Tome

What is Tome about?

Tome provides a user‑friendly interface for interacting with both cloud‑based and locally hosted large language models. It integrates Model Context Protocol servers so models can call tools such as search engines, file systems, or custom APIs directly from the chat window.

How to use Tome?

1. Download the Windows or macOS installer from the latest release page.
2. Install the app and launch it.
3. Add an LLM provider – preset options include OpenAI, Google Gemini, Ollama, LM Studio, etc. Provide the endpoint URL and any required API key.
4. Open the MCP tab, add or install MCP servers (e.g., uvx mcp-server-fetch), and enable the ones you need.
5. Start a chat, or create a scheduled task to run a prompt at a chosen interval.

Key Features

• Beginner‑friendly experience – no JSON, Docker, or programming required.
• Scheduled tasks – run prompts hourly or at specific times each day.
• Broad model support – remote (Gemini, OpenAI‑compatible) and local (Ollama, LM Studio, Cortex, etc.).
• One‑click MCP server management – install, enable, disable servers from the UI; supports npm, uvx, node, and python servers.
• Integration with Smithery.ai registry – thousands of pre‑built MCP servers available.
• Context window & temperature customization.
• Native tool‑call handling – clear UI separation of tool calls and model reasoning.

Use Cases

• Personal knowledge assistant – ask the model to fetch latest news, retrieve files, or query APIs.
• Automation of routine tasks – schedule daily summaries, report generation, or data pulls.
• Prototyping AI‑augmented workflows – combine local models for privacy‑first projects with remote models for high‑quality output.
• Educational tool – let non‑technical users experiment with LLMs and tool integration.

FAQ

Q: Do I need to be a developer to use Tome? A: No. The UI handles model connections and MCP server setup without any code.

Q: Can I run everything offline? A: Yes. Use Ollama or Qwen3 locally and install only local MCP servers.

Q: Which operating systems are supported? A: macOS and Windows are currently supported; Linux support is planned.

Q: How do I add a custom MCP server? A: In the MCP tab, enter the command to launch the server (e.g., uvx mcp-server-fetch) and save. The server will appear in the list for activation.

Q: Where can I find community help? A: Join the Discord community linked in the README for tips, troubleshooting, and feature requests.

Tome - Magical AI Spellbook

Tome

Tome is a desktop app that lets anyone harness the magic of LLMs and MCP. Download Tome, connect any local or remote LLM and hook it up to thousands of MCP servers to create your own magical AI-powered spellbook.

What is MCP? MCP stands for Model Context Protocol and lets your LLM access tools - like search engines, your filesystem, or APIs like Scryfall or Atlassian

🫥 Want it to be 100% local, 100% private? Use Ollama and Qwen3 with only local MCP servers to cast spells in your own pocket universe. ⚡ Want state of the art cloud models with the latest remote MCP servers? You can have that too. It's all up to you!

🏗️ This is a Technical Preview so bear in mind things will be rough around the edges. Join us on Discord to share tips, tricks, and issues you run into. Star this repo to stay on top of updates and feature releases!

🪄 Features

• 🧙 Streamlined Beginner Friendly Experience
  • Simply download and install Tome and hook up the LLM of your choice
  • No fiddling with JSON, Docker, python or node
  • Chat with MCP-powered models within minutes
• 🗓 NEW! Scheduled Tasks
  • Schedule prompts to run hourly or at a specific time every day
  • Support for any model or MCP servers
• 🤖 AI Model Support
  • Remote: Google Gemini, OpenAI, any OpenAI API-compatible endpoint
  • Local: Ollama, LM Studio, Cortex, any OpenAI API-compatible endpoint
• 🔮 Enhanced MCP support
  • UI to install, remove, turn on/off MCP servers
  • npm, uvx, node, python MCP servers all supported out of box
• 🏪 Integration into Smithery.ai registry
  • Thousands of MCP servers available via one-click installation
• ✏️ Customization of context windows and temperature
• 🧰 Native support for tool calls and reasoning models
  • UI enhancements that clearly delineate tool calls and thinking messages

Demo

https://github.com/user-attachments/assets/0775d100-3eba-4219-9e2f-360a01f28cce

Getting Started

Requirements

• MacOS or Windows (Linux coming soon!)
• LLM Provider of your choice: Ollama or Gemini API key are easy/free
• Download the latest release of Tome

Quickstart

1. Install Tome
2. Connect your preferred LLM provider - OpenAI, Ollama and Gemini are preset but you can also add providers like LM Studio by using http://localhost:1234/v1 as the URL
3. Open the MCP tab in Tome and install your first MCP server (Fetch is an easy one to get started with, just paste uvx mcp-server-fetch into the server field).
4. Chat with your MCP-powered model! Ask it to fetch the top story on Hacker News.

Vision

We want to make local LLMs and MCP accessible to everyone. We're building a tool that allows you to be creative with LLMs, regardless of whether you're an engineer, tinkerer, hobbyist, or anyone in between.

Core Principles

• Tome is local first: You are in control of where your data goes.
• Tome is for everyone: You shouldn't have to manage programming languages, package managers, or json config files.

What's Next

We've gotten a lot of amazing feedback in the last few weeks since releasing Tome but we've got big plans for the future. We want to break LLMs out of their chatbox, and we've got a lot of features coming to help y'all do that.

• Scheduled tasks: LLMs should be doing helpful things even when you're not in front of the computer.
• Native integrations: MCP servers are a great way to access tools and information, but we want to add more powerful integrations to interact with LLMs in unique. ways
• App builder: we believe long term that the best experiences will not be in a chat interface. We have plans to add additional tools that will enable you to create powerful applications and workflows.
• ??? Let us know what you'd like to see! Join our community via the links below, we'd love to hear from you.

Community

Discord Blog Bluesky Twitter