Nerdearla MCP Server

Nerdearla MCP Server

Provides information about Nerdearla events, speakers, and sessions, enabling natural language queries about event data.

Category
访问服务器

README

Nerdearla MCP Server

🚀 Live Server: The server is running at https://mcp.nerdear.la/mcp

An MCP (Model Context Protocol) server that provides information about Nerdearla events, speakers, and sessions. Built with FastMCP and supports streamable HTTP in stateless mode with JSON responses.

Quick Start - Add to VS Code Copilot

To use this MCP server with VS Code Copilot:

  1. Open the command palette in VS Code (Cmd+Shift+P / Ctrl+Shift+P)
  2. Type "MCP: Add Server" and select it
  3. Select "HTTP" as the server type
  4. Enter the server URL: https://mcp.nerdear.la/mcp
  5. Give it a name, any name is fine
  6. Select if you want to save it in your user or workspace settings

You can now ask Copilot about Nerdearla events, speakers, and sessions!

Quick Start - Add to your favourite Agent/IDE

Most Agents/IDEs support MCP servers out of the box. Check your documentation for instructions on how to add a new server.

Local Developtment Setup

This project uses uv for dependency management. Make sure you have uv installed:

# Install uv if you haven't already
curl -LsSf https://astral.sh/uv/install.sh | sh

Then install the project dependencies:

# Clone and navigate to the repository
cd nerdearla-mcp

# Install dependencies with uv
uv sync

Usage

Running the Server

Start the MCP server:

# Using uv
uv run nerdearla-mcp

# Or directly with Python
uv run python -m nerdearla_mcp.server

The server will start on http://localhost:8000/mcp by default.

Development

Project Structure

nerdearla-mcp/
├── nerdearla_mcp/
│   ├── __init__.py
│   └── server.py          # Main MCP server implementation
├── pyproject.toml         # Project configuration and dependencies
├── README.md              # This file
└── ...

Adding New Tools

To add new tools to the server:

  1. Define your tool function in nerdearla_mcp/server.py
  2. Use the @mcp.tool() decorator
  3. Add proper type hints and docstrings
  4. Implement the tool to retrieve the data from an API, file or database as needed

Example:

@mcp.tool()
def get_sponsors(tier: Optional[str] = None) -> List[Dict[str, Any]]:
    """
    Get information about event sponsors.
    
    Args:
        tier: Optional filter by sponsor tier (e.g., "Gold", "Silver", "Bronze")
    
    Returns:
        List of sponsor information
    """
    # Implementation here
    pass

Running Tests

# Run tests with pytest
uv run pytest

Code Formatting

Pre-commit Hooks (Recommended)

This project uses pre-commit hooks to automatically format and lint code before commits:

Install pre-commit hooks:

# Install dependencies (includes pre-commit)
uv sync

# Install the git hooks
uv run pre-commit install

Usage:

  • Hooks run automatically on git commit
  • To run manually on all files: uv run pre-commit run --all-files
  • To skip hooks for a commit: git commit --no-verify

The hooks will automatically:

  • Format code with Black
  • Lint and fix issues with Ruff
  • Format code with Ruff formatter

Configuration

Port Configuration

The server runs on port 8000 by default. You can configure the port using environment variables:

Environment Variable:

export PORT=3000
uv run nerdearla-mcp

Using .env file: Create a .env file in the project root:

PORT=3000

Priority order:

  1. Environment variable PORT
  2. .env file
  3. Default: 8000

Server Configuration

The server uses streamable HTTP transport with the following default settings:

  • Host: 0.0.0.0 (accepts connections from any IP)
  • Port: as described above
  • Path: /mcp (API endpoint)
  • Transport: streamable-http
  • Mode: stateless_http=True

Contributing

  1. Fork the repository
  2. Make your changes
  3. Add tests if applicable
  4. Run the linter and formatter
  5. Submit a pull request

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