What are the runtime requirements?
Node.js v18 or later, npm or yarn, and a valid NPS API key obtained from the National Park Service developer page. Claude Desktop is required for running the MCP server interactively.
@amysatterlee
基本信息
Model Context Protocol (MCP) Server for National Park Services data
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"nps": {
"command": "node",
"args": [
"/<Path to Server>/build/index.js"
],
"env": {
"API_KEY": ""
}
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
This server provides an interface to retrieve National Park Services (NPS) data, including a list of national parks in a given U.S. state and detailed information about a specific national park. It uses the National Park Service API and is designed for use with Claude Desktop.
Install dependencies with npm install, set your NPS API key in a .env file, build with npm run build, and run node ./build/server.js. For Claude Desktop, add the server to claude_desktop_config.json specifying the path to the build and your API key, then restart Claude. Use the tools park-list (stateCode) and park-details (parkCode) or prompts parks-by-state and details-for-park to query data.
Node.js v18 or later, npm or yarn, and a valid NPS API key obtained from the National Park Service developer page. Claude Desktop is required for running the MCP server interactively.
Visit [https://www.nps.gov/subjects/developer/get-started.htm](https://www.nps.gov/subjects/developer/get-started.htm) and follow the instructions to request a free API key.
The server provides two tools: `park-list` (parameter: `stateCode`) and `park-details` (parameter: `parkCode`). It also includes two prompts: `parks-by-state` and `details-for-park` for natural language access.
Add an entry to your `claude_desktop_config.json` with the command `node`, the path to the built `index.js` file, and your API key in the `env` field. Restart Claude Desktop and verify the server is recognized via the tools icon.
All data is retrieved live from the National Park Service API. No local cache or database is used.

Research workbooks your agent keeps current: spreadsheets and memos where every figure cites its primary source (SEC filings, customs records, trial registries), plus data programs such as website traffic for 1,000 domai

Competitive intelligence for AI agents: competitor teardowns, pricing, ads, reviews and momentum, cited and dated. Read-only by default.
Hosted YouTube MCP server for search, video metadata, channel data and timestamped transcripts. Connect Claude, Cursor or other MCP clients with HasData; no YouTube API key required.

17 tools for marketing and SEO research inside Claude Code, Cursor, Codex or ChatGPT: the ads any domain runs on Meta and Google, how a product grew from 12 public sources with every claim linked, your own Search Console

US rental listings for AI assistants: free live search and rent statistics, plus licensed feeds.
评论