erickwendel-contributions-mcp

erickwendel-contributions-mcp

An MCP server that enables querying Erick Wendel's contributions across platforms including talks, blog posts, and videos using natural language through AI assistants like Claude and Cursor.

Category
访问服务器

README

erickwendel-contributions-mcp

CI Status npm version npm downloads

A Model Context Protocol (MCP) server that provides tools to query Erick Wendel's contributions across different platforms. Query talks, blog posts, and videos using natural language through Claude, Cursor or similars. This project was built using Cursor IDE with the default agent (trial version).

Quick Start

Use this MCP server directly with Claude Desktop or Cursor without installation:

{
  "mcpServers": {
    "erickwendel-contributions": {
      "command": "npx",
      "args": ["-y", "@erickwendel/contributions-mcp"]
    }
  }
}

Add this configuration to:

  • Claude Desktop: ~/Library/Application Support/Claude/claude_desktop_config.json (macOS)
  • Cursor: ~/.cursor/mcp.json

Available Tools

This MCP server provides the following capabilities:

Tools

  • get-talks: Retrieves a paginated list of talks with optional filtering

    • Supports filtering by ID, title, language, city, country, and year
    • Can return counts grouped by language, country, or city
  • get-posts: Fetches posts with optional filtering and pagination

    • Supports filtering by ID, title, language, and portal
  • get-videos: Retrieves videos with optional filtering and pagination

    • Supports filtering by ID, title, and language
  • check-status: Verifies if the API is alive and responding

Prompts

  • find-content: Generate queries to find specific content by type, topic, and language
  • summarize-activity: Create summaries of content activity by year

Resources

  • erickwendel://about: Server information and capabilities metadata
  • erickwendel://statistics: Content statistics and available queries

Integration with AI Tools

Inspect MCP Server Capabilities

You can inspect this MCP server's capabilities using the MCP Inspector:

npm run inspect

This will show you all available tools, their parameters, and how to use them.

Setup

  1. Make sure you're using Node.js v20+
node -v
# v20.x.x or higher
  1. Clone this repository:
git clone https://github.com/erickwendel/erickwendel-contributions-mcp.git
cd erickwendel-contributions-mcp
  1. Install dependencies:
npm ci
  1. Run the server:
npm start

Integration with AI Tools

Cursor Setup

Add the following configuration to ~/.cursor/mcp.json:

{
  "mcpServers": {
    "erickwendel-contributions": {
      "command": "npx",
      "args": ["-y", "@erickwendel/contributions-mcp"]
    }
  }
}

Make sure Cursor chat is in Agent mode by selecting "Agent" in the lower left side dropdown, then ask "how many videos were published about JavaScript in 2024":

Local Development

For local development, use the absolute path to the project:

{
  "mcpServers": {
    "erickwendel-contributions": {
      "command": "node",
      "args": ["--experimental-strip-types", "ABSOLUTE_PATH_TO_PROJECT/src/index.ts"]
    }
  }
}

Claude Desktop Setup

  1. Go to Claude settings
  2. Click in the Developer tab
  3. Click in edit config
  4. Open the config in a code editor
  5. Add the following configuration to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS):
{
  "mcpServers": {
    "erickwendel-contributions": {
      "command": "npx",
      "args": ["-y", "@erickwendel/contributions-mcp"]
    }
  }
}

Local Development

For local development, use the absolute path to the project:

{
  "mcpServers": {
    "erickwendel-contributions": {
      "command": "node",
      "args": ["--experimental-strip-types", "ABSOLUTE_PATH_TO_PROJECT/src/index.ts"]
    }
  }
}

MCPHost with Ollama (Free Alternative)

If you don't have access to Claude Desktop or Cursor, you can use MCPHost with Ollama as a free alternative.

  1. Install MCPHost:
go install github.com/mark3labs/mcphost@latest
  1. Create a config file (e.g. ./mcp.jsonc):
{
  "mcpServers": {
    "erickwendel-contributions": {
      "command": "npx",
      "args": ["-y", "@erickwendel/contributions-mcp"]
    }
  }
}
  1. Run with Ollama:
ollama pull MODEL_NAME
mcphost --config ./mcp.jsonc -m ollama:MODEL_NAME

Local Development

For local development, update the config:

{
  "mcpServers": {
    "erickwendel-contributions": {
      "command": "node",
      "args": ["--experimental-strip-types", "ABSOLUTE_PATH_TO_PROJECT/src/index.ts"]
    }
  }
}

Example Queries

Here are some examples of queries you can ask Claude, Cursor or any MCP Client:

  1. "How many talks were given in 2023?"

  1. "Show me talks in Spanish"

  1. "Find posts about WebXR"

Development

Features

  • Built with Model Context Protocol (MCP)
  • Full MCP Capabilities: Tools, Prompts, and Resources
  • Type-safe with TypeScript and Zod schema validation
  • Native TypeScript support in Node.js without transpilation
  • Generated SDK using GenQL
  • Modular architecture with separation of concerns
  • Standard I/O transport for easy integration
  • Structured error handling
  • Compatible with Claude Desktop, Cursor, and MCPHost (free alternative)

Note: This project requires Node.js v23+ as it uses the native TypeScript support added in the last year.

Architecture

The codebase follows a modular structure:

src/
  ├── config/      # Configuration settings
  ├── types/       # TypeScript interfaces and types
  ├── tools/       # MCP tool implementations
  ├── utils/       # Utility functions
  ├── services/    # API service layer
  └── index.ts     # Main entry point

Testing

To run the test suite:

npm test

For development mode with watch:

npm run test:dev

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

Author

Erick Wendel

License

This project is licensed under the MIT License - see the LICENSE file for details.

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选