Connect RAG knowledge base to Agentset platform

Agentset MCP Server is an MCP connector that exposes Agentset's Retrieval-Augmented Generation (RAG) platform to AI clients like Claude. It enables developers to build intelligent, document-based applications that combine large language models with proprietary or domain-specific knowledge bases stored in Agentset namespaces.

Use Agentset MCP Server when you need an AI assistant to answer questions grounded in your own document collections, technical documentation, or knowledge bases. It's ideal for building customer support bots, internal knowledge assistants, or any application where you want to connect AI clients to curated document sets stored in Agentset. Use it when you already have or plan to maintain documents in Agentset namespaces.

Do NOT use this connector if you don't have an Agentset account or namespace set up - the server requires both an API key and namespace ID to function. Avoid it if your use case doesn't involve document retrieval or if you need real-time data that isn't stored in static documents.

You provide an Agentset API key and namespace ID as environment variables or command-line arguments. Optionally, you can specify a tenant ID for multi-tenant scenarios and a custom tool description.

The server connects to the Agentset platform API to perform operations on your namespace.

The connector can be added to Claude Desktop by configuring your MCP servers file:

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

The server is distributed via npm and can be run with npx, yarn dlx, or pnpm dlx. It connects to the Agentset platform API to perform retrieval operations.

This connector is designed for developers building document-based AI applications who want to leverage RAG without building retrieval infrastructure from scratch. It's particularly suited for teams using Agentset as their RAG platform. Product teams building internal tools, customer support automation, or knowledge management systems will find it useful for connecting their document repositories to conversational AI interfaces.

Installation is straightforward with package managers:

AGENTSET_API_KEY=your-api-key npx @agentset/mcp --ns your-namespace-id

For advanced configurations, you can pass environment variables separately or customize the tool description:

AGENTSET_API_KEY=your-api-key npx @agentset/mcp --ns your-namespace-id -d "Your custom tool description"