MCP Toolkit

0 forks

0 stars

Free

What is mcp-toolkit

mcp-toolkit is a versatile Model Context Protocol (MCP) server developed by zxfgds. It's designed to empower AI assistants by enabling them to interact with local systems, files, databases, and external services securely and efficiently. By implementing the MCP, mcp-toolkit extends AI capabilities, allowing them to handle real-world tasks while ensuring security and control. This toolkit is ideal for users looking to integrate AI systems with various data sources and tools, enhancing their ability to process and utilize information in real-time.

How to Use mcp-toolkit

To begin using mcp-toolkit, you need to install it and configure your environment:

Installation: Use the following command to install mcp-toolkit:
```
npm install mcp-toolkit
```

Configuration: Set up a config.json file in your project directory. This file will define your workspace paths, network settings, and database connections. Here’s a basic example:

{
  "workspace": {
    "rootPath": "/path/to/workspace",
    "allowedPaths": ["/allowed/path1", "/allowed/path2"]
  },
  "network": {
    "proxy": "http://proxy-server:port"
  },
  "database": {
    "mysql": {
      "host": "localhost",
      "port": 3306,
      "user": "user",
      "password": "password",
      "database": "dbname"
    }
  }
}

Starting the Server: In your code, you can start the server using:

import { Server } from 'mcp-toolkit';

const server = new Server({
  configPath: './config.json'
});

server.start();

Key Features of mcp-toolkit

mcp-toolkit offers a variety of powerful features to enhance AI functionality:

File System Operations: Perform tasks like reading, writing, and searching files. You can also manage directories and extract code definitions.
Database Integration: Seamlessly connect to MySQL, PostgreSQL, and Redis databases. Manage transactions and execute parameterized queries safely.
GitHub Integration: Interact with GitHub repositories by managing repositories, searching code, and analyzing the tree structure.
Web Capabilities: Extract web page content, utilize Brave search, handle HTTP requests, and manage proxy settings for web interactions.
System Tools: Execute system commands, perform local file searches, analyze stack traces, and use a comprehensive logging system.
Security: Ensures secure operations through configurable workspace restrictions, command execution controls, and database access management.

mcp-toolkit is designed to be user-friendly while providing extensive functionalities to integrate AI systems with real-world data sources. Whether you’re looking to enhance an AI assistant's capabilities or streamline data access across multiple platforms, mcp-toolkit provides a robust solution.

English | 中文

Overview

MCP Toolkit is a comprehensive Model Context Protocol (MCP) server implementation that provides a rich set of tools for AI assistants to interact with the local system, files, databases, and external services. It's designed to extend AI capabilities with real-world interactions while maintaining security and control.

Features

File System Operations
Read and write files
Create and delete directories
Search files with regex patterns
List directory contents
Extract code definitions
Database Integration
MySQL support
PostgreSQL support
Redis support
Transaction management
Parameterized queries
GitHub Integration
Repository management
Code search
File operations
Tree structure analysis
Web Capabilities
Web page content extraction
Brave search integration
HTTP request handling
Proxy support
System Tools
Command execution
Everything search integration
Stack trace analysis
Logging system

Installation

npm install mcp-toolkit

Configuration

Create a config.json file in your project:

 "workspace": {
 "rootPath": "/path/to/workspace",
 "allowedPaths": ["/allowed/path1", "/allowed/path2"]
 "network": {
 "proxy": " // Optional
 "database": {
 "mysql": {
 "host": "localhost",
 "port": 3306,
 "user": "user",
 "password": "password",
 "database": "dbname"
 // Similar configuration for PostgreSQL and Redis

Usage

import { Server } from 'mcp-toolkit';
const server = new Server({
 configPath: './config.json'
server.start();

Tool Details

File Operation Tools

read_file: Read file contents, supports text and binary files
write_to_file: Write or create files
apply_diff: Apply differential modifications to files
insert_content: Insert content at specified positions
search_and_replace: Search and replace file contents
list_files: List directory contents
search_files: Search files using regex
list_code_definition_names: Extract code definitions

Database Tools

db_connect: Connect to databases (MySQL/PostgreSQL/Redis)
db_query: Execute database queries
db_begin_transaction: Start transaction
db_commit_transaction: Commit transaction
db_rollback_transaction: Rollback transaction
db_close: Close database connection

GitHub Tools

github_ls: List repository contents
github_tree: Display repository tree structure
github_search_repo: Search repositories
github_search_code: Search code
github_cat: View file contents
github_list_repos: List user repositories
github_create_repo: Create repository
github_update_repo: Update repository settings
github_delete_repo: Delete repository

Web Tools

read_webpage: Extract webpage content
brave_search: Use Brave search
http_request: Send HTTP requests

System Tools

execute_command: Execute system commands
everything_search: Local file search
logger: Logging
get_stack_trace: Stack trace analysis

Security

Configurable workspace restrictions
Command execution controls
Database access management
Token-based authentication for external services

Contributing

Contributions are welcome! Please read our Contributing Guidelines for details.

License

MIT License

How to Use

To use the mcp-toolkit, follow these steps:

Visit https://github.com/zxfgds/mcp-toolkit
Follow the setup instructions to create an account (if required)
Connect the MCP server to your Claude Desktop application
Start using mcp-toolkit capabilities within your Claude conversations

Additional Information

Created

March 4, 2025

Company

zxfgds

Related MCP Servers

Start building your own MCP Server

Interested in creating your own MCP Server? Check out the official documentation and resources.

Learn More