mcpField
3
302_custom_mcp

302_custom_mcp

Local
github.com/302aiDeveloper Tools2Updated 64w ago

About 302_custom_mcp

302_custom_mcp lets users of 302.AI select tools in its backend and create configured MCP servers. It supports several tool categories and can be used with 302.AI's chatbot and other MCP-compatible clients.

Key features

  1. 01Create servers by selecting APIs
  2. 02Configure server-specific tool sets
  3. 03Use BrowserUseTools, FileTools, ImageTools, MathTools, and SandboxTools
  4. 04Switch server configurations by changing the API key
  5. 05Connect to MCP-compatible clients

Use cases

  1. 01Create a server containing selected tools for a task
  2. 02Use configured tools in the 302.AI chatbot
  3. 03Import the server configuration into ChatWise

MCP support

It provides configurable MCP servers that expose selected tools to MCP clients. Different servers use separate keys to retrieve their tool configurations.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"302_custom_mcp": {
"command": "npx",
"args": [
"-y",
"@302ai/custom-mcp"
],
"env": {
"302AI_API_KEY": "<302AI_API_KEY>"
}
}
}
}
Run commandnpx -y @302ai/custom-mcp
Environment variables to set
302AI_API_KEYSecret

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@302ai/custom-mcp

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

🤖 302AI Custom MCP Server🚀✨

A customizable MCP service that supports tool selection and flexible configuration to meet your various needs.

README image

中文 | English | 日本語

README image

Tutorial

Open MCP Server in the menu
README image

Enter a name and select the tools you want to configure.
README image

This is the current list of available tools, which is continuously being updated
README image

After creation, click on the Server name to view the Server configuration
README image

Different Servers use different KEYs to obtain tool configurations. The client only needs to be installed once, no repeated installation required. Switching between different Servers only requires changing the API_KEY.
README image

Open the MCP Server button in the chatbot
README image

Enter the key you just created in 302ai-custom-server
README image README image Turn on the Server switch to start using it.

Taking Chatwise as an example for use in third-party clients Click on the Server name, then click the copy button
README image README image

Open Chatwise settings-tools, click the bottom left corner, import JSON from clipboard
README image README image MCP Server imported successfully, you can now use it normally.

✨ Features ✨

  • 🔧 Quickly generate your own MCP Server by selecting different APIs
  • 🌐 Compatible with: Various MCP-supported clients, including 302.AI's chatbot
  • 💻 Currently includes multiple tool types such as BrowserUseTools, FileTools, ImageTools, MathTools, SandboxTools, with more updates coming

Development

Install dependencies:

npm install

Build the server:

npm run build

For development with auto-rebuild:

npm run watch

Installation

To use with Claude Desktop, add the server config:

On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json On Windows: %APPDATA%/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "302ai-custom-mcp": {
      "command": "npx",
      "args": ["-y", "@302ai/custom-mcp"],
      "env": {
        "302AI_API_KEY": "YOUR_API_KEY_HERE",
        "LANGUAGE": "YOUR_LANGUAGE_HERE"
      }
    }
  }
}

To use with Cherry Studio, add the server config:

{
  "mcpServers": {
    "Li2ZXXJkvhAALyKOFeO4N": {
      "name": "302ai-custom-mcp",
      "description": "",
      "isActive": true,
      "registryUrl": "",
      "command": "npx",
      "args": [
        "-y",
        "@302ai/custom-mcp"
      ],
      "env": {
        "302AI_API_KEY": "YOUR_API_KEY_HERE"
      }
    }
  }
}

To use with ChatWise, copy the following content to clipboard

{
  "mcpServers": {
    "302ai-custom-mcp": {
      "command": "npx",
      "args": ["-y", "@302ai/custom-mcp"],
      "env": {
        "302AI_API_KEY": "YOUR_API_KEY_HERE"
      }
    }
  }
}

Go to Settings -> Tools -> Add button -> Select Import from Clipboard README image

Find Your 302AI_API_KEY here

Using Tutorials

Debugging

Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the MCP Inspector, which is available as a package script:

npm run inspector

The Inspector will provide a URL to access debugging tools in your browser.

✨ About 302.AI ✨

302.AI is an enterprise-oriented AI application platform that offers pay-as-you-go services, ready-to-use solutions, and an open-source ecosystem.✨

  1. 🧠 Integrates the latest and most comprehensive AI capabilities and brands, including but not limited to language models, image models, voice models, and video models.
  2. 🚀 Develops deep applications based on foundation models - we develop real AI products, not just simple chatbots
  3. 💰 Zero monthly fee, all features are pay-per-use, fully open, achieving truly low barriers with high potential.
  4. 🛠 Powerful management backend for teams and SMEs - one person manages, many people use.
  5. 🔗 All AI capabilities provide API access, all tools are open source and customizable (in progress).
  6. 💡 Strong development team, launching 2-3 new applications weekly, products updated daily. Developers interested in joining are welcome to contact us.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.