What is Gumcp

guMCP is an open-source collection of Model Context Protocol (MCP) servers designed for both remote and local execution. It aims to create a comprehensive repository of MCP servers with a unified backend to support AI integrations and the future of AGI.

Use cases

Use cases for guMCP include automating web tasks, managing databases, developing AI tools, and enhancing productivity through various integrated services, showcasing its adaptability in real-world scenarios.

How to use

To use guMCP, clone the repository from GitHub, set up a virtual environment, install the necessary dependencies, and configure the environment variables. You can then run the desired MCP server locally or remotely using the provided commands.

Key features

Key features of guMCP include dual transport support for local and remote hosting, a unified backend architecture for consistent implementation, and an extensive collection of servers catering to various needs such as file systems, databases, development tools, and AI applications.

Where to use

guMCP can be used in various fields including software development, web automation, productivity tools, communication systems, and artificial intelligence research, making it versatile for different applications.

Gumloop Unified Model Context Protocol (guMCP)

guMCP is an open-source collection of Model Context Protocol (MCP) servers that can be run both remotely and locally. The project aims to create the largest collection of MCP servers with a unified backend, fostering a community around AI integrations and the future of AGI.

Overview

While many MCP server providers are closed source, and open-source alternatives typically only support local hosting through stdio, guMCP provides:

• A comprehensive collection of MCP servers that work both locally and remotely
• Support for both stdio and SSE (Server-Sent Events) transports
• A unified backend architecture for consistent implementation
• Full open-source access to encourage community contributions

Features

• Dual Transport Support: All servers support both:

  • Local hosting through stdio
  • Remote hosting through SSE

• Unified Backend: Consistent implementation patterns across all servers

• Extensive Server Collection: Including servers for:

  • File systems and databases
  • Development tools
  • Web and browser automation
  • Productivity and communication
  • AI and specialized tools

Getting Started

Prerequisites

• Python 3.11
• Git

Installation

1. Clone the repository:

git clone https://github.com/gumloop/guMCP.git
cd guMCP

2. Create and activate virtual environment:

python -m venv venv
source venv/bin/activate  # On Unix/macOS
venv\Scripts\activate     # On Windows

3. Install dependencies:

pip install -r requirements.txt
pip install -r requirements-dev.txt

4. Set up environment variables:

cp .env.example .env  # Then edit with your configuration

Usage

Running Stdio Servers

python src/servers/local.py --server=simple-tools-server

For convenience, we also provide a lightweight MCP Client to start and connect to stdio servers. Usage:

 python tests/clients/LocalMCPTestClient.py --server=simple-tools-server

Running SSE Servers

An SSE server can be run locally. This will provide a single URL and host every server available.

To start the SSE development server, run:

./start_remote_dev_server.sh

For convenience, we also prove a lightweight MCP Client to connect to SSE servers. Usage:

python tests/clients/RemoteMCPTestClient.py --endpoint=http://localhost:8000/simple-tools-server/local

Contributing

We welcome contributions! Please see our CONTRIBUTING.md for guidelines.

Key areas for contribution:

• New server implementations
• Transport improvements
• Documentation
• Test coverage
• Bug fixes

License

This project is licensed under the GNU General Public License v3.0 (GPL-3.0) - see the LICENSE file for details.

Security

Security is the single highest priority for us.

That’s why Gumloop is SOC 2 Type II, GDPR, and HIPAA compliant, and why for this OSS repo, we’re actively rewarding those who responsibly disclose serious vulnerabilities and exploits to [email protected].

Community

• GitHub Issues: Bug reports and feature requests
• GitHub Discussions: General questions and discussions
• Forum: Community discussions and support

Acknowledgments

This project builds on the Model Context Protocol (MCP) specification and is inspired by the work of various MCP implementations in the community, especially those at Anthropic.

Thank you to all the contributors that have provided feedback, advice, and early servers for the repository.