Register in AI clients Leave feedback

Register the GroupDocs.Search MCP server in any AI client with the exact config file location and JSON block for each. Restart the client after any registration change.

Note

Every entry below uses Docker, because that is the only channel for this product. The packed tool is 280.9 MiB — the GroupDocs.Search engine is about 200 MiB with its ONNX and SkiaSharp natives — which is over nuget.org’s 250 MB package limit, so dnx and dotnet tool install are not available for this product.

Note

One-click installs pre-fill every supported setting. After installing, edit the placeholder documents folder (/path/to/documents) — that host path is what the container sees as /data, and where the index is written. On Linux, also add "--user", "1000:1000" (your id -u:id -g) — why.

The standard server entry:

{
  "command": "docker",
  "args": [
    "run", "--rm", "-i",
    "-v", "/path/to/documents:/data",
    "ghcr.io/groupdocs-search/search-net-mcp:latest"
  ]
}

Everything after the image name is passed to the server; everything before it configures the container. Environment variables therefore go before the image, as -e flags — see Configuration.

Add to claude_desktop_config.json under the mcpServers key:

• Windows: %APPDATA%\Claude\claude_desktop_config.json
• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Linux: ~/.config/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "groupdocs-search": {
      "type": "stdio",
      "command": "docker",
      "args": [
        "run", "--rm", "-i",
        "-v", "/path/to/documents:/data",
        "ghcr.io/groupdocs-search/search-net-mcp:latest"
      ]
    }
  }
}

claude mcp add groupdocs-search -- docker run --rm -i \
  -v /path/to/documents:/data ghcr.io/groupdocs-search/search-net-mcp:latest

--scope user makes it machine-wide. To search the documents of the repository you are in, run it from the repository root with -v "$(pwd)":/data — search documents in a code repository.

User-level mcp.json (root key servers), or workspace .vscode/mcp.json:

• Windows: %APPDATA%\Code\User\mcp.json · macOS: ~/Library/Application Support/Code/User/mcp.json · Linux: ~/.config/Code/User/mcp.json

{
  "servers": {
    "groupdocs-search": {
      "type": "stdio",
      "command": "docker",
      "args": [ "run", "--rm", "-i",
                "-v", "${workspaceFolder}:/data",
                "ghcr.io/groupdocs-search/search-net-mcp:latest" ]
    }
  }
}

${workspaceFolder} mounts the open folder, so the agent searches the project you have open.

Create .mcp.json in your solution root — same servers shape as VS Code.

~/.cursor/mcp.json (or .cursor/mcp.json in a project), root key mcpServers — same entry as Claude Desktop.

~/.codeium/windsurf/mcp_config.json, root key mcpServers (Settings → Cascade → Manage MCP servers → View raw config), then refresh the server list.

VS Code globalStorage: …/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json, root key mcpServers.

codex mcp add groupdocs-search -- docker run --rm -i \
  -v /path/to/documents:/data ghcr.io/groupdocs-search/search-net-mcp:latest

Or add a [mcp_servers.groupdocs-search] table to ~/.codex/config.toml.

Register manually: Settings → Tools → AI Assistant → Model Context Protocol (MCP) → Add, using the standard entry above.

Replace :latest with :26.10.1 in any entry above. Recommended for shared or committed configurations, so a new release cannot change behaviour under a running workflow.

Ready-made config files for each client live in install/generated/ in the server repository.