MCPgee
MCPgee
MCPgeeMCPgee

Tome

v1.0.0•Developer Tools•stable

a magical LLM desktop client that makes it easy for *anyone* to use LLMs and MCP

geminillmllm-clientllmslocal-llm
Share:
620
Stars
0
Downloads
0
Weekly
0/5
View on GitHub

What is Tome?

Tome is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to magical llm desktop client that makes it easy for *anyone* to use llms and mcp

a magical LLM desktop client that makes it easy for *anyone* to use LLMs and MCP

This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • a magical LLM desktop client that makes it easy for *anyone*

Use Cases

Magical LLM desktop client
Gemini and local LLM support
MCP client interface
runebookai

Maintainer

LicenseApache-2.0
Languagesvelte
Versionv1.0.0
UpdatedMay 22, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux
View SourceBrowse All Servers

Installation

Manual Installation

npx tome

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Tome

Tome is an open-source, beginner-friendly LLM desktop client built with Svelte that makes it easy for anyone — including non-developers — to chat with AI models and connect MCP servers through a simple graphical interface. It supports remote providers (Google Gemini, OpenAI, and OpenAI-compatible endpoints) as well as local models via Ollama, LM Studio, and Cortex, with a built-in MCP tab for installing and managing MCP servers directly from the Smithery.ai registry. Users choose Tome when they want the power of MCP-connected AI without the complexity of editing JSON config files or running command-line tools.

Prerequisites

  • Windows or macOS (Linux support coming soon)
  • At least one LLM provider: an OpenAI API key, a Google Gemini API key, or Ollama running locally for private/offline use
  • No coding experience required — Tome is a no-code desktop application
  • Optional: uvx or npx available on PATH if you plan to install CLI-based MCP servers
1

Download and install Tome

Visit the Tome GitHub releases page at https://github.com/runebookai/tome/releases and download the appropriate installer for your OS: a .exe for Windows or a .dmg for macOS. Run the installer to complete setup.

2

Connect an LLM provider

On first launch, Tome will prompt you to configure an LLM provider. Enter your API key for OpenAI or Google Gemini, or point Tome at your local Ollama endpoint (http://localhost:11434/v1 by default).

3

Install an MCP server via the MCP tab

Navigate to the MCP tab in the Tome sidebar. Click 'Install MCP Server' and browse the Smithery.ai registry for one-click installs, or enter a custom uvx/npx command manually. Example: install the fetch MCP server.

# Equivalent CLI command for reference (Tome runs this for you):
uvx mcp-server-fetch
4

Start chatting with MCP tools active

Return to the Chat tab and start a conversation. Tome will automatically make installed MCP tools available to the model. You can see tool calls and reasoning steps in the enhanced UI display.

5

Tune model parameters

Adjust context window size and temperature via the settings panel for each conversation. These settings persist per-model across sessions.

Tome Examples

Client configuration

Tome manages MCP servers through its UI, but here is the equivalent JSON configuration for a fetch MCP server as Tome would store it internally.

{
  "mcpServers": {
    "fetch": {
      "command": "uvx",
      "args": ["mcp-server-fetch"]
    }
  }
}

Prompts to try

Example prompts to use in Tome once an LLM and MCP servers are configured.

- "Fetch the content of https://news.ycombinator.com and summarize the top 5 stories"
- "Use the local Ollama model to explain quantum entanglement in simple terms"
- "Search for recent papers on retrieval-augmented generation and list the key findings"
- "Set up a scheduled daily summary of my favorite RSS feed at 9am"
- "Connect to the filesystem MCP server and list the files in my Downloads folder"

Troubleshooting Tome

MCP server fails to start after installation via Tome

Ensure the required runtime is on your system PATH. For uvx-based servers, run pip install uv and verify uv is accessible. For npx-based servers, install Node.js 18+. Tome runs the install command in a subprocess and needs these tools available.

Ollama models are not appearing as an option in Tome

Confirm Ollama is running: open a terminal and run ollama list. Then in Tome's provider settings, add a custom endpoint with base URL http://localhost:11434/v1 and a blank API key. Restart Tome after saving.

Tool calls from MCP servers show no output in the chat

Check the Labs section in Tome settings for tool call visibility options. Ensure the installed MCP server is marked as enabled in the MCP tab (green indicator). Some servers require a model that explicitly supports tool use — try switching to GPT-4o or Gemini 1.5 Pro.

Frequently Asked Questions about Tome

What is Tome?

Tome is a Model Context Protocol (MCP) server that magical llm desktop client that makes it easy for *anyone* to use llms and mcp It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Tome?

Follow the installation instructions on the Tome GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Tome?

Tome works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Tome free to use?

Yes, Tome is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.

Learn More About MCP Servers

Getting Started with MCP

Set up your first MCP server in minutes

MCP Setup Guide

Configure MCP in Claude, Cursor & VS Code

All MCP Tutorials

18+ hands-on guides for developers

MCP FAQ

40+ answers about Model Context Protocol

Tome Alternatives — Similar Developer Tools Servers

Looking for alternatives to Tome? Here are other popular developer tools servers you can use with Claude, Cursor, and VS Code.

Ecc

★ 188.2k

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

Javaguide

★ 155.8k

Java 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发

Gemini CLI

★ 104.5k

A secure MCP server that wraps the Google Gemini CLI, allowing clients to query Gemini models using local OAuth sessions without requiring an API key. It provides tools for model interaction and diagnostics with built-in protection against command in

Awesome MCP Servers

★ 87.3k

⭐ Curated list of Model Context Protocol (MCP) servers - tools that extend Claude Desktop, Cursor, Windsurf, and other MCP clients with custom capabilities.

MCP Servers

★ 86.0k

Model Context Protocol Servers

CC Switch

★ 77.5k

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io

Browse More Developer Tools MCP Servers

Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Developer ToolsBrowse All Servers

Quick Config Preview

{ "mcpServers": { "tome": { "command": "npx", "args": ["-y", "tome"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Tome?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides
Explore All ServersRead Our Guides