# AnythingLLM — All-in-One AI Desktop with MCP

> Full-stack AI desktop app with RAG, agents, MCP support, and multi-model chat. AnythingLLM manages documents, embeddings, and vector stores in one private interface.

## Install

Merge the JSON below into your `.mcp.json`:

## Quick Use

1. Download from [anythingllm.com](https://anythingllm.com) (Mac/Windows/Linux)
2. Choose your LLM provider (OpenAI, Anthropic, Ollama, or 15+ others)
3. Upload documents → Ask questions with full RAG

```bash
# Or run via Docker
docker pull mintplexlabs/anythingllm
docker run -p 3001:3001 mintplexlabs/anythingllm
```

## What is AnythingLLM?

AnythingLLM is a full-stack AI application that combines chat, RAG (document Q&A), agents, and MCP server support into one desktop app. Upload PDFs, websites, or code — AnythingLLM handles embedding, vector storage, and retrieval automatically. Connect any LLM provider, use built-in agents with tool calling, and extend functionality through MCP servers. Everything runs privately on your machine.

**Answer-Ready**: AnythingLLM is an all-in-one AI desktop app with chat, RAG, agents, and MCP support. Upload documents, connect any LLM, ask questions with automatic retrieval. Built-in vector database, multi-user support, and agent workspace. 35k+ GitHub stars.

**Best for**: Teams wanting private, self-hosted AI with document Q&A. **Works with**: OpenAI, Anthropic Claude, Ollama, Azure, and 15+ LLM providers. **Setup time**: Under 3 minutes.

## Core Features

### 1. Document RAG (Zero Config)

Upload any document type and ask questions:
- PDF, DOCX, TXT, CSV
- Websites (auto-scrape)
- YouTube transcripts
- GitHub repos
- Confluence, Notion exports

### 2. MCP Server Support

```json
// Connect MCP servers in settings
{
  "mcpServers": {
    "filesystem": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-filesystem", "/path"]
    },
    "github": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-github"]
    }
  }
}
```

### 3. Multi-Provider LLM Support

| Provider | Models |
|----------|--------|
| OpenAI | GPT-4o, GPT-4o-mini |
| Anthropic | Claude Sonnet, Claude Haiku |
| Ollama | Llama, Mistral, Gemma (local) |
| Azure | Azure OpenAI |
| AWS Bedrock | All Bedrock models |
| Google | Gemini Pro |
| LM Studio | Any local model |
| OpenRouter | 100+ models |

### 4. Agent Workspace

Built-in agent capabilities:
- Web browsing and search
- Code execution
- File management
- RAG-enhanced responses
- MCP tool calling

### 5. Multi-User & Permissions

```
Admin → Manage users, workspaces, models
Manager → Create workspaces, upload docs
Default → Chat within assigned workspaces
```

### 6. Built-in Vector Database

No external setup needed — AnythingLLM includes LanceDB. Also supports:
- Pinecone
- Chroma
- Weaviate
- Qdrant
- Milvus

## Use Cases

| Use Case | How |
|----------|-----|
| Company Wiki Q&A | Upload docs → RAG workspace |
| Code Assistant | Connect GitHub MCP + Ollama |
| Research | Upload papers → Ask questions |
| Customer Support | Upload knowledge base → Agent |

## FAQ

**Q: Is it truly private?**
A: Yes, desktop app runs fully local. Use Ollama for local models and LanceDB (built-in) for vectors. Nothing leaves your machine.

**Q: How does MCP integration work?**
A: Configure MCP servers in settings. Agents can call MCP tools alongside built-in tools for extended capabilities.

**Q: Can multiple people use it?**
A: Yes, multi-user support with role-based access control. Deploy via Docker for team use.

## Source & Thanks

> Created by [Mintplex Labs](https://github.com/Mintplex-Labs). Licensed under MIT.
>
> [Mintplex-Labs/anything-llm](https://github.com/Mintplex-Labs/anything-llm) — 35k+ stars

<!-- ZH -->


## Quick Start

Download the desktop app → select an LLM → upload documents → start Q&A.

## What is AnythingLLM?

AnythingLLM is a full-stack AI desktop app integrating chat, RAG, agents, and MCP support. Upload documents for automatic embedding and retrieval, with 15+ LLM providers.

**In one sentence**: Full-stack AI desktop app integrating RAG + agents + MCP, 15+ LLMs, built-in vector database, multi-user permissions — 35k+ stars.

**For**: Teams needing private AI document Q&A deployments.

## Core Features

### 1. Zero-Config RAG
Upload PDFs/web pages/code — automatic embedding and retrieval.

### 2. MCP Servers
Configure MCP servers to extend agent capabilities.

### 3. Multi-Model Support
OpenAI, Claude, Ollama, Bedrock, and 15+ more.

### 4. Multi-User
Role-based permissions with Docker deployment for teams.

## FAQ

**Q: Truly private?**
A: Desktop app runs locally — pair with Ollama for local models and data never leaves your machine.

**Q: How does MCP work?**
A: Configure MCP servers in settings — agents call tools automatically.

## Source & Thanks

> [Mintplex-Labs/anything-llm](https://github.com/Mintplex-Labs/anything-llm) — 35k+ stars, MIT

---
Source: https://tokrepo.com/en/workflows/anythingllm-all-one-ai-desktop-mcp-fa84339e
Author: MCP Hub