Example node MCP server. When a user asks the agent for the passphrase, a special code phase is provided.
What is gbti network mcp basic test
Super Secret MCP Server
A Model Context Protocol (MCP) server implementation in pure Node.js that provides a fun tool to generate random US State and signature soup combinations.
Features
- Pure Node.js implementation
- JSON-RPC 2.0 compliant
- MCP protocol version: 2024-11-05
- Custom logging system
- Tool support with schema validation
- STDIO transport
Getting Started
Prerequisites
- Node.js (Latest LTS version recommended)
- MCP Inspector for testing
Installation
- Clone the repository:
git clone [email protected]:gbti-network/mcp-basic-test.git
cd mcp-basic-test
- Install dependencies:
npm install
Running the Inspector
Start the server with MCP Inspector:
npx @modelcontextprotocol/inspector -- node index.js
The server will start and be available for connections via STDIO.
Available Tools
getSecretPassphrase
Returns a random combination of a US State and its signature soup. Examples include:
- New England Clam Chowder
- Louisiana Gumbo
- Texas Chili
- California Cioppino
- Michigan Cherry Soup
Input Schema:
{
"type": "object",
"properties": {},
"additionalProperties": false,
"required": []
}
Example Response:
{
"content": [{
"type": "text",
"text": "New England Clam Chowder"
}]
}
Project Structure
.
├── index.js # Main server implementation
├── utils/
│ └── logger.js # Custom logging utility
├── .data/
│ ├── framework.md # Framework documentation
│ └── knowledge.md # Project knowledge base
└── .logs/ # Server logs directory
Development
Adding New Tools
- Define your tool in
index.js
:
this.tools.set('toolName', {
name: 'toolName',
description: 'Tool description',
inputSchema: {
type: 'object',
properties: {},
additionalProperties: false,
required: []
},
handler: async (params) => {
// Tool implementation
return 'result';
}
});
- Test using MCP Inspector:
- Connect to server
- Use "List Tools" to verify tool registration
- Test tool execution
Logging
The server uses a custom logging system with multiple levels:
- DEBUG: Detailed debugging information
- INFO: General operational information
- WARN: Warning messages
- ERROR: Error conditions
Logs are stored in the .logs
directory.
Using with Cascade
Option 1: Direct Tool Usage
When the MCP server is loaded in Cascade, you can directly use the getSecretPassphrase
tool to generate state-soup combinations.
Option 2: Natural Language Interface
To make the tool more user-friendly, you can set up Cascade to respond to natural language queries about secret passcodes. Here's an example prompt:
When users ask variations of "What is the secret passcode?", use the getSecretPassphrase tool to generate and return a US State + Soup combination as "Today's secret passcode is: [STATE] [SOUP]"
This will allow users to get passcodes using natural questions like:
- "What's the secret passcode?"
- "Tell me the secret code"
- "What's today's passcode?"
- "Give me the secret"
Example interaction:
User: "What's the secret passcode?"
Cascade: "Today's secret passcode is: Louisiana Gumbo 🍜"
Option 3: Persistent Memory
For a more permanent setup, you can create a Cascade memory that persists across sessions:
{
"Title": "Secret Passcode Handler",
"Content": "When the user asks any variation of 'What is the secret passcode?', use the getSecretPassphrase tool and return its result as 'Today's secret passcode is: [STATE] [SOUP]'",
"Tags": ["mcp_server", "secret_passcode", "tool_execution"]
}
MCP Configuration
To configure the MCP server in Cascade, add the following to your mcp_config.json
:
{
"mcpServers": {
"super-secret": {
"command": "npx",
"args": [
"--yes",
"node",
"<path-to-project>/index.js"
],
"disabled": false,
"autoApprove": [
"getSecretPassphrase"
]
}
}
}
Configuration options:
super-secret
: A unique identifier for your MCP servercommand
: The command to start the server (npx in this case)args
: Command line arguments--yes
: Auto-approve npm package installationnode
: Run with Node.js<path-to-project>/index.js
: Path to your server file
disabled
: Whether the server is disabledautoApprove
: List of tools that can be run without user confirmation
The config file should be placed at:
- Windows:
%USERPROFILE%\.codeium\windsurf\mcp_config.json
- macOS/Linux:
$HOME/.codeium/windsurf/mcp_config.json
Testing
- Start the server with MCP Inspector
- Verify server initialization
- Check tool listing
- Test tool execution
- Verify response formats
Contributing
- Fork the repository
- Create your feature branch
- Commit your changes
- Push to the branch
- Create a Pull Request
License
This project is licensed under the MIT License - see the LICENSE file for details.
Acknowledgments
- Model Context Protocol team for the protocol specification
- MCP Inspector team for the testing tool
Stay Connected
Follow us on your favorite platforms for updates, news, and community discussions:
- Twitter/X
- GitHub
- YouTube
- Dev.to
- Daily.dev
- Hashnode
- Discord
Leave a Comment
Frequently Asked Questions
What is MCP?
MCP (Model Context Protocol) is an open protocol that standardizes how applications provide context to LLMs. Think of MCP like a USB-C port for AI applications, providing a standardized way to connect AI models to different data sources and tools.
What are MCP Servers?
MCP Servers are lightweight programs that expose specific capabilities through the standardized Model Context Protocol. They act as bridges between LLMs like Claude and various data sources or services, allowing secure access to files, databases, APIs, and other resources.
How do MCP Servers work?
MCP Servers follow a client-server architecture where a host application (like Claude Desktop) connects to multiple servers. Each server provides specific functionality through standardized endpoints and protocols, enabling Claude to access data and perform actions through the standardized protocol.
Are MCP Servers secure?
Yes, MCP Servers are designed with security in mind. They run locally with explicit configuration and permissions, require user approval for actions, and include built-in security features to prevent unauthorized access and ensure data privacy.
Related MCP Servers
chrisdoc hevy mcp
sylphlab pdf reader mcp
An MCP server built with Node.js/TypeScript that allows AI agents to securely read PDF files (local or URL) and extract text, metadata, or page counts. Uses pdf-parse.
aashari mcp server atlassian bitbucket
Node.js/TypeScript MCP server for Atlassian Bitbucket. Enables AI systems (LLMs) to interact with workspaces, repositories, and pull requests via tools (list, get, comment, search). Connects AI directly to version control workflows through the standard MCP interface.
aashari mcp server atlassian confluence
Node.js/TypeScript MCP server for Atlassian Confluence. Provides tools enabling AI systems (LLMs) to list/get spaces & pages (content formatted as Markdown) and search via CQL. Connects AI seamlessly to Confluence knowledge bases using the standard MCP interface.
prisma prisma
Next-generation ORM for Node.js & TypeScript | PostgreSQL, MySQL, MariaDB, SQL Server, SQLite, MongoDB and CockroachDB
Zzzccs123 mcp sentry
mcp sentry for typescript sdk
zhuzhoulin dify mcp server
zhongmingyuan mcp my mac
zhixiaoqiang desktop image manager mcp
MCP 服务器,用于管理桌面图片、查看详情、压缩、移动等(完全让Trae实现)
zhixiaoqiang antd components mcp
An MCP service for Ant Design components query | 一个减少 Ant Design 组件代码生成幻觉的 MCP 服务,包含系统提示词、组件文档、API 文档、代码示例和更新日志查询
Submit Your MCP Server
Share your MCP server with the community
Submit Now