP Desktop can perform the same setup from its Set up in Codex button.
Compatible AI clients can show an interactive upload and evidence-review view. Clients without that interface still receive the same workflow results through ordinary MCP tools.
- Python, HTTP, and MCP installation
- Local HTTP API and MCP server
- Premiere Pro extension
- ChatGPT and Codex plugin integration
- Optional capability packages
- Coolify server setup
Downloads and storage
First setup downloads only the models needed for the capabilities you select. VidXP shows the download size and destination before it starts.
The Desktop-managed Python runtime and its selected dependencies can use approximately 3 GiB.
| Capability | Approximate model download |
|---|---|
| Speech search | 2.64 GiB |
| Sound event search | 0.94 GiB |
| Scene search | 1.43 GiB |
| Action search | 0.93 GiB |
| Actor matching | 37 MiB |
A full local Desktop setup with every search capability uses approximately 9.0 GiB. Leave additional temporary space during installation and for indexes, source videos, and exported results.
By default, the CLI and desktop app share the same VidXP data directory:
| Platform | Default location |
|---|---|
| Windows | %LOCALAPPDATA%\VidXP |
| macOS | ~/Library/Application Support/VidXP |
| Linux | ${XDG_DATA_HOME:-~/.local/share}/VidXP |
Docker keeps the same data in the vidxp-data volume shown above.
Product roadmap
The next product improvements are focused on:
- labeling actor groups and matching the same person across different videos;
- more reliable face tracking across angle, lighting, motion, and occlusion;
- connecting visible people with the dialogue they are speaking;
- better search ranking, time ranges, and natural-language questions across a whole library;
- richer previews, timelines, filters, saved searches, and result playback;
- easier organization for large personal and project video collections;
- faster indexing and supported GPU acceleration; and
- smoother desktop updates, repair, and model management.
VidXP is in beta. Feedback about search quality, actor workflows, and real video-library use cases is especially useful.
Help and project links
- Installation and troubleshooting
- Desktop development
- Coolify deployment
- Changelog
- Issue tracker
- MIT license
Contributing
Contributions are welcome. Read the contribution guide before opening a pull request.
Credits
VidXP began as a student research project by:
The research was conducted with Dr Shahab Tahzeeb at NED University of Engineering and Technology and Saad Bazaz at Grayhat.
VidXP is now built by Grayhat and maintained by community contributors.
Email: info@grayhat.studio
Pertanyaan tentang VidXP MCP
Apa yang bisa saya cari dalam video menggunakan VidXP?
Anda dapat mencari berdasarkan kata-kata yang diucapkan, kejadian suara, adegan visual, aksi multi-frame, dan wajah yang muncul berulang kali. Setiap hasil menyertakan video sumber, timestamp, skor kecocokan, dan bukti pendukung.
Bagaimana cara menggunakan VidXP dengan AI client melalui MCP?
Install mcp extra, lalu jalankan vidxp mcp-config untuk mencetak pengaturan bagi local MCP client. MCP client dapat menambahkan dan mengindeks video, mencari di dalam library, serta mengajukan pertanyaan berbasis data.
Apakah video saya akan keluar dari mesin saya?
Tidak, VidXP bersifat local-first sehingga video Anda tetap berada di mesin Anda. Client yang di-host akan terhubung ke server VidXP yang sudah di-deploy.
Berapa banyak ruang disk yang dibutuhkan oleh model pencarian?
Download model berkisar antara sekitar 37 MiB untuk actor matching hingga 2.64 GiB untuk speech search. Setup lokal lengkap dengan semua kapabilitas menggunakan sekitar 9.0 GiB.
Apakah saya memerlukan API key atau login untuk menggunakan VidXP?
README tidak menyebutkan adanya API key, token, atau login OAuth untuk menggunakan VidXP secara lokal melalui desktop app, CLI, MCP, atau HTTP API.

