Copy for LLM Copy
Copied
Failed
View as Markdown Markdown
Set up agent Agent
Give your coding agent live access to the GroupDocs documentation and API reference through the
GroupDocs Docs MCP server — no install, no API key. Learn more
Claude Code
Cursor
VS Code
Codex
Claude Desktop
Other
Claude Code Cursor VS Code Codex Claude Desktop Other claude mcp add --transport http groupdocs-docs https://docs.groupdocs.com/mcpAlso process documents locally
The GroupDocs.Merger MCP server lets your agent work with files on your machine; they are never uploaded. It needs the .NET 10 SDK or Docker.
claude mcp add groupdocs-merger -- dnx GroupDocs.Merger.Mcp --yesFolders, licensing and more → Add to Cursor Or add it to ~/.cursor/mcp.json:
{
"mcpServers": {
"groupdocs-docs": { "url": "https://docs.groupdocs.com/mcp" }
}
}Also process documents locally
The GroupDocs.Merger MCP server lets your agent work with files on your machine; they are never uploaded. It needs the .NET 10 SDK or Docker.
Set up the GroupDocs.Merger MCP server → Install in VS Code Or add it to .vscode/mcp.json in your workspace:
{
"servers": {
"groupdocs-docs": { "type": "http", "url": "https://docs.groupdocs.com/mcp" }
}
}Also process documents locally
The GroupDocs.Merger MCP server lets your agent work with files on your machine; they are never uploaded. It needs the .NET 10 SDK or Docker.
Set up the GroupDocs.Merger MCP server → codex mcp add groupdocs-docs --url https://docs.groupdocs.com/mcpAlso process documents locally
The GroupDocs.Merger MCP server lets your agent work with files on your machine; they are never uploaded. It needs the .NET 10 SDK or Docker.
codex mcp add groupdocs-merger -- dnx GroupDocs.Merger.Mcp --yesFolders, licensing and more → In Claude Desktop or claude.ai, open Settings → Connectors → Add custom connector, and paste this URL:
https://docs.groupdocs.com/mcpAlso process documents locally
The GroupDocs.Merger MCP server lets your agent work with files on your machine; they are never uploaded. It needs the .NET 10 SDK or Docker.
Set up the GroupDocs.Merger MCP server → Any MCP client that supports remote (HTTP) servers:
{
"mcpServers": {
"groupdocs-docs": { "url": "https://docs.groupdocs.com/mcp" }
}
}No MCP support? Point your agent at https://docs.groupdocs.com/merger/mcp/llms.txt — every page also has a Markdown version at its URL + .md.
Also process documents locally
The GroupDocs.Merger MCP server lets your agent work with files on your machine; they are never uploaded. It needs the .NET 10 SDK or Docker.
Set up the GroupDocs.Merger MCP server → get_document_info returns the file type, page count, size, and per-page dimensions without modifying anything. It is the natural precondition check: how many pages are there, and are these files even the same format? Example prompt: “How many pages does each of these have?”
Tool description (as the AI agent sees it):
Returns the file type, page count, size, and per-page dimensions of a document as JSON, without modifying the file. Supports PDF, DOCX, XLSX, PPTX, and 30+ more document formats. Call this tool whenever the user asks to inspect a document, check its page count, or get its details — useful as a precondition check before Merge or Split (e.g. ‘how many pages does this PDF have?’). Do NOT pre-check whether the file exists — just pass the filename the user provided. Returns a JSON object with fields fileName, fileType, fileFormat, extension, pageCount, size, and pages (array of { number, width, height, visible }). On failure, the response text starts with ‘Document-info lookup failed for’ followed by the underlying exception type, message, and inner-exception chain.
Name Type Required Description fileobject yes The document — see FileInput shape passwordstring no Password for protected documents
{
"name" : "get_document_info" ,
"arguments" : {
"file" : {
"filePath" : "report.pdf"
}
}
}
A JSON object with fileName, fileType, pageCount, sizeBytes, and pages (width and height per page).
Two things it prevents: asking split for a page that does not exist, and merging a DOCX into a set of PDFs because nobody checked the extensions.
On failure the text starts with Document-info lookup failed for, followed by the exception type and message.
“How many pages does each of these documents have?” “Are these all PDFs?” “What is the page size of this document?” We value your opinion. Your feedback will help us improve our documentation.