Tome

Tome is a MacOS application (support for Windows and Linux is coming soon) developed by the Runebook team. It aims to simplify the use of local large language models (LLMs) with MCP servers. By integrating Ollama and managing MCP servers, users can quickly start chatting with MCP-powered models without dealing with complex configurations.

Artificial intelligence chatbots Developer tools #Local LLM #MCP tool #Model management #Rapid deployment .TypeScript

rating : 2.5 points

downloads : 41

update time : 2025-04-29

What is Tome?

Tome is an application designed specifically for MacOS (support for Windows and Linux is coming soon). It aims to simplify the use of local large language models (LLMs) with MCP servers. Developed by the Runebook team, it provides an intuitive interface to manage MCP servers without the need to manually handle complex configurations or command-line tools.

How to use Tome?

After installing Tome and Ollama, simply paste the MCP server command (e.g., `uvx mcp-server-fetch`) in the MCP tab of Tome to quickly connect and start interacting with the model.

Use cases

Suitable for developers, researchers, or any users interested in local LLM and MCP technologies, especially non-technical users who want to avoid complex configurations.

Main Features

One-click MCP server managementAutomatically handle the installation and configuration of MCP servers without manually operating uv/npm or editing JSON files.

Ollama integrationSupports local or remote Ollama instances for flexible model connection configuration.

User-friendly interfaceA simple chat interface that lowers the technical threshold, making it easy for non-technical users to use.

Advantages and Limitations

Advantages

Completely local-first, giving users full control over their data

Can be used without programming or configuration experience

Supports quick switching between different MCP servers and models

Limitations

Currently only supports MacOS (other platforms are coming soon)

Relies on Ollama as the backend

There may be stability issues in the technical preview version

How to Use

Install necessary software

Download and install Tome and Ollama. Ollama can be a local or remote instance.

Install a model that supports tool calls

Install a model that supports tool calls in Ollama, such as Qwen2.5 7B or 14B.

Add an MCP server

In the MCP tab of Tome, paste the MCP server command (e.g., `uvx mcp-server-fetch`) and install it.

Start chatting

Interact with your MCP-powered model in the chat interface and try to make it perform tasks such as getting network information.

Usage Examples

Get the top story on Hacker NewsAsk the model to get the current top story on Hacker News through the Fetch MCP server

Local data queryAfter configuring an appropriate MCP server, query information in local files or databases

Frequently Asked Questions

Which operating systems does Tome support?

How much RAM do I need to run larger models?

How can I report issues or make suggestions?

Related Resources

Tome download page

Get the latest version of the Tome application

Ollama official website

Download and manage local LLM models

Runebook Discord community

Join the community to get help and share experiences

MCP server repository

Explore more available MCP servers

🚀 Tome Introduction

Tome is a magical tool for connecting local large language models (LLMs) via MCP servers.

🎉 Tome is Here

Tome is an application designed specifically for MacOS (support for Windows and Linux is coming soon). Developed by the Runebook team, it aims to help users connect their local LLMs to MCP servers. Tome manages your MCP servers, so you don't have to deal with uv/npm or JSON files. Simply connect it to Ollama, paste some MCP server configurations, and you can start chatting with MCP-powered models in seconds.

This is our first technical preview version, so be prepared to encounter some imperfections. Given the rapidly changing (and somewhat unstable) nature of MCP servers and local models, we recommend joining our Discord community to share tips, tricks, and any issues you encounter. Also, remember to star this repository on GitHub to stay informed about updates and new features.

🚀 Quick Start

Compatibility and Requirements

MacOS (Sequoia 15.0 or higher is recommended).
Ollama (either locally or remotely; you can configure any Ollama URL in the settings).

Download the latest version of Tome

Getting Started Quickly

We'll be updating our website in the coming weeks with more detailed documentation and step-by-step tutorials. Here's a quick interim guide:

Install Tome and Ollama.
Install a supported model (we recommend Qwen2.5, either the 14B or 7B version, depending on your memory).
Open the MCP tab in Tome and install your first MCP server (Fetch is a good starting point; just paste uvx mcp-server-fetch in the server field).
Start chatting with an MCP-powered model! Try getting the top stories from Hacker News.

🌟 Project Vision

Our goal is to make local large language models and MCP more accessible to everyone. We're building a tool that allows you to interact freely with LLMs in any situation, whether you're an engineer, a tech enthusiast, or an ordinary user.

Core Principles

Tome is Local-First: You have control over where your data goes.
Tome is for Everyone: You don't need to manage programming languages, package managers, or JSON configuration files.

Future Plans

Model Support: Currently, Tome uses Ollama for model management, but we plan to expand support to other LLM engines and even cloud models. Let us know your requirements.
Operating System Support: We plan to add support for Windows first, followed by Linux.
More features are in development.