MCPgee
MCPgee
MCPgeeMCPgee

Anything LLM

v1.0.0•Cloud Services•stable

The all-in-one AI productivity accelerator. On device and privacy first with no annoying setup or configuration.

ai-agentscustom-ai-agentsdeepseekkimillama3
Share:
60,443
Stars
0
Downloads
0
Weekly
0/5
View on GitHub

What is Anything LLM?

Anything LLM is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to all-in-one ai productivity accelerator. on device and privacy first with no annoying setup or configuration.

The all-in-one AI productivity accelerator. On device and privacy first with no annoying setup or configuration.

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

Features

  • The all-in-one AI productivity accelerator. On device and pr

Use Cases

On-device AI productivity
Privacy-first setup
Local LLM execution
Mintplex-Labs

Maintainer

LicenseMIT
Languagejavascript
Versionv1.0.0
UpdatedMay 22, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux
View SourceBrowse All Servers

Installation

Manual Installation

npx anything-llm

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 Anything LLM

AnythingLLM is an all-in-one AI productivity platform that lets you build a private, ChatGPT-like system on your own hardware or cloud environment. It supports document ingestion (PDF, DOCX, TXT), multi-user workspaces, a no-code AI Agent builder with web browsing capabilities, and dynamic routing across dozens of LLM providers — including local models via LM Studio, Ollama, and LocalAI. Developers and teams use it to chat with private documents, automate workflows, and embed AI chat widgets into their own applications without sending data to third-party servers.

Prerequisites

  • Node.js 18+ or Docker installed on your machine
  • An LLM provider API key (OpenAI, Anthropic, etc.) or a local model server (LM Studio, Ollama, LocalAI)
  • A vector database (LanceDB is bundled; Pinecone, PGVector, or Chroma can be configured)
  • An MCP client such as Claude Desktop or Cursor
  • Git (for source-based setup) or Docker Desktop (for container deployment)
1

Download or clone AnythingLLM

The easiest path is the desktop app available at https://anythingllm.com/download for Mac, Windows, and Linux. For server or Docker deployment, clone the repository and follow the Docker setup guide at ./docker/HOW_TO_USE_DOCKER.md.

git clone https://github.com/Mintplex-Labs/anything-llm.git
cd anything-llm
2

Configure your environment

Copy the example environment file and fill in your LLM provider credentials, vector database connection, and any optional settings such as telemetry opt-out.

cp server/.env.example server/.env.development
# Edit server/.env.development and set your LLM API key, e.g.:
# OPEN_AI_KEY=sk-...
# DISABLE_TELEMETRY=true
3

Install dependencies and start the development server

Run the setup helper to install all workspace dependencies, then start the backend server, frontend, and document collector in separate terminals.

yarn setup
yarn dev:server    # Terminal 1
yarn dev:frontend  # Terminal 2
yarn dev:collector # Terminal 3
4

Create a workspace and upload documents

Open http://localhost:3000 in your browser. Create a new workspace, upload your documents (PDF, DOCX, TXT, CSV, etc.), and AnythingLLM will ingest and index them automatically.

5

Configure the MCP server in your AI client

Add AnythingLLM as an MCP server in your Claude Desktop or Cursor config file so your AI client can interact with it programmatically.

Anything LLM Examples

Client configuration

Add AnythingLLM to your Claude Desktop config. The server runs locally; adjust the host and port if you changed defaults.

{
  "mcpServers": {
    "anything-llm": {
      "command": "npx",
      "args": ["anything-llm"],
      "env": {
        "ANYTHINGLLM_URL": "http://localhost:3001",
        "ANYTHINGLLM_API_KEY": "your-api-key-here"
      }
    }
  }
}

Prompts to try

Once connected, try these prompts to explore AnythingLLM's capabilities through your AI client.

- "Summarize the key points from the documents in my 'Legal Contracts' workspace"
- "Search my knowledge base for anything related to GDPR compliance"
- "Use an AI agent to browse the web and find the latest pricing for AWS EC2 instances, then save a summary"
- "List all workspaces I have and how many documents are in each"

Troubleshooting Anything LLM

Frontend loads but shows no response from the LLM

Verify that the LLM API key is correctly set in server/.env.development and that the selected model name matches what your provider supports. Restart the dev:server process after any .env changes.

Document upload succeeds but answers seem unaware of the content

Check that the vector database is running and accessible. With the default LanceDB, ensure the data directory is writable. Re-embed the document by removing and re-adding it to the workspace.

Docker container starts but the UI is unreachable

Confirm the port mapping in your docker-compose command (default is 3001:3001). Check container logs with 'docker logs <container-name>' for configuration errors.

Frequently Asked Questions about Anything LLM

What is Anything LLM?

Anything LLM is a Model Context Protocol (MCP) server that all-in-one ai productivity accelerator. on device and privacy first with no annoying setup or configuration. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Anything LLM?

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

Which AI clients work with Anything LLM?

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

Is Anything LLM free to use?

Yes, Anything LLM is open source and available under the MIT 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

Anything LLM Alternatives — Similar Cloud Services Servers

Looking for alternatives to Anything LLM? Here are other popular cloud services servers you can use with Claude, Cursor, and VS Code.

Open WebUI

★ 138.2k

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

LocalAI

★ 46.4k

LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.

Nacos

★ 33.0k

an easy-to-use dynamic service discovery, configuration and service management platform for building AI cloud native applications.

Xiaozhi ESP32

★ 26.7k

本项目为xiaozhi-esp32提供后端服务，帮助您快速搭建ESP32设备控制服务器。Backend service for xiaozhi-esp32, helps you quickly build an ESP32 device control server.

Gateway

★ 11.8k

A blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.

Nginx UI

★ 11.2k

Yet another WebUI for Nginx

Browse More Cloud Services MCP Servers

Explore all cloud services servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Cloud ServicesBrowse All Servers

Quick Config Preview

{ "mcpServers": { "anything-llm": { "command": "npx", "args": ["-y", "anything-llm"] } } }

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

Read the full setup guide →

Ready to use Anything LLM?

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