MCPgee
MCPgee
MCPgeeMCPgee

Agentset

v1.0.0•Knowledge & Memory•stable

The open-source RAG platform: built-in citations, deep research, 22+ file formats, partitions, MCP server, and more.

agentic-ragaiai-agentsai-sdkchatbots
Share:
1,989
Stars
0
Downloads
0
Weekly
0/5
View on GitHub

What is Agentset?

Agentset is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to open-source rag platform: built-in citations, deep research, 22+ file formats, partitions, mcp server, and more.

The open-source RAG platform: built-in citations, deep research, 22+ file formats, partitions, MCP server, and more.

This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • The open-source RAG platform: built-in citations, deep resea

Use Cases

Open-source RAG platform with built-in citations
Support for 22+ file formats and deep research
agentset-ai

Maintainer

LicenseMIT License
Languagetypescript
Versionv1.0.0
UpdatedMay 19, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux
View SourceBrowse All Servers

Installation

Manual Installation

npx agentset

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Agentset

Agentset is an open-source Retrieval-Augmented Generation (RAG) platform that exposes your document knowledge base directly to AI models via an MCP server. It supports over 22 file formats, provides built-in citation tracking, and organizes documents into namespaces for multi-tenant use cases. Developers and teams use Agentset to give Claude and other AI models accurate, source-attributed answers drawn from their own private document collections — without building RAG infrastructure from scratch.

Prerequisites

  • Node.js 18+ and npx available on your system
  • An Agentset account and API key from agentset.ai
  • A namespace created in the Agentset dashboard with documents ingested
  • An MCP client such as Claude Desktop or VS Code with MCP support
1

Create an Agentset account and namespace

Sign up at agentset.ai and create a new namespace. A namespace is an isolated document collection (your RAG corpus). Upload your files through the dashboard — Agentset supports PDFs, Word docs, spreadsheets, and 20+ other formats.

2

Retrieve your API key and namespace ID

From the Agentset dashboard, navigate to Settings to find your API key (prefixed agentset_xxx) and note your namespace ID (prefixed ns_xxx). You will need both values for the MCP server configuration.

3

Test the MCP server from the command line

Before configuring a client, verify the server starts correctly by running it manually with your credentials. The --ns flag specifies which namespace to query.

AGENTSET_API_KEY=agentset_xxx npx @agentset/mcp@latest --ns ns_xxx
4

Add Agentset to your MCP client configuration

Configure your MCP client (Claude Desktop, VS Code, etc.) to launch the Agentset MCP server with your API key and namespace ID passed as environment variables.

{
  "mcpServers": {
    "agentset": {
      "command": "npx",
      "args": ["-y", "@agentset/mcp@latest"],
      "env": {
        "AGENTSET_API_KEY": "agentset_xxx",
        "AGENTSET_NAMESPACE_ID": "ns_xxx"
      }
    }
  }
}
5

Query your documents through the AI model

Once connected, ask your AI model questions that require looking up information from your namespace. The server will retrieve relevant passages with citations and return them to the model.

Agentset Examples

Client configuration

Claude Desktop configuration for the Agentset MCP server using environment variables for authentication.

{
  "mcpServers": {
    "agentset": {
      "command": "npx",
      "args": ["-y", "@agentset/mcp@latest"],
      "env": {
        "AGENTSET_API_KEY": "agentset_xxx",
        "AGENTSET_NAMESPACE_ID": "ns_xxx"
      }
    }
  }
}

Prompts to try

Example questions to ask after connecting to a namespace containing your documents.

- "What does our employee handbook say about the vacation policy?"
- "Summarize the key findings from the Q3 financial report"
- "Find all mentions of the API rate limits in the technical documentation"
- "What are the onboarding steps described in the HR documents?"

Troubleshooting Agentset

Authentication error: invalid API key

Double-check that AGENTSET_API_KEY is set to the full key including the 'agentset_' prefix. Ensure the key is active in your Agentset dashboard under Settings.

No results returned even though documents are uploaded

Confirm that AGENTSET_NAMESPACE_ID matches the namespace ID (ns_xxx) where your documents are stored. It is easy to copy the wrong identifier from the dashboard.

npx command times out during startup

Set UV_HTTP_TIMEOUT=300 in your environment to allow more time for package download on slow connections, or pre-install with 'npm install -g @agentset/mcp' and use the global binary instead.

Frequently Asked Questions about Agentset

What is Agentset?

Agentset is a Model Context Protocol (MCP) server that open-source rag platform: built-in citations, deep research, 22+ file formats, partitions, mcp server, and more. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Agentset?

Follow the installation instructions on the Agentset GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Agentset?

Agentset works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Agentset free to use?

Yes, Agentset is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.

Learn More About MCP Servers

Getting Started with MCP

Set up your first MCP server in minutes

MCP Setup Guide

Configure MCP in Claude, Cursor & VS Code

All MCP Tutorials

18+ hands-on guides for developers

MCP FAQ

40+ answers about Model Context Protocol

Agentset Alternatives — Similar Knowledge & Memory Servers

Looking for alternatives to Agentset? Here are other popular knowledge & memory servers you can use with Claude, Cursor, and VS Code.

MemPalace

★ 52.6k

A local AI memory system that stores all conversations verbatim and organizes them into navigable structures. It provides 19 MCP tools for AI assistants to search and retrieve past decisions, debugging sessions, and architecture debates automatically

Kratos

★ 25.7k

🏛️ Memory System for AI Coding Tools - Never explain your codebase again. MCP server with perfect project isolation, 95.8% context accuracy, and the Four Pillars Framework.

Context Mode

★ 15.4k

An MCP server that preserves LLM context by intercepting large data outputs and returning only concise summaries or relevant sections. It enables efficient sandboxed code execution, file processing, and documentation indexing across multiple programm

Memu

★ 13.7k

Memory for 24/7 proactive agents like OpenClaw.

MemOS

★ 9.3k

MemOS (Memory Operating System) is a memory management operating system designed for AI applications. Its goal is: to enable your AI system to have long-term memory like a human, not only remembering what users have said but also actively invoking, u

Everos

★ 5.4k

Build, evaluate, and integrate long-term memory for self-evolving agents.

Browse More Knowledge & Memory MCP Servers

Explore all knowledge & memory servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Knowledge & MemoryBrowse All Servers

Quick Config Preview

{ "mcpServers": { "agentset": { "command": "npx", "args": ["-y", "agentset"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Agentset?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides
Explore All ServersRead Our Guides