ConvertAgent
@vid-factory
About ConvertAgent
File conversion built for AI agents. CLI, REST API, and MCP server.
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"convertagent": {
"url": "http://localhost:3001/mcp"
}
}
}Tools
2Convert a file from one format to another
List all supported conversion format pairs
Overview
What is ConvertAgent?
ConvertAgent is a self-hosted, open-source file conversion toolkit designed for AI agents. It provides a CLI, REST API, and MCP (Model Context Protocol) server—all sharing one conversion engine—so agents can convert files locally without cloud uploads or per-conversion fees.
How to use ConvertAgent?
Install by cloning the repository, then run npm install and npm run build. Ensure system dependencies (ffmpeg, libreoffice, imagemagick, pandoc) are installed. Use the CLI with convertagent convert <file> --to <format> or start the API server with node dist/api/server.js. For MCP integration, add the server configuration to your MCP client (e.g., Claude Desktop) pointing to http://localhost:3001/mcp or the local script.
Key features of ConvertAgent
- CLI, REST API, and MCP server from one unified engine.
- 20 conversion pairs across documents, images, and audio/video.
- Self-hosted: files never leave your infrastructure.
- Powered by open-source engines (FFmpeg, LibreOffice, ImageMagick, Pandoc).
- No cloud uploads, no API keys, no per-conversion fees.
- Real-file test matrix with 20/20 verified passing.
Use cases of ConvertAgent
- AI agents convert PDF reports to Word documents for editing.
- Extract audio from video files for transcription by an agent.
- Batch convert images (e.g., PNG to WebP) for web optimization.
- Convert markdown to PDF for document generation pipelines.
- Integrate with MCP-compatible clients (e.g., Claude Desktop) for on-the-fly file conversion.
FAQ from ConvertAgent
What dependencies does ConvertAgent require?
ConvertAgent requires Node.js ≥22 and the system engines FFmpeg, LibreOffice, ImageMagick, and Pandoc. On Ubuntu/Debian install them with sudo apt-get install ffmpeg libreoffice imagemagick pandoc.
How do I run ConvertAgent as an MCP server?
After building, start the MCP server by running node dist/mcp/server.js or the API server (which also serves MCP on /mcp). Then configure your MCP client with the appropriate command or URL.
Does ConvertAgent send my files to the cloud?
No. ConvertAgent is self-hosted and runs entirely on your infrastructure. Files remain local; no cloud uploads are involved.
How many file conversions are supported?
ConvertAgent currently supports 20 conversion pairs covering documents (PDF, DOCX, HTML, MD, XLSX, CSV, PPTX), images (
Frequently asked questions
What dependencies does ConvertAgent require?
ConvertAgent requires Node.js ≥22 and the system engines FFmpeg, LibreOffice, ImageMagick, and Pandoc. On Ubuntu/Debian install them with `sudo apt-get install ffmpeg libreoffice imagemagick pandoc`.
How do I run ConvertAgent as an MCP server?
After building, start the MCP server by running `node dist/mcp/server.js` or the API server (which also serves MCP on `/mcp`). Then configure your MCP client with the appropriate command or URL.
Does ConvertAgent send my files to the cloud?
No. ConvertAgent is self-hosted and runs entirely on your infrastructure. Files remain local; no cloud uploads are involved.
How many file conversions are supported?
ConvertAgent currently supports 20 conversion pairs covering documents (PDF, DOCX, HTML, MD, XLSX, CSV, PPTX), images (
Basic information
More Developer Tools MCP servers

directree
coburn2716directree MCP server — query the honest software directory from any AI assistant

Skilder.ai
skilder.aiRun skills and MCP tools like production software: versioned, composed into roles, distributed to every agent from one governed library.
CodeSentinel
icohangar-opsCodebase health as MCP tools: dead code, circular dependencies, coupling, architectural drift.
MCP Server By TestMu AI
TestMu AITestMu AI MCP Server lets developers run, debug, and triage tests through natural language directly from their IDE (Cursor, Claude, GitHub Copilot, and other MCP clients). It exposes five tools — HyperExecute (test orche
Mobbin
MobbinMobbin MCP connects your AI agents to 600,000+ real product screens, so what they build starts with what already works.
Comments