MCPgee
MCPgee
MCPgeeMCPgee

Ultrarag

v1.0.0•Data Science & ML•stable

A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines

deepseekdemoeasyembeddingflask
Share:
5,552
Stars
0
Downloads
0
Weekly
0/5
View on GitHub

What is Ultrarag?

Ultrarag is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to low-code mcp framework for building complex and innovative rag pipelines

A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines

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

Features

  • A Low-Code MCP Framework for Building Complex and Innovative

Use Cases

Build complex RAG pipelines with low-code framework
Implement embedding and retrieval systems
OpenBMB

Maintainer

LicenseApache-2.0
Languagepython
Versionv1.0.0
UpdatedMay 21, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux
View SourceBrowse All Servers

Installation

Manual Installation

npx ultrarag

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 Ultrarag

UltraRAG is a low-code framework for building complex and innovative Retrieval-Augmented Generation (RAG) pipelines, developed by OpenBMB. It uses MCP architecture to expose core RAG components — including retrievers, generators, and evaluators — as independent MCP servers orchestrated through YAML workflow files. Researchers and ML engineers use it to prototype advanced RAG systems with modular components, run standardized benchmarks, and generate interactive UIs for their pipelines without writing boilerplate integration code.

Prerequisites

  • Python 3.10+ installed on your system
  • UV package manager installed (pip install uv) or Docker for containerized deployment
  • Git to clone the repository
  • API keys for your chosen LLM provider (OpenAI, DeepSeek, or compatible)
  • An MCP-compatible client to interface with the exposed MCP servers
1

Clone the UltraRAG repository

Clone the repository with minimal history to save disk space, then enter the project directory.

git clone https://github.com/OpenBMB/UltraRAG.git --depth 1
cd UltraRAG
2

Install dependencies with UV

Install the core package first, then add extras for specific capabilities. Use --all-extras for the full feature set including multimodal retrieval.

pip install uv
uv sync --all-extras
3

Activate the virtual environment

Activate the UV-managed virtual environment before running any UltraRAG commands.

# Linux/macOS
source .venv/bin/activate

# Windows PowerShell
.venv\Scripts\Activate.ps1
4

Verify the installation

Run the hello-world example to confirm UltraRAG is installed and working correctly.

ultrarag run examples/experiments/sayhello.yaml
5

Create a RAG pipeline workflow file

Define your RAG pipeline in a YAML file specifying the retriever, generator, and evaluation components. Each component runs as an independent MCP server.

# my_rag_pipeline.yaml
workflow:
  retriever:
    type: vector
    model: text-embedding-3-small
  generator:
    type: openai
    model: gpt-4o-mini
  evaluation:
    metrics: [faithfulness, relevancy]
6

Run your pipeline

Execute the pipeline using the ultrarag CLI. The framework will start each component as an MCP server and orchestrate the workflow.

ultrarag run my_rag_pipeline.yaml

Ultrarag Examples

Client configuration

MCP client configuration to connect to a running UltraRAG server instance.

{
  "mcpServers": {
    "ultrarag": {
      "command": "npx",
      "args": ["ultrarag"]
    }
  }
}

Prompts to try

Build and query RAG pipelines through the MCP interface.

- "Create a RAG pipeline that retrieves from my PDF documents and answers questions using GPT-4o-mini"
- "Run the faithfulness and relevancy evaluation metrics on my pipeline's last 100 responses"
- "Set up a multimodal retrieval pipeline that can handle both text and images"
- "Generate an interactive UI for my current RAG pipeline configuration"

Troubleshooting Ultrarag

uv sync fails with dependency resolution errors

Try installing specific module extras instead of --all-extras: 'uv sync --extra retriever' or 'uv sync --extra generation'. This avoids conflicts between optional dependencies.

Docker deployment fails to access GPU

Use the GPU-enabled image tag and ensure the --gpus all flag is passed: 'docker run -it --gpus all -p 5050:5050 hdxin2002/ultrarag:v0.3.0'. Also verify the NVIDIA Container Toolkit is installed on your host.

YAML workflow validation errors when running a pipeline

Run the hello-world example first to confirm the installation is correct: 'ultrarag run examples/experiments/sayhello.yaml'. Then compare your YAML structure against the provided examples in the examples/experiments/ directory.

Frequently Asked Questions about Ultrarag

What is Ultrarag?

Ultrarag is a Model Context Protocol (MCP) server that low-code mcp framework for building complex and innovative rag pipelines It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Ultrarag?

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

Which AI clients work with Ultrarag?

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

Is Ultrarag free to use?

Yes, Ultrarag 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

Ultrarag Alternatives — Similar Data Science & ML Servers

Looking for alternatives to Ultrarag? Here are other popular data science & ml servers you can use with Claude, Cursor, and VS Code.

RocketRide

★ 3.1k

📇 🏠 - MCP server that exposes RocketRide AI pipelines as t

Aix Db

★ 2.1k

Aix-DB 基于 LangChain/LangGraph 框架，结合 MCP Skills 多智能体协作架构，实现自然语言到数据洞察的端到端转换。

NeMo Data Designer

★ 1.9k

🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.

PaperBanana

★ 1.7k

Open source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.

MiniMax

★ 1.5k

Bridges MiniMax AI capabilities to the Model Context Protocol, enabling AI agents to perform image understanding, text-to-image generation, and speech synthesis. It provides a standardized interface for accessing MiniMax's core tools via JSON-RPC.

NpcPy

★ 1.4k

The python library for research and development in NLP, multimodal LLMs, Agents, ML, Knowledge Graphs, and more.

Browse More Data Science & ML MCP Servers

Explore all data science & ml servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Data Science & MLBrowse All Servers

Quick Config Preview

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

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

Read the full setup guide →

Ready to use Ultrarag?

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