# mcp-video

> Video editing MCP server for AI agents. 83 tools, 858 tests collected, 3 interfaces. Works with Claude Code, Cursor, and any MCP client. Local, fast, free.

- **URL**: https://www.freshcrate.ai/projects/mcp-video
- **Author**: Pastorsimon1798
- **Category**: MCP Servers
- **Latest version**: `v1.5.1` (2026-06-04)
- **License**: Apache-2.0
- **Source**: https://github.com/Pastorsimon1798/mcp-video
- **Homepage**: https://pastorsimon1798.github.io/mcp-video/
- **Language**: Python
- **GitHub**: 5 stars, 6 forks
- **Registry**: github (`Pastorsimon1798/mcp-video`)
- **Tags**: `agent-tools`, `ai-agents`, `ai-video`, `animation`, `claude`, `claude-code`, `cursor`, `ffmpeg`, `mcp`, `python`

## Description

Video editing MCP server for AI agents. 83 tools, 858 tests collected, 3 interfaces. Works with Claude Code, Cursor, and any MCP client. Local, fast, free.

## Recent releases

| Version | Date | Urgency | Changes |
| --- | --- | --- | --- |
| `v1.5.1` | 2026-06-04 | High | Patch release for Glama/package-builder compatibility.  Fixed: - Removed the unpublished meltysynth dependency from optional audio extras so uv, Glama, and package metadata validators can resolve mcp-video. - Updated doctor/runtime guidance for MeltySynth to avoid recommending a nonexistent PyPI package. - Updated repository readiness audit after the intentionally removed /explainer-video Dependabot path. - Added regression coverage so optional extras do not advertise unpublished dependencies. |
| `v1.4.1` | 2026-05-26 | High | ## Highlights  - Added preflight guardrails across high-risk video/audio edit paths: filters, merge, add-audio, overlay, watermark, chroma key, text animation, grid layout, and split screen. - Refreshed docs and metadata for the current 119-tool guardrailed surface.  ## Fixes  - Fixed base installs without optional NumPy extras so public audio facades and CLI/doctor imports stay available. - Added pure-Python fallback coverage for the newer DSP symbols and typed validation errors for invalid fal |
| `v1.4.0` | 2026-05-09 | High | ## What's new in 1.4.0  ### New features - **Hyperframes 0.5 orchestration** — snapshots, inspection, metadata, catalog, website capture, local TTS, transcription, background removal, diagnostics, benchmarks, and richer render controls - **Video repurposing helpers** — dry-run manifests and platform-ready variants with thumbnails, storyboards, and optional release checkpoints - **Real color extraction** — `analyze_video(include_colors=True)` and `video_info_detailed` now return actual dominant c |
| `v1.3.1` | 2026-05-03 | High | ## v1.3.1 — Security Fixes, Bug Fixes, Landing Page Redesign  ### Security - **Command injection fix** — vectors file path validated as absolute in `engine_stabilize.py` - **SSL certificate verification** enabled for AI model downloads in `ai_engine/upscale.py` - **Path redaction** in error messages — no more full filesystem paths leaked  ### Fixed - Proper AI operation timeout (3600s) for demucs/whisper — no more premature kills on long videos - FFmpeg stderr buffer increased from 1MB → 10MB — |
| `v1.3.0` | 2026-04-28 | High | # Changelog  All notable user-facing changes should be recorded here.  This project follows a simple release-note style:  - `Added` for new capabilities. - `Changed` for behavior changes. - `Fixed` for bug fixes. - `Security` for vulnerability fixes.  ## 1.3.0 - 2026-04-28  ### Added  - **Crop by percentage** — `crop()` now accepts `crop_percent` (e.g. `crop_percent=50` for a center 50% crop). Alternative to explicit `width` + `height`. - **Orientation-aware metadata** — `VideoInfo` now exposes |
| `v1.2.5` | 2026-04-23 | High | Bug fixes from comprehensive 81-tool testing: - FFmpeg filter escaping fixes - design_quality serialization and output path fixes - Remotion template fixes (imports, braces, paths) - layout.py ffprobe parsing fix - Landing page redesign (no video) - docs: test results and SKOOL post |
| `v1.2.2` | 2026-04-22 | High | ## Release v1.2.2  ### Security - Fixed TOCTOU race conditions and sanitized numeric values in FFmpeg filters (#134) - Added `_validate_output_path()` and rolled it out across all engines (#135) - Hardened AI engine resource guards for scene detection, spatial audio, stem separation, transcription, and upscaling (#136, #141, #142) - Hardened direct download paths with timeout and size limits (#142) - Fixed design quality security and SRT format safety issues (#131)  ### Added - Client-side valid |
| `v1.2.1` | 2026-04-19 | High | ## v1.2.1  This release aligns the published project version with the current package metadata and wraps the post-audit trust and maintainability work.  ### Changed  - Prepared the 1.2.1 package metadata and public badge. - Improved runtime error contracts and diagnostics. - Repaired repository trust rails for deploys, packages, tests, and AI extras. - Added GitHub community, governance, maintainer, support, and discovery metadata. - Added AI-agent discovery files including `llms.txt`, `robots.t |
| `v1.2.0` | 2026-03-31 | Medium | ## Security Hardening (56 tasks)  ### What changed - Centralized validation module (`validation.py`) with parameter validators and allowed-value constants - Shared FFmpeg helpers (`ffmpeg_helpers.py`) — deduplicated escape, validate, run utilities - FFmpeg filter injection prevention on all 82 tools — all numeric params sanitized before interpolation - Color validation hardened — whitelist CSS named colors + hex + 0xRRGGBB format - Null byte rejection on all input paths across all engines - Serv |
| `v1.1.5` | 2026-03-31 | Medium | ## What's Changed  ### CLI Improvements - **New `extract-frame` command** with `--time` flag for extracting frames at specific timestamps - **`edit` command now accepts inline JSON** — no need to create a separate file - **`export-frames` renamed flag** — `--format` → `--image-format` to avoid shadowing global `--format` - **Effect commands auto-generate output** — `effect-vignette`, `effect-glow`, `effect-noise`, `effect-scanlines`, `effect-chromatic-aberration` now auto-generate output paths w |

## Citation

- HTML: https://www.freshcrate.ai/projects/mcp-video
- Markdown: https://www.freshcrate.ai/projects/mcp-video.md
- Dependencies JSON: https://www.freshcrate.ai/api/projects/mcp-video/deps

_Generated by freshcrate.ai. Indexes github releases for AI-agent ecosystem packages._