# DM by AuzzurA

> DM by AuzzurA is a freemium MCP server for knowledge and memory. Shared rules, skills and decisions for teams, served to AI agents with human review. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Freemium
- **Platforms:** Web, API
- **Website:** https://auzzura.com
- **MCP Registry name:** io.github.auzzura-team/dm-by-auzzura
- **Categories:** knowledge and memory, productivity
- **Listing updated:** 2026-11-15

## About

DM is a layer that sits between a team's knowledge and the agents doing work. Instead of dumping documents into a prompt, it prepares task-specific context: only approved, active, workspace-visible items that apply to the job, with a stated reason for each. Agents reach it over MCP at api.dm.auzzura.com.

Learning flows back as a proposal. A connected agent returns its findings, and a person approves, edits or rejects them before they become trusted for later tasks. The vendor is explicit that fully automatic report ingestion is not claimed. Memory is listed as in progress, while rules, skills, decisions, repository intelligence and architecture context are listed as available.

Knowledge and account control data are kept in separate databases, managed DM can be provisioned in an EU region, and dedicated or customer-controlled stores are set up during onboarding. Bring-your-own-key and bring-your-own-model are marked as planned.

## Features

- **Task-specific context:** Prepare Context selects the approved knowledge that applies to a given task.
- **Rules, skills, decisions:** Stores team conventions and choices with provenance and history.
- **Human-reviewed write-back:** Agent findings arrive as proposals that people approve or reject.
- **Workspace isolation:** Each workspace resolves to its own knowledge store and fails closed.
- **MCP agent access:** Connected agents read approved context over a remote MCP endpoint.

## Good for

- Give a coding agent the team's settled decisions before it starts
- Capture what an agent learned for human approval
- Keep architecture rules consistent across several agents
- Reduce re-explaining the same constraints in each session

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http dm-by-auzzura https://api.dm.auzzura.com/mcp
```

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

```sh
https://api.dm.auzzura.com/mcp
```

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

```json
{
  "mcpServers": {
    "dm-by-auzzura": {
      "url": "https://api.dm.auzzura.com/mcp"
    }
  }
}
```

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

```json
{
  "servers": {
    "dm-by-auzzura": {
      "type": "http",
      "url": "https://api.dm.auzzura.com/mcp"
    }
  }
}
```

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

```json
{
  "mcpServers": {
    "dm-by-auzzura": {
      "serverUrl": "https://api.dm.auzzura.com/mcp"
    }
  }
}
```

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

```json
{
  "mcpServers": {
    "dm-by-auzzura": {
      "type": "http",
      "url": "https://api.dm.auzzura.com/mcp"
    }
  }
}
```

## FAQ

### Does agent output become trusted automatically?

No. It comes back as a proposal and a person approves it first.

### Is there a free plan?

Yes, a free tier for one user and one workspace; Team, Business and Enterprise pricing is agreed with the vendor.

### Where is data hosted?

Managed DM can be provisioned in an EU cloud region.

### Are BYOK and BYOM available?

The vendor lists both as planned, not available yet.

### Is DM by AuzzurA free?

DM by AuzzurA has a free plan, with paid plans for more usage or features.

### How do I add DM by AuzzurA to Claude Code?

Run this command in your terminal: claude mcp add --transport http dm-by-auzzura https://api.dm.auzzura.com/mcp

### What are the best alternatives to DM by AuzzurA?

The closest alternatives to DM by AuzzurA 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/dm-by-auzzura
