MCP Media Processing Server
A server for media processing, offering powerful video and image manipulation using FFmpeg and ImageMagick.
MCP Media Processing Server
A Node.js server implementing Model Context Protocol (MCP) for media processing operations, providing powerful video and image manipulation capabilities.
Features
- Video processing and conversion
- Image processing and manipulation
- Media compression
- Video trimming and editing
- Image effects and watermarking
Prerequisites
Before using this server, make sure you have the following dependencies installed on your system:
-
FFmpeg: Required for video processing operations
- macOS:
brew install ffmpeg - Ubuntu/Debian:
sudo apt-get install ffmpeg - Windows: Download from FFmpeg official website
- macOS:
-
ImageMagick: Required for image processing operations
- macOS:
brew install imagemagick - Ubuntu/Debian:
sudo apt-get install imagemagick - Windows: Download from ImageMagick official website
- macOS:
How to use
Add this to your claude_desktop_config.json:
NPX
{
"mcpServers": {
"mediaProcessor": {
"command": "npx",
"args": [
"-y",
"mcp-media-processor@latest"
]
}
}
}
API
Tools
Video Operations
-
execute-ffmpeg
- Execute any FFmpeg command with custom options
- Inputs:
inputPath(string): Absolute path to input video fileoptions(string[]): Array of FFmpeg command optionsoutputPath(string, optional): Absolute path for output fileoutputFilename(string, optional): Output filename
-
convert-video
- Convert video to different format
- Inputs:
inputPath(string): Absolute path to input video fileoutputFormat(string): Desired output format (e.g., mp4, mkv, avi)outputPath(string, optional): Custom output pathoutputFilename(string, optional): Custom output filename
-
compress-video
- Compress video file
- Inputs:
inputPath(string): Absolute path to input video filequality(number, optional): Compression quality (1-51, lower is better quality)outputPath(string, optional): Custom output pathoutputFilename(string, optional): Custom output filename
-
trim-video
- Trim video to specified duration
- Inputs:
inputPath(string): Absolute path to input video filestartTime(string): Start time in format HH:MM:SSduration(string): Duration in format HH:MM:SSoutputPath(string, optional): Custom output pathoutputFilename(string, optional): Custom output filename
Image Operations
-
compress-image
- Compress PNG image using ImageMagick
- Inputs:
inputPath(string): Absolute path to input PNG imagequality(number, optional): Compression quality (1-100)outputPath(string, optional): Custom output pathoutputFilename(string, optional): Custom output filename
-
convert-image
- Convert image to different format
- Inputs:
inputPath(string): Absolute path to input image fileoutputFormat(string): Desired output format (e.g., jpg, png, webp, gif)outputPath(string, optional): Custom output pathoutputFilename(string, optional): Custom output filename
-
resize-image
- Resize image to specified dimensions
- Inputs:
inputPath(string): Absolute path to input image filewidth(number, optional): Target width in pixelsheight(number, optional): Target height in pixelsmaintainAspectRatio(boolean, optional): Whether to maintain aspect ratiooutputPath(string, optional): Custom output pathoutputFilename(string, optional): Custom output filename
-
rotate-image
- Rotate image by specified degrees
- Inputs:
inputPath(string): Absolute path to input image filedegrees(number): Rotation angle in degreesoutputPath(string, optional): Custom output pathoutputFilename(string, optional): Custom output filename
-
add-watermark
- Add watermark to image
- Inputs:
inputPath(string): Absolute path to input image filewatermarkPath(string): Absolute path to watermark image fileposition(string, optional): Position of watermark (default: "southeast")opacity(number, optional): Watermark opacity (0-100)outputPath(string, optional): Custom output pathoutputFilename(string, optional): Custom output filename
-
apply-effect
- Apply visual effect to image
- Inputs:
inputPath(string): Absolute path to input image fileeffect(string): Effect to apply (blur, sharpen, edge, emboss, grayscale, sepia, negate)intensity(number, optional): Effect intensity (0-100)outputPath(string, optional): Custom output pathoutputFilename(string, optional): Custom output filename
License
This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.
関連サーバー
AgentSignal
Collective intelligence for AI shopping agents — 23 MCP tools for buyer intelligence, seller analytics, price alerts, and trend tracking.
Healthcare RAG
A healthcare-focused RAG server using Groq API and Chroma for information retrieval from patient records.
Synmerco
Fully autonomous AI agent commerce — USA-built, 1.75% fee (11x cheaper than ACP). 15 tools for escrow, reputation, spending limits, collateral staking, referrals. ERC-8004 on 4 chains. $1K insurance. Stripe fiat + crypto. npx @synmerco/mcp-server
AGA MCP Server
Cryptographic runtime governance for AI agents. 20 tools. Sealed policy artifacts, continuous measurement, tamper-evident proof. Ed25519 + SHA-256.
AstraCipher
Cryptographic identity MCP server for AI agents using W3C DIDs, Verifiable Credentials, and NIST post-quantum cryptography (ML-DSA-65 FIPS 204).
CraftedTrust
Independent trust verification for MCP servers. 7-factor trust scoring, 3,400+ packages indexed, embeddable badges, free API. Agents can query trust scores natively via MCP protocol.
AsusWRT MCP Server
Model Context Protocol server for secure AsusWRT router administration via SSH. Provides 42+ read-only monitoring tools and guarded mutation tools for managing AsusWRT/Merlin routers.
OpenPaper MCP
Generate academic papers with verified citations via AI
Geneva Forecasting MCP
MCP server that gives Claude and other AI assistants enterprise-grade time series forecasting powered by the Geneva Forecasting engine - the same forecasting engine shipped in Oracle products for 25+ years.
Librarian Nexus
Librarian Nexus is a shared knowledge library for AI agents. Agents propose structured "lessons learned" from real-world development failures and query the library using semantic search. Lessons include epic (what was attempted), failure (what went wrong), and solution (what fixed it). Queries are paywalled at $0.01 USDC via the x402 payment protocol on Base.