About convertica
convertica is an MCP server for converting documents and images through Convertica's service, aimed at users of AI assistants and MCP clients. It offers more than 35 conversion tools, with files read from and saved to local disk.
Key features
- 01List available converters and options
- 02Convert documents and images
- 03Merge, split, and compress PDFs
- 04Save results locally or to an output directory
Use cases
- 01Convert a PDF report to Word
- 02Merge and compress several PDFs
- 03Change a HEIC photo to JPG
- 04Render a URL as a PDF
MCP support
The MCP server exposes `list_converters` and `convert_file`. The latter invokes Convertica conversion tools on local files and requires `CONVERTICA_API_KEY`.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
npx -y convertica-mcpCONVERTICA_API_KEYSecretAPI key from https://convertica.net/users/api-keys/Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
2Saved tool list · updated 2w ago
This tool takes no parameters.
Details
From the project READMEConvertica MCP Server
Convert files without leaving your AI assistant. Connect Claude, Cursor, Windsurf or any MCP client to Convertica and its 35+ document and image conversion tools.
"Convert ~/Downloads/report.pdf to Word"
"Merge these three PDFs and compress the result"
"Turn this HEIC photo into a JPG"
"Render https://example.com as a PDF"
MCP tools
The server exposes two tools.
list_converters
Lists all 35+ Convertica converters with their file fields and options. Call this first to find the right tool slug for convert_file. Takes no input.
{ "type": "object", "properties": {} }
convert_file
Runs one of convertica.net's 35+ conversion tools on local file(s) and saves the result next to the input (or into output_dir). Requires authentication via the CONVERTICA_API_KEY env var.
{
"type": "object",
"required": ["tool"],
"properties": {
"tool": { "type": "string", "description": "Converter slug from list_converters, e.g. pdf-to-word or pdf-organize/merge" },
"files": { "type": "array", "items": { "type": "string" }, "description": "Absolute paths of input file(s); order matters for multi-file tools" },
"options": { "type": "object", "description": "Tool-specific options as listed by list_converters, e.g. {angle: 90}" },
"output_dir": { "type": "string", "description": "Directory to save the result (default: alongside the first input file)" }
}
}
Supported conversions include: PDF ⇄ Word / Excel / PowerPoint / JPG / HTML / Markdown / Text / EPUB, PDF → PDF/A, HTML / URL → PDF, merge / split / compress / rotate / crop / watermark / sign / protect / unlock PDF, image convert / optimize / HEIC → JPG·PNG·PDF, and more. Full list via list_converters or at convertica.net.
Setup and API key
You need a Convertica API key: subscribe at convertica.net/pricing, then create a key at convertica.net/users/api-keys. API docs: convertica.net/api/docs.
Claude Code
claude mcp add convertica -e CONVERTICA_API_KEY=cvk_live_... -- npx -y convertica-mcp
Claude Desktop / Cursor / Windsurf
{
"mcpServers": {
"convertica": {
"command": "npx",
"args": ["-y", "convertica-mcp"],
"env": { "CONVERTICA_API_KEY": "cvk_live_..." }
}
}
}
Usage notes
- Files are read from and written to your local disk; results are saved next to the input file unless you pass
output_dir. - Conversions run synchronously over HTTPS; processed files are deleted from Convertica's servers right after the response (details).
- API calls are metered against your plan's monthly quota; failed calls are not counted.
Local development
npm install
npm run smoke # protocol check, no key needed
CONVERTICA_API_KEY=... npm run smoke # + one real conversion
License and credits
MIT. Not affiliated with Anthropic; "Convertica" is the service behind convertica.net.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.