https://github.com/tigranbs/mcgravity
A proxy tool for composing multiple MCP servers into one unified endpoint. Scale your AI tools by load balancing requests across multiple MCP servers, similar to how Nginx works for web servers.
https://github.com/tigranbs/mcgravity
Last synced: 5 months ago
JSON representation
A proxy tool for composing multiple MCP servers into one unified endpoint. Scale your AI tools by load balancing requests across multiple MCP servers, similar to how Nginx works for web servers.
- Host: GitHub
- URL: https://github.com/tigranbs/mcgravity
- Owner: tigranbs
- License: apache-2.0
- Created: 2025-04-13T00:02:41.000Z (6 months ago)
- Default Branch: main
- Last Pushed: 2025-04-16T13:57:15.000Z (6 months ago)
- Last Synced: 2025-04-16T20:43:45.963Z (6 months ago)
- Language: TypeScript
- Size: 267 KB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.docker.md
- License: LICENSE
Awesome Lists containing this project
- awesome-mcp-servers - tigranbs/mcgravity - A proxy tool for composing and load balancing across multiple MCP servers, offering a unified endpoint. Useful for scaling AI tools via multiple MCP servers. ([Read more](/details/tigranbsmcgravity.md)) `proxy` `load-balancing` `scaling` `ai-integration` (MCP Middleware & Orchestration)
- awesome-devops-mcp-servers - tigranbs/mcgravity - A proxy tool for composing multiple MCP servers into one unified endpoint. Scale your AI tools by load balancing requests across multiple MCP servers, similar to how Nginx works for web servers. (CI/CD & DevOps Pipelines / 🔗 Aggregators)
- best-of-mcp-servers - GitHub - 50% open · ⏱️ 18.04.2025) (Aggregators)
- awesome - tigranbs/mcgravity - A proxy tool for composing multiple MCP servers into one unified endpoint. Scale your AI tools by load balancing requests across multiple MCP servers, similar to how Nginx works for web servers. (TypeScript)
- awesome-mcp-servers - tigranbs/mcgravity - 複数のMCPサーバーを1つの統一エンドポイントに構成するためのプロキシツール。Nginxがウェブサーバーのために機能するのと同様に、複数のMCPサーバー間でリクエストの負荷分散を行うことで、AIツールをスケーリングします。 (サーバー実装 / 🔗 <a name="aggregators"></a>アグリゲーター)
- awesome-devops-mcp-servers - tigranbs/mcgravity - A proxy tool for composing multiple MCP servers into one unified endpoint. Scale your AI tools by load balancing requests across multiple MCP servers, similar to how Nginx works for web servers. (CI/CD & DevOps Pipelines / 🔗 Aggregators)
- awesome-ai-tools - tigranbs/mcgravity - Proxy tool composing multiple MCP servers with load balancing capabilities (MCP Servers / 🔗 Aggregators & Meta Servers)
README
# McGravity Docker Guide
## Overview
McGravity is a tool that connects multiple MCP (Model Context Protocol) servers into one unified service. This document explains how to use McGravity with Docker.
## Using the Docker Image
### Pull the Docker Image
```bash
docker pull tigranbs/mcgravity
```
### Run McGravity with Docker
Basic usage:
```bash
docker run -p 3001:3001 tigranbs/mcgravity http://mcp1.example.com http://mcp2.example.com
```
With custom host and port:
```bash
docker run -p 4000:4000 tigranbs/mcgravity --host 0.0.0.0 --port 4000 http://mcp1.example.com
```
### Using a Configuration File
1. Create a config.yaml file locally
2. Mount it to the container:
```bash
docker run -p 3001:3001 -v $(pwd)/config.yaml:/app/config.yaml tigranbs/mcgravity --config /app/config.yaml
```
## Building the Docker Image Locally
1. Clone the repository:
```bash
git clone https://github.com/tigranbs/mcgravity.git
cd mcgravity
```
2. Build the Docker image:
```bash
docker build -t mcgravity .
```
3. Run your local build:
```bash
docker run -p 3001:3001 mcgravity
```
## Docker Compose Example
```yaml
services:
mcgravity:
image: tigranbs/mcgravity:latest
ports:
- '3001:3001'
volumes:
- ./config.yaml:/app/config.yaml
command: --config /app/config.yaml
restart: unless-stopped
```
## Container Details
- The McGravity Docker image is based on Alpine Linux for minimal size
- The application is compiled to a single binary for optimal performance
- Default port exposed: 3001
- Default command: `--help`
## Environment Variables
None currently supported. All configuration is done via command-line arguments or the config file.
## Troubleshooting
If you encounter issues:
1. Ensure ports are correctly mapped
2. Check that your config file is correctly mounted
3. Verify MCP server URLs are accessible from the container
For more details about McGravity itself, see the main [README.md](https://github.com/tigranbs/mcgravity/blob/main/README.md).