The ToolBox MCP Server is an AI-powered automation tool development platform that provides modular architecture, AI assistance, enterprise-grade capabilities, and real-time updates. It allows you to create, manage, and orchestrate tools through a flexible system that integrates with Claude Desktop.
npm install
npm run build
npm run watch
To integrate with the Claude Desktop application, add the following server configuration to the appropriate location:
~/Library/Application Support/Claude/claude_desktop_config.json
%APPDATA%/Claude/claude_desktop_config.json
{
"command": "node",
"args": [
"--inspect=9229",
"/MCP/ToolBox/build/index.js"
],
"env": {
"MONGO_URI": "mongodb://user:password@host:port/db",
"MONGO_INDEX_OPS": "true",
"REDIS_URI": "redis://:password@host:port",
"SSH_server1_URI": "username:password@host:port",
"GEMINI_API_KEY":"GEMINI_API_KEY",
"SSEPORT": "8080"
},
"disabled": false,
"autoApprove": []
}
ToolBox provides various tools that you can use for automation. These tools are loaded from the src/tools
directory and can be invoked through the Claude Desktop interface.
The workflow_tool
allows you to orchestrate complex workflows by chaining multiple tools together:
Resources are generated dynamically as a result of tool execution. For example:
create_note
tool creates a note resource that can be accessed via its URIsummarize_notes
prompt can generate summaries of notes created with the create_note
toolLaunch the server with the inspection flag:
node --inspect=9229 build/index.js
Then, connect to the server using Chrome DevTools by navigating to chrome://inspect
.
Create a .vscode/launch.json
file with the following configuration:
{
"version": "0.2.0",
"configurations": [
{
"type": "node",
"request": "attach",
"name": "ToolBox",
"address": "localhost",
"port": 9229,
"localRoot": "${workspaceFolder}"
}
]
}
Launch the server with the --inspect=9229
flag and attach the VSCode debugger.
Do not configure containers with sensitive data such as API keys or database passwords. Any sensitive data exchanged with the LLM is inherently compromised unless the LLM is running on your local machine.
There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json
file so that it is available in all of your projects.
If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json
file.
To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".
When you click that button the ~/.cursor/mcp.json
file will be opened and you can add your server like this:
{
"mcpServers": {
"cursor-rules-mcp": {
"command": "npx",
"args": [
"-y",
"cursor-rules-mcp"
]
}
}
}
To add an MCP server to a project you can create a new .cursor/mcp.json
file or add it to the existing one. This will look exactly the same as the global MCP server example above.
Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.
The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.
You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.