MCPgee
MCPgee
MCPgeeMCPgee

Beever Atlas

v1.0.0•Knowledge & Memory•stable

Your First LLM-Wiki Conversation Knowledge Base

adk-googleagentsdiscord-botfastapigemini
Share:
340
Stars
0
Downloads
0
Weekly
0/5
View on GitHub

What is Beever Atlas?

Beever Atlas is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to your first llm-wiki conversation knowledge base

Your First LLM-Wiki Conversation Knowledge Base

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

Features

  • Your First LLM-Wiki Conversation Knowledge Base

Use Cases

LLM-wiki knowledge base
Conversational knowledge access
Agent memory system
Beever-AI

Maintainer

LicenseApache-2.0
Languagepython
Versionv1.0.0
UpdatedMay 22, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux
View SourceBrowse All Servers

Installation

Manual Installation

npx beever-atlas

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 Beever Atlas

Beever Atlas is a self-hosted, LLM-powered knowledge base platform that ingests chat history from Slack, Discord, Teams, and Mattermost, then makes it searchable and queryable through a dual-memory architecture combining a 3-tier semantic store and a graph store. It exposes 28 MCP tools for external AI agents, enabling semantic search, wiki page retrieval, entity graph traversal, and conversational Q&A over your organization's accumulated chat knowledge without sending data to third-party services. Teams that lose institutional knowledge in sprawling chat channels will find Beever Atlas transforms that history into a structured, AI-queryable wiki.

Prerequisites

  • Docker and Docker Compose installed
  • A Google API key from aistudio.google.com/apikey (for Gemini-powered extraction and QA)
  • A Jina API key from jina.ai/api-dashboard (for 2048-dimensional semantic embeddings)
  • Access to at least one chat platform: Slack, Discord, Microsoft Teams, or Mattermost
  • An MCP-compatible client such as Claude Desktop or Claude Code
1

Clone the Beever Atlas repository

Clone the repository to your server or local machine.

git clone https://github.com/Beever-AI/beever-atlas.git && cd beever-atlas
2

Configure environment variables

Copy the example env file and fill in your API keys. At minimum you need GOOGLE_API_KEY and JINA_API_KEY. Generate random hex strings for the credential keys.

cp .env.example .env
# Edit .env and set:
# GOOGLE_API_KEY=<from aistudio.google.com/apikey>
# JINA_API_KEY=<from jina.ai/api-dashboard>
# CREDENTIAL_MASTER_KEY=<64 random hex chars>
# WEAVIATE_API_KEY=<32 random hex chars>
3

Run the one-line installer

Execute the Atlas installer script for a guided 5-step setup that handles Docker service orchestration, database initialization, and initial configuration. This typically completes in about 2 minutes.

./atlas
4

Connect a chat platform and ingest data

Open the Beever Atlas dashboard (default: http://localhost:3000) and connect your Slack, Discord, Teams, or Mattermost workspace. Trigger an initial data sync to populate the knowledge base.

5

Configure an MCP client to use Beever Atlas tools

Add Beever Atlas to your Claude Desktop or Claude Code configuration to expose the 28 MCP tools for semantic search, wiki retrieval, and graph queries.

{
  "mcpServers": {
    "beever-atlas": {
      "command": "npx",
      "args": ["beever-atlas"],
      "env": {
        "BEEVER_API_KEY": "your_beever_api_key",
        "BEEVER_API_URL": "http://localhost:3000"
      }
    }
  }
}
6

Try the demo mode (no API keys needed)

To explore Beever Atlas with pre-seeded demo data before configuring your own sources, run the demo target.

make demo

Beever Atlas Examples

Client configuration

Claude Desktop or Claude Code configuration for Beever Atlas MCP integration, pointing to your self-hosted instance.

{
  "mcpServers": {
    "beever-atlas": {
      "command": "npx",
      "args": ["beever-atlas"],
      "env": {
        "GOOGLE_API_KEY": "AIza...",
        "JINA_API_KEY": "jina_...",
        "BEEVER_API_URL": "http://localhost:3000"
      }
    }
  }
}

Prompts to try

With Beever Atlas connected, use these prompts to query your organization's accumulated chat knowledge:

- "Search for all discussions about the Q3 product launch across our Slack channels"
- "What decisions were made about the database migration last month?"
- "Show me the wiki page summarizing everything we know about our authentication system"
- "Find all entities related to our customer 'Acme Corp' and how they're connected"
- "What did the team discuss about performance issues in the #backend channel?"

Troubleshooting Beever Atlas

Docker services fail to start with port conflicts

Beever Atlas uses Weaviate, Neo4j, MongoDB, and Redis. Check for port conflicts with `docker ps` and `lsof -i :<port>`. Edit the `.env` file to remap ports if needed, then restart with `docker compose up -d --build`.

Semantic search returns no results after ingesting chat data

Verify your JINA_API_KEY is valid and has not exceeded its free-tier quota at jina.ai. Check the backend logs with `docker compose logs -f beever-atlas` for embedding errors. Ensure the ingestion sync completed fully before running queries.

Google API extraction fails for entity graph building

Confirm your GOOGLE_API_KEY is from Google AI Studio (aistudio.google.com), not Google Cloud Console. The key must have access to the Gemini API. Check API quotas in the Google AI Studio dashboard if extraction stops mid-sync.

Frequently Asked Questions about Beever Atlas

What is Beever Atlas?

Beever Atlas is a Model Context Protocol (MCP) server that your first llm-wiki conversation knowledge base It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Beever Atlas?

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

Which AI clients work with Beever Atlas?

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

Is Beever Atlas free to use?

Yes, Beever Atlas is open source and available under the Apache-2.0 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

Beever Atlas Alternatives — Similar Knowledge & Memory Servers

Looking for alternatives to Beever Atlas? 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": { "beever-atlas": { "command": "npx", "args": ["-y", "beever-atlas"] } } }

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

Read the full setup guide →

Ready to use Beever Atlas?

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