# Korpus

> Korpus is a freemium MCP server for knowledge and memory. Shared Markdown memory that teams and their AI agents read and write, with an audit trail. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Freemium
- **Platforms:** Web, API, self-hosted
- **Website:** https://korpus.cloud
- **MCP Registry name:** cloud.korpus/korpus
- **Categories:** knowledge and memory, productivity
- **Listing updated:** 2026-11-15

## About

Korpus stores memory as bundles: folders of Markdown concepts for one subject, private or shared. A concept is one document at a path with a type, tags, links and a revision number that counts every edit. Links are typed, such as supersedes or depends on, and each bundle names its own kinds. README and AGENTS concepts tell people where to start and tell agents how to behave in that bundle.

People and agents work side by side. Agents such as Claude, ChatGPT, Cursor or a CI job connect over MCP, each acting for one person and limited to the bundles that person grants, with read, write or path-level access. Every change is stamped with who wrote it, and each write names the revision it read so nobody overwrites blind.

It is hosted in Frankfurt (eu-central-1) and runs serverless on AWS. On the Business plan the same stack can be deployed into your own AWS account, with Microsoft Entra sign-in. Free is for private non-commercial use, and Pro is 10 euros a month or 100 a year.

## Features

- **Bundles of concepts:** Folders of Markdown with types, tags and typed links.
- **Scoped agent access:** Agents get read, write or path-limited access per bundle.
- **Revision-checked writes:** Each write names the revision it read, preventing blind overwrites.
- **Attribution on every change:** Edits show whether a person or their agent wrote them.
- **Catalog templates:** Start from ready bundles such as incident response or security audit.
- **Own-cloud deployment:** Business plan can run in your own AWS account and region.

## Good for

- Give a team's Claude Code the same decisions and runbooks
- Keep a per-client memory and hand it over at project end
- Let a CI job write findings that people can review
- Maintain architecture decision records that agents follow

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http korpus https://mcp.fra.korpus.cloud/
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://mcp.fra.korpus.cloud/
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "korpus": {
      "url": "https://mcp.fra.korpus.cloud/"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "korpus": {
      "type": "http",
      "url": "https://mcp.fra.korpus.cloud/"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "korpus": {
      "serverUrl": "https://mcp.fra.korpus.cloud/"
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "korpus": {
      "type": "http",
      "url": "https://mcp.fra.korpus.cloud/"
    }
  }
}
```

## FAQ

### What does it cost?

Free for private, non-commercial use; Pro is 10 euros a month or 100 a year; Business is on request.

### Where is data hosted?

In Frankfurt (eu-central-1), or in your own AWS account on the Business plan.

### Do agents count as users?

No. The pricing page says agents never count as users.

### Which agents can connect?

Claude, ChatGPT, Cursor or a CI job over MCP.

### Is Korpus free?

Korpus has a free plan, with paid plans for more usage or features.

### How do I add Korpus to Claude Code?

Run this command in your terminal: claude mcp add --transport http korpus https://mcp.fra.korpus.cloud/

### What are the best alternatives to Korpus?

The closest alternatives to Korpus are Codebase Memory, XERJ, Ha MCP, Claude Code Ultimate Guide and Nautilus Compass Memory.

## Alternatives

- [Codebase Memory](https://ai-powered.com/mcp/codebase-memory): Codebase Memory is an open-source MCP server for knowledge and memory.
- [XERJ](https://ai-powered.com/mcp/xerj): XERJ is an open-source MCP server for knowledge and memory.
- [Ha MCP](https://ai-powered.com/mcp/ha-mcp): Ha MCP is an open-source MCP server for productivity.
- [Claude Code Ultimate Guide](https://ai-powered.com/mcp/claude-code-ultimate-guide): Claude Code Ultimate Guide is an open-source MCP server for ai models and llm tooling.
- [Nautilus Compass Memory](https://ai-powered.com/mcp/nautilus-compass-memory): Nautilus Compass Memory is an open-source MCP server for knowledge and memory.
- [Concord MCP](https://ai-powered.com/mcp/concord-mcp): Concord MCP is a freemium MCP server for developer tools.
- [note1](https://ai-powered.com/mcp/note1): note1 is an MCP server for productivity.
- [CalderFlow](https://ai-powered.com/mcp/calderflow): CalderFlow is a free MCP server for design and media.

---
Source: https://ai-powered.com/mcp/korpus
