Next MCP Server

Next MCP Server

An MCP server that enables LLMs to interact with NEXT structured data, providing tools for retrieving highlights and clusters.

Category
访问服务器

README

Next MCP server

A NEXT Model Context Protocol (MCP) server that provides tools for interacting NEXT data.

Overview

This MCP server allows Large Language Models (LLMs) like Claude to interact with NEXT structured data. It provides tools for:

  • Getting highlights
  • Getting cluster

The server is built using TypeScript and the MCP SDK, providing a secure and standardized way for LLMs to interface with NEXT.

Installation

Prerequisites

  • Node.js 18 or higher
  • npm
  • NEXT api key

Setup

  1. Install via npm:
# Install globally via npm
npm install -g @collaborne/mcp-server

# Or as a dependency in your project
npm install @collaborne/mcp-server
  1. If building from source:
# Clone the repository
git clone https://github.com/Collaborne/mcp-server.git
cd mcp-server

# Install dependencies and build
npm install
npm run build
  1. Configure NEXT access:

Create a .env file with your AWS configuration:

API_KEY=your-api-key

Or set these as environment variables.

Configuration

The server can be configured using the following environment variables:

Variable Description Default
API_KEY NEXT api key that you can generate from your settings ``

Running the Server

You can run the server with Node.js:

# Using npx (without installing)
npx @collaborne/mcp-server

# If installed globally
npm install -g @collaborne/mcp-server
cd mcp-server

# If running from cloned repository
npm start

# Or directly
node dist/index.js

Debugging on MCP Inspector

To debug the server using MCP Inspector, you can run sh run-inspector.sh

sh run-inspector.sh

Connecting to Claude Desktop

To use this server with Claude Desktop:

  1. Edit your Claude Desktop configuration file:

    • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
    • Windows: %APPDATA%\Claude\claude_desktop_config.json
  2. Add the NEXT MCP server to the configuration:

{
  "mcpServers": {
    "mcp-server": {
      "command": "npx",
      "args": ["@collaborne/mcp-server"],
      "env": {
        "API_KEY": "your-api-key"
      }
    }
  }
}

Important: Please note the following when using the configuration above

  • Replace NEXT_API_KEY with your actual api key from next team-space. Access to the NEXT API is scoped to a specific team-space. Each API token is bound to one team-space and cannot access data outside of it.

💣 If error occurs on Claude Desktop

If you encounter errors with the above configuration in Claude Desktop, try using absolute paths as follows:

# Get the path of node and mcp-server
which node
which @collaborne/mcp-server
{
  "globalShortcut": "",
  "mcpServers": {
    "next": {
      "command": "your-absolute-path-to-node",
      "args": ["your-absolute-path-to-mcp-server/dist/index.js"],
      "env": {
        "API_KEY": "your-api-key",
      }
    }
  }
}

Available Tools

next-get-highlights

Lists available NEXT highlights that the server has permission to access. This tool is limited to one team-space

Parameters:

  • searchFilters (required): filters for highlights based on the user query

Example input:

What are the user frustrations and issues mentioned in the last week 

Example output:

{
  "searchFilters": {
    "dateFilter": "last week",
    "typeFilters": [
      "Pain Point"
    ]
  }
}

next-get-clusters

Lists available NEXT clusters that the server has permission to access. This tool is limited to one team-space

Parameters:

  • searchQuery (required): search query for clusters based on the user query

Example input:

Summarize the main topics 

Example output:

{
  "searchQuery": "main topics"
}

Security Considerations

  • The server will only access team-space specific data

Usage with Claude

When interacting with Claude in the desktop app, you can ask it to perform NEXT operations like:

  • "Summarize highlights about X topic"
  • "What are the main pain points mentioned in clusters"

Claude will use the appropriate MCP tool to carry out the request and show you the results.

License

MIT

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