Experimental: serves a Model Context Protocol endpoint for AI agents, off by default and authenticated like every other Nextly route. Read-only, and the one tool it exposes reports what the connecting
接入你的智能体
发布者自己的命令。不是 PlugMCP 端点。
用我们的密钥与日志托管一份副本。
npx -y @nextlyhq/[email protected]Claude Code 没有针对本地命令的安装链接。复制下方命令并在终端中运行。
claude mcp add nextlyhq-plugin-mcp -- npx -y @nextlyhq/plugin-mcp@0.0.2-alpha.78在终端中运行。
{ "mcpServers": { "nextlyhq-plugin-mcp": { "command": "npx", "args": [ "-y", "@nextlyhq/[email protected]" ] } }}claude_desktop_config.json
远程 URL 还是本机命令? 两种安装方式的区别
来自发布者
尚未抓取 README。 打开仓库
Experimental: serves a Model Context Protocol endpoint for AI agents, off by default and authenticated like every other Nextly route. Read-only, and the one tool it exposes reports what the connecting credential may read
{ "mcpServers": { "nextlyhq-plugin-mcp": { "command": "npx", "args": [ "-y", "@nextlyhq/[email protected]" ] } }}概览
Experimental: serves a Model Context Protocol endpoint for AI agents, off by default and authenticated like every other Nextly route. Read-only, and the one tool it exposes reports what the connecting credential may read
工具
暂无工具列表。远程服务器在首次健康检查后会获得工具列表。
常见问题
在本页复制适用于 Cursor、Claude Desktop、Claude Code 或 VS Code 的 stdio 配置。它使用发布者的安装方式,而不是 PlugMCP 代理。
此记录未列出必需的环境变量。
@nextlyhq/plugin 通过 stdio 在本地运行。
上次检查时间:2026-11-16。 Experimental: serves a Model Context Protocol endpoint for AI agents, off by default and authenticated like every other Nextly route. Read-only, and the one tool it exposes reports what the connecting credential may read