Agentset
About
RAG MCP for your [Agentset](https://agentset.ai/) data.
Details
- Author
- agentset-ai
- GitHub stars
- 30
- Downloads
- 279
- Categories
- Search, Community, Other
Jump to
- Connects to Agentset RAG platform via MCP protocol
- Requires API key and namespace ID for authentication
- Supports custom tool descriptions and tenant IDs
- Runs via npx, yarn dlx, or pnpm dlx
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
AgentsetCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Install and run using npm, yarn, or pnpm with an Agentset API key and namespace ID. Configure it as an MCP server in Claude by adding a JSON entry with AGENTSET_API_KEY and AGENTSET_NAMESPACE_ID environment variables. Optional parameters include custom tool descriptions (-d) and tenant IDs (-t).
knowledge-base-retrieve
Look up information in the Knowledge Base. Use this tool when you need to: - Find relevant documents or information on specific topics - Retrieve company policies, procedures, or guidelines - Access product specifications or technical documentation - Get contextual information to answer company-specific questions - Find historical data or information about projects
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"agentset": {
"agentset": {
"command": "npx",
"args": [
"-y",
"@agentset/mcp@latest"
],
"env": {
"AGENTSET_API_KEY": "agentset_xxx",
"AGENTSET_NAMESPACE_ID": "ns_xxx"
}
}
}
}
}McpServers
{
"agentset": {
"command": "npx",
"args": [
"-y",
"@agentset/mcp@latest"
],
"env": {
"AGENTSET_API_KEY": "agentset_xxx",
"AGENTSET_NAMESPACE_ID": "ns_xxx"
}
}
}Agentset MCP
MCP server for Agentset, an open-source platform for Retrieval-Augmented Generation (RAG). Designed for developers who want to build intelligent, document-based applications quickly and efficiently.
[![npm version][npm-badge]][npm]
[![License][license-badge]][license]
[![Build Status][build-badge]][build]
[![Downloads][downloads-badge]][npm]
[![Size][size-badge]][npm]
Installation
using npm:
AGENTSET_API_KEY=your-api-key npx @agentset/mcp --ns your-namespace-id
using yarn:
AGENTSET_API_KEY=your-api-key yarn dlx @agentset/mcp --ns your-namespace-id
using pnpm:
AGENTSET_API_KEY=your-api-key pnpm dlx @agentset/mcp --ns your-namespace-id
Adding to Claude
{
"mcpServers": {
"agentset": {
"command": "npx",
"args": ["-y", "@agentset/mcp@latest"],
"env": {
"AGENTSET_API_KEY": "agentset_xxx",
"AGENTSET_NAMESPACE_ID": "ns_xxx"
}
}
}
}
Tips
Passing namespace id as an environment variable
AGENTSET_API_KEY=your-api-key AGENTSET_NAMESPACE_ID=your-namespace-id npx @agentset/mcp
Passing a custom tool description
AGENTSET_API_KEY=your-api-key npx @agentset/mcp --ns your-namespace-id -d "Your custom tool description"
Passing a tenant id:
AGENTSET_API_KEY=your-api-key npx @agentset/mcp --ns your-namespace-id -t your-tenant-id
API Reference
Visit the full documentation for more details.
<!-- Links -->
[docs]: https://docs.agentset.ai/
[build-badge]: https://github.com/agentset-ai/mcp-server/actions/workflows/release.yml/badge.svg
[build]: https://github.com/agentset-ai/mcp-server/actions/workflows/release.yml
[license-badge]: https://badgen.net/github/license/agentset-ai/mcp-server
[license]: https://github.com/agentset-ai/mcp-server/blob/main/LICENSE
[npm]: https://www.npmjs.com/package/@agentset/mcp
[npm-badge]: https://badgen.net/npm/v/@agentset/mcp
[downloads-badge]: https://img.shields.io/npm/dm/@agentset/mcp.svg
[size-badge]: https://badgen.net/packagephobia/publish/@agentset/mcp
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
