Grant the AI octopus access to a portion of your desktop
Config is the same across clients — only the file and path differ.
{
"mcpServers": {
"gnome-mcp-server": {
"command": "<see-readme>",
"args": []
}
}
}Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
Grant the AI octopus access to a portion of your desktop with a Model Context Protocol (MCP) server for the GNOME desktop.
No automated test available for this server. Check the GitHub README for setup instructions.
Five weighted categories — click any category to see the underlying evidence.
No known CVEs.
No package registry to scan.
Click any tool to inspect its schema.
calendarAccess calendar events with configurable lookahead and lookbehind
gnome://calendar
tasksAccess tasks with filtering options for completion and due dates
gnome://tasks
contactsAccess contacts with optional email-only filtering
gnome://contacts
Be the first to review
Have you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Others in productivity
Persistent memory using a knowledge graph
Official Miro MCP server - Supports context to code and creating diagrams, docs, and data tables.
a self-hosted project management & Kanban solution + Instant shareable boards
All-in-one local AI hub for Obsidian — LLM chat with vault tools, MCP servers, RAG, workflow automation, encryption, and edit history. Fully private, no cloud required.
MCP Security Weekly
Get CVE alerts and security updates for Gnome Mcp Server and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
Grant the AI octopus access to a portion of your desktop with a Model Context Protocol (MCP) server for the GNOME desktop.
To build and install the MCP server to your system:
cargo install --path .
The resulting binary will typically be under ~/.cargo/bin/gnome-mcp-server.
To use this MCP server, you need to configure an MCP client. The configuration varies slightly from client to client, but this is the information that you will need:
stdiognome-mcp-server (assuming ~/.cargo/bin is in your PATH)[] (empty list)The following is a list of general-purpose MCP clients known to work on Linux (in alphabetical order):
| Name | Description | Open Source | Local LLM Support | Documentation |
|---|---|---|---|---|
| goose | AI agent by Block (creators of Square) | ✅ | ✅ | Docs |
| LM Studio | Desktop app for running local LLMs | ❌ | ✅ | Docs |
| Speed of Light | Native GNOME MCP client | ✅ | ✅ | Docs |
Know of other MCP clients that work on Linux? Please submit a PR to add them to this table.
Coding-specific agents like Claude Code, OpenAI Codex, Gemini CLI, VS Code Copilot, or Cursor also support MCP, but they typically rely on cloud models and have limited or no support for on-device LLMs.
For additional MCP clients, see this section in the official documentation.
By default, all tools and resources are enabled. Create a configuration file to customize behavior:
./gnome-mcp-config.json (current directory)~/.config/gnome-mcp/config.json (user config)/etc/gnome-mcp/config.json (system config)"calendar": {
"days_ahead": 30, // Days to look ahead (default: 30)
"days_behind": 0 // Days to look behind (default: 0)
}
"tasks": {
"include_completed": true, // Include completed tasks (default: true)
"include_cancelled": false, // Include cancelled tasks (default: false)
"due_within_days": 0 // Filter by due date, 0 = all (default: 0)
}
"contacts": {
"email_only": false // Include only contacts with emails (default: false)
}
send_notificationlaunch_applicationopen_fileset_wallpaperset_volumeConfig:
"audio": {
"volume_step": 10 // Default step size (default: 10)
}
media_controlquick_settingstake_screenshotConfig:
"screenshot": {
"interactive": false // Default interactive mode (default: false)
}
window_management