MCP server for GroupDocs.Viewer — render pages as PNG and inspect view info via AI agents.
Groupdocs MCP server is a locally run integration for AI assistants that speak the Model Context Protocol. MCP server for GroupDocs.Viewer — render pages as PNG and inspect view info via AI agents.
MCP server that exposes GroupDocs.Viewer as AI-callable tools for Claude, Cursor, GitHub Copilot, and other MCP agents.
Once Groupdocs is connected, these are the calls the assistant has available:
RenderPage — Renders a single document page as a PNG image and returns it inline (plus saves a copy to storage as _page.png). Supports PDF, WordGetViewInfo — Returns file type, page count, and per-page dimensions as JSON — without rendering. Useful as a pre-flight check before deciding which page(s) toYou will need 3 environment variables: GROUPDOCS_MCP_STORAGE_PATH, GROUPDOCS_LICENSE_PATH, GROUPDOCS_MCP_OUTPUT_PATH. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client. The configuration blocks on this page cover the common clients.
This sits in the file and storage access group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Groupdocs's toolset — RenderPage, GetViewInfo — is a fair guide to whether it matches your workflow. It is maintained by groupdocs-viewer; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against Groupdocs's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| RenderPage | Renders a single document page as a PNG image and returns it inline (plus saves a copy to storage as <source-stem>_page<N>.png). Supports PDF, Word, Excel, PowerPoint, ODT, RTF, HTML, and 170+ more formats; optional pass |
| GetViewInfo | Returns file type, page count, and per-page dimensions as JSON — without rendering. Useful as a pre-flight check before deciding which page(s) to render. Optional password for protected documents. |
{
"mcpServers": {
"groupdocs-viewer": {
"type": "stdio",
"command": "dnx",
"args": ["GroupDocs.Viewer.Mcp", "--yes"],
"env": {
"GROUPDOCS_MCP_STORAGE_PATH": "/path/to/documents"
}
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| GROUPDOCS_MCP_STORAGE_PATH | Filesystem location the server is allowed to use. | Optional |
| GROUPDOCS_LICENSE_PATH | Filesystem location the server is allowed to use. | Optional |
| GROUPDOCS_MCP_OUTPUT_PATH | Filesystem location the server is allowed to use. | Optional |
Scoped local file access — read, write, search and reorganise files in directories you explicitly allow.
Search and read your Drive — Docs, Sheets and files become context your assistant can actually use.
Query, modify and analyse local SQLite databases in conversation — the fastest way to chat with a data file.
Build a programmable telecommunications stack for connecting telephony services with the Internet via a cloud-based utility.
Chat with your second brain — search, read and write vault notes through the Local REST API.
Connects AI models to an Obsidian knowledge base for direct access and manipulation of notes and folders.