🚀 MCPverse

🚀 MCPverse

By Harika-BV GitHub

MCPverse is a search and discovery tool for MCP (Model Context Provider) servers hosted on GitHub. It ranks and displays repos with client configs in a clean, interactive UI.

Overview

what is MCPverse?

MCPverse is a search and discovery tool designed for MCP (Model Context Provider) servers hosted on GitHub. It provides a clean and interactive user interface to rank and display repositories with client configurations.

how to use MCPverse?

To use MCPverse, visit the live app at mcpverse.streamlit.app, where you can search for and discover various MCP servers and their configurations.

key features of MCPverse?

  • Interactive UI for easy navigation and discovery of MCP servers.
  • Ranking system to highlight the best repositories.
  • Ability to view client configurations for each repository.

use cases of MCPverse?

  1. Finding the best MCP servers for specific applications.
  2. Exploring client configurations for different projects.
  3. Assisting developers in selecting suitable repositories for their needs.

FAQ from MCPverse?

  • What is an MCP server?

An MCP server is a Model Context Provider that serves as a backend for applications needing context-aware data.

  • How can I contribute to MCPverse?

You can contribute by submitting your own MCP server repositories on GitHub and sharing them with the community.

  • Is MCPverse free to use?

Yes! MCPverse is completely free to use.

Content

🚀 MCPverse

MCPverse is a semantic search engine for discovering Model Configuration Protocol (MCP) servers across GitHub. It indexes public MCP repositories and enables powerful natural language search using vector embeddings and OpenSearch.

📡 Live Demo

Try out the hosted version of MCPverse here: 👉 https://mcpverse.streamlit.app

✨ Features

  • 🔍 Semantic search using OpenAI embeddings (text-embedding-ada-002)
  • 📚 Indexes name, description, and README content
  • ⚙️ Client configuration preview (where available)
  • 🎨 Interactive UI using Streamlit

📦 Project Structure

.
├── backend
│   ├── fetch_repos.py      # Get MCP server repos from Github
│   ├── extract_config.py   # Logic to extract MCP client config from README
│   ├── embedder.py         # OpenAI + OpenSearch indexing and search logic
|   ├── github_scraper.py   # Using Github API to search on MCP servers 
│   └── data/
│       └── mcpverse_data.json  
├── frontend
│   └── app.py               # Streamlit app
├── requirements.txt
├── README.md
├── .env
├── .gitignore

🛠️ Local Setup Guide

1. Clone the Repository

git clone https://github.com/Harika-BV/MCPverse.git
cd MCPverse

2. Set Up Python Environment

python -m venv venv
source venv/bin/activate  # For Windows: venv\Scripts\activate
pip install -r requirements.txt

3. Configure Environment Variables

Create a .env file in the root:

GH_API_KEY=your-github-token
ENV=local
OPENAI_API_KEY=your-openai-key
OPENSEARCH_HOST=localhost
OPENSEARCH_PORT=9200
OPENSEARCH_USER=admin
OPENSEARCH_PASS=admin

💡 You can also connect to your hosted OpenSearch or Elasticsearch cluster.

4. Start OpenSearch Locally (Optional)

If you're running OpenSearch locally, use Docker:

docker run -d --name opensearch -p 9200:9200 \
  -e "discovery.type=single-node" \
  -e "plugins.security.disabled=true" \
  opensearchproject/opensearch:2.11.1

5. Index MCP Repositories

cd backend
python embedder.py

This will:

  • Load the GitHub MCP repo data (from mcpverse_data.json)
  • Generate OpenAI embeddings
  • Index them into OpenSearch

6. Run the Streamlit App

cd frontend
streamlit run app.py

Then open http://localhost:8501 in your browser.

🧑‍💻 Maintainer

Built with ❤️ by Harika B V

⚠️ Disclaimer

All repositories and data are publicly available on GitHub.
MCPverse is a community project and is not affiliated with any third-party MCP maintainers.

No tools information available.
No content found.