Next MCP Server
An MCP server that enables LLMs to interact with NEXT structured data, providing tools for retrieving highlights and clusters.
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
- 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
- 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
- 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:
-
Edit your Claude Desktop configuration file:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
- macOS:
-
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_KEYwith 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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.