Skip to content
Back to search

chat-mcp

A Desktop Chat App that leverages MCP(Model Context Protocol) to interface with other LLMs.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/ai-ql--chat-mcp/badge.svg)](/listings/ai-ql--chat-mcp)

HTML

<a href="/listings/ai-ql--chat-mcp"><img src="/api/listings/ai-ql--chat-mcp/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Generally, after executing `npm install` for the entire project, the total size of files in the `node_modules` directory typically exceeds 500MB.

If the installation process stalls at less than 300MB and the progress bar remains static, it is likely due to a timeout during the installation of the latter part, specifically Electron.

This issue often arises because the download speed from Electron's default server is excessively slow or even inaccessible in certain regions. To resolve this, you can modify the environment or global variable `ELECTRON_MIRROR` to switch to an Electron mirror site that is accessible from your location.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 211 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # MCP Chat Desktop App
  2. ## A Cross-Platform Interface for LLMs
  3. This desktop application utilizes the MCP (Model Context Protocol) to seamlessly connect and interact with various Large Language Models (LLMs). Built on Electron, the app ensures full cross-platform compatibility, enabling smooth operation across different operating systems.
  4. The primary objective of this project is to deliver a clean, minimalistic codebase that simplifies understanding the core principles of MCP. Additionally, it provides a quick and efficient way to test multiple servers and LLMs, making it an ideal tool for developers and researchers alike.
  5. ## News
  6. This project originated as a modified version of Chat-UI, initially adopting a minimalist code approach to implement core MCP functionality for educational purposes.
  7. Through iterative updates to MCP, I received community feedback advocating for a completely new architecture - one that eliminates third-party CDN dependencies and establishes clearer modular structure to better support derivative development and debugging workflows.
  8. This led to the creation of [Tool Unitary User Interface](https://github.com/AI-QL/tuui), a restructured desktop application optimized for AI-powered development. Building upon the original foundation, TUUI serves as a practical AI-assisted development paradigm, if you're interested, you can also leverage AI to develop new features for TUUI. The platform employs a strict linting and formatting system to ensure AI-generated code adheres to coding standards.
  9. > **📢 Update: June 2025**
  10. > The current project refactoring has been largely completed, and a pre-release version is now available. Please refer to the following documentation for details:
  11. > - [TUUI GitHub Repository](https://github.com/AI-QL/tuui)
  12. > - [TUUI Architecture](https://deepwiki.com/AI-QL/tuui)
  13. > - [TUUI Official Website](https://www.tuui.com/)
  14. ## Features
  15. - Cross-Platform Compatibility: Supports Linux, macOS, and Windows.
  16. - Flexible Apache-2.0 License: Allows easy modification and building of your own desktop applications.
  17. - Dynamic LLM Configuration: Compatible with all OpenAI SDK-supported LLMs, enabling quick testing of multiple backends through manual or preset configurations.
  18. - Multi-Client Management: Configure and manage multiple clients to connect to multiple servers using MCP config.
  19. - UI Adaptability: The UI can be directly extracted for web use, ensuring consistent ecosystem and interaction logic across web and desktop versions.
  20. ## Architecture
  21. Adopted a straightforward architecture consistent with the MCP documentation to facilitate a clear understanding of MCP principles by:
  22. [DeepWiki](https://deepwiki.com/AI-QL/chat-mcp)
  23. ## How to use
  24. After cloning or downloading this repository:
  25. 1. Please modify the `config.json` file located in [src/main](src/main).
  26. Ensure that the `command` and `path` specified in the `args` are valid.
  27. 2. Please ensure that [Node.js](https://nodejs.org/) is installed on your system.
  28. You can verify this by running `node -v` and `npm -v` in your terminal to check their respective versions.
  29. 3. `npm install`
  30. 4. `npm start`
  31. ## Configuration
  32. Create a `.json` file and paste the following content into it. This file can then be provided as the interface configuration for the Chat UI.
  33. - `gtp-api.json`
  34. ```json
  35. {
  36. "chatbotStore": {
  37. "apiKey": "",
  38. "url": "https://api.aiql.com",
  39. "path": "/v1/chat/completions",
  40. "model": "gpt-4o-mini",
  41. "max_tokens_value": "",
  42. "mcp": true
  43. },
  44. "defaultChoiceStore": {
  45. "model": [
  46. "gpt-4o-mini",
  47. "gpt-4o",
  48. "gpt-4",
  49. "gpt-4-turbo"
  50. ]
  51. }
  52. }
  53. ```
  54. You can replace the 'url' if you have direct access to the OpenAI API.
  55. Alternatively, you can also use another API endpoint that supports function calls:
  56. - `qwen-api.json`
  57. ```json
  58. {
  59. "chatbotStore": {
  60. "apiKey": "",
  61. "url": "https://dashscope.aliyuncs.com/compatible-mode",
  62. "path": "/v1/chat/completions",
  63. "model": "qwen-turbo",
  64. "max_tokens_value": "",
  65. "mcp": true
  66. },
  67. "defaultChoiceStore": {
  68. "model": [
  69. "qwen-turbo",
  70. "qwen-plus",
  71. "qwen-max"
  72. ]
  73. }
  74. }
  75. ```
  76. - `deepinfra.json`
  77. ```json
  78. {
  79. "chatbotStore": {
  80. "apiKey": "",
  81. "url": "https://api.deepinfra.com",
  82. "path": "/v1/openai/chat/completions",
  83. "model": "meta-llama/Meta-Llama-3.1-70B-Instruct",
  84. "max_tokens_value": "32000",
  85. "mcp": true
  86. },
  87. "defaultChoiceStore": {
  88. "model": [
  89. "meta-llama/Meta-Llama-3.1-70B-Instruct",
  90. "meta-llama/Meta-Llama-3.1-405B-Instruct",
  91. "meta-llama/Meta-Llama-3.1-8B-Instruct"
  92. ]
  93. }
  94. }
  95. ```
  96. ## Build Application
  97. You can build your own desktop application by:
  98. ```bash
  99. npm run build-app
  100. ```
  101. This CLI helps you build and package your application for your current OS, with artifacts stored in the /artifacts directory.
  102. For Debian/Ubuntu users experiencing RPM build issues, try one of the following solutions:
  103. - Edit `package.json` to skip the RPM build step. Or
  104. - Install `rpm` using `sudo apt-get install rpm` (You may need to run `sudo apt update` to ensure your package list is up-to-date)
  105. # Troubleshooting
  106. ## Error: spawn npx ENOENT - [ISSUE 40](https://github.com/modelcontextprotocol/servers/issues/40)
  107. Modify the `config.json` in [src/main](src/main)
  108. On windows, npx may not work, please refer my workaround: [ISSUE 101](https://github.com/modelcontextprotocol/typescript-sdk/issues/101)
  109. - Or you can use `node` in config.json:
  110. ```json
  111. {
  112. "mcpServers": {
  113. "filesystem": {
  114. "command": "node",
  115. "args": [
  116. "node_modules/@modelcontextprotocol/server-filesystem/dist/index.js",
  117. "D:/Github/mcp-test"
  118. ]
  119. }
  120. }
  121. }
  122. ```
  123. Please ensure that the provided path is valid, especially if you are using a relative path. It is highly recommended to provide an absolute path for better clarity and accuracy.
  124. By default, I will install `server-everything`, `server-filesystem`, and `server-puppeteer` for test purposes. However, you can install additional server libraries or use `npx` to utilize other server libraries as needed.
  125. ## Installation timeout
  126. Generally, after executing `npm install` for the entire project, the total size of files in the `node_modules` directory typically exceeds 500MB.
  127. If the installation process stalls at less than 300MB and the progress bar remains static, it is likely due to a timeout during the installation of the latter part, specifically Electron.
  128. This issue often arises because the download speed from Electron's default server is excessively slow or even inaccessible in certain regions. To resolve this, you can modify the environment or global variable `ELECTRON_MIRROR` to switch to an Electron mirror site that is accessible from your location.
  129. ## Electron builder timeout
  130. When using electron-builder to package files, it automatically downloads several large release packages from GitHub. If the network connection is unstable, this process may be interrupted or timeout.
  131. On Windows, you may need to clear the cache located under the `electron` and `electron-builder` directories within `C:\Users\YOURUSERNAME\AppData\Local` before attempting to retry.
  132. Due to potential terminal permission issues, it is recommended to use the default shell terminal instead of VSCode's built-in terminal.
  133. ## Demo
  134. ### Multimodal Support
  135. ![](https://gcore.jsdelivr.net/gh/AI-QL/.github/public/chat-mcp/demo-multimodal.png)
  136. ### Reasoning and Latex Support
  137. ![](https://gcore.jsdelivr.net/gh/AI-QL/.github/public/chat-mcp/demo-latex.png)
  138. ### MCP Tools Visualization
  139. ![](https://gcore.jsdelivr.net/gh/AI-QL/.github/public/chat-mcp/demo-tools.png)
  140. ### MCP Toolcall Process Overview
  141. ![](https://gcore.jsdelivr.net/gh/AI-QL/.github/public/chat-mcp/demo-toolcall.png)
  142. ### MCP Prompts Template
  143. ![](https://gcore.jsdelivr.net/gh/AI-QL/.github/public/chat-mcp/demo-prompts.png)
  144. ### Dynamic LLM Config
  145. ![](https://gcore.jsdelivr.net/gh/AI-QL/.github/public/chat-mcp/demo-llms.png)
  146. ### DevTool Troubleshooting
  147. ![](https://gcore.jsdelivr.net/gh/AI-QL/.github/public/chat-mcp/demo-devtool.png)

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.