# beever-atlas

This MCP server turns team chats into a linked knowledge base and cited wiki. Use it when an agent needs answers grounded in past discussions.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 451
- Author: Beever-AI
- License: Apache-2.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/Beever-AI/beever-atlas
- Updated: 2026-09-10
- HTML: https://affpapa.org/en/nevibecode/mcp/beever-atlas

## What it does

beever-atlas pulls messages from Slack, Discord, Microsoft Teams, and Mattermost, then extracts facts, entities, and relationships, removes duplicates, and groups the result into topic pages. You can ask questions through its dashboard or through MCP and receive answers cited back to source messages.

The system uses a six-stage Google ADK pipeline, a three-tier semantic store, and an entity graph. Its wiki is maintained per channel, while a smart router chooses semantic or graph retrieval for each question. The MCP server exposes 28 tools with per-agent authentication. Docker is required for the provided setup command; without it, the beever-atlas container will not start.

## Requirements
- Needs: Docker

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add beever-atlas -- docker run -i --rm ghcr.io/beever-ai/beever-atlas:0.3.0
```

### Codex

**Platform CLI**
```bash
codex mcp add beever-atlas -- docker run -i --rm ghcr.io/beever-ai/beever-atlas:0.3.0
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "beever-atlas": {
            "command": "docker",
            "args": [
                "run",
                "-i",
                "--rm",
                "ghcr.io/beever-ai/beever-atlas:0.3.0"
            ]
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "beever-atlas": {
            "type": "stdio",
            "command": "docker",
            "args": [
                "run",
                "-i",
                "--rm",
                "ghcr.io/beever-ai/beever-atlas:0.3.0"
            ]
        }
    }
}
```

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add beever-atlas docker run -i --rm ghcr.io/beever-ai/beever-atlas:0.3.0
```

## When to use it
- turn team chat history into wiki pages
- trace an answer back to source messages
- connect people, projects, and decisions in a graph
- query project knowledge through an MCP agent
- separate duplicate facts from chat history

## Example prompts
- Search the knowledge base for decisions about the project and cite the source messages.
- Create a wiki overview of a topic from our Slack channels, including related decisions.
- Compare mentions of this project and its people across team chats with citations.

## Similar
- [REA](https://affpapa.org/en/nevibecode/mcp/rea.md) — MCP server · ★ 386989
- [GitHub](https://affpapa.org/en/nevibecode/mcp/github.md) — MCP server · ★ 33918
- [Netdata](https://affpapa.org/en/nevibecode/mcp/netdata.md) — MCP server · ★ 81115
- [browser-use](https://affpapa.org/en/nevibecode/mcp/browser-use.md) — MCP server · ★ 119160
- [Codebase Memory](https://affpapa.org/en/nevibecode/mcp/codebase-memory.md) — MCP server · ★ 47392
- [mcp-server](https://affpapa.org/en/nevibecode/mcp/mcp-server.md) — MCP server · ★ 43872

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md