- MCP Servers Collection
MCP Servers Collection
Content
MCP Servers Collection
This project runs multiple MCP servers using Supergateway to expose each server over SSE (Server-Sent Events). Each server runs in its own container on a dedicated port.
Quick Start
# Copy environment file
cp .env.example .env
# Edit your API tokens
vim .env
# Start all services
docker-compose up -d
Architecture
- Multiple containers, each running a specific MCP server via Supergateway
- Each server exposed on a unique port (9001-9006)
- Servers can be connected to individually or all at once
- Persistent data stored in mounted volumes
Available Commands
Basic Operations
# Start all services
docker-compose up -d
# Stop all services
docker-compose down
# Restart all services
docker-compose restart
# Check status
docker-compose ps
# View logs from all services
docker-compose logs -f
# View logs from specific service
docker-compose logs -f mcp-filesystem
docker-compose logs -f mcp-github
Individual Service Management
# Restart specific service
docker-compose restart mcp-filesystem
docker-compose restart mcp-github
# Shell into specific container
docker-compose exec mcp-filesystem sh
docker-compose exec mcp-github sh
# View logs from last 50 lines
docker-compose logs --tail=50
Cleanup
# Stop and remove containers
docker-compose down
# Stop and remove containers + volumes
docker-compose down -v
# Pull latest images
docker-compose pull
MCP Servers & Ports
| Service | Port | Description | Environment Variables |
|---|---|---|---|
| mcp-github | 9001 | GitHub repository access | GITHUB_TOKEN, GITHUB_OWNER |
| mcp-linear | 9002 | Linear issue tracking | LINEAR_API_KEY, GITHUB_TOKEN |
| mcp-notion | 9003 | Notion workspace access | NOTION_TOKEN |
| mcp-filesystem | 9004 | File system operations | - |
| mcp-memory | 9005 | Persistent memory | - |
| mcp-sequential-thinking | 9006 | Step-by-step reasoning | - |
| mcp-context7 | 9007 | Up-to-date documentation | DEFAULT_MINIMUM_TOKENS |
| mcp-prisma | 9009 | Prisma database management | - |
Configuration
Environment Variables
- Copy the example:
make setup(orcp .env.example .env) - Edit
.envwith your actual API tokens:GITHUB_OWNER- Your GitHub usernameGITHUB_TOKEN- GitHub Personal Access TokenNOTION_TOKEN- Notion API tokenLINEAR_API_KEY- Linear API key
Connecting to MCP Servers
Each server is available via SSE at:
- SSE Endpoint:
http://localhost:900X/sse - POST Messages:
http://localhost:900X/message
Claude Desktop Configuration
Connect to individual servers:
{
"mcpServers": {
"github": {
"command": "npx",
"args": ["-y", "supergateway", "--sse", "http://localhost:9001/sse"]
},
"linear": {
"command": "npx",
"args": ["-y", "supergateway", "--sse", "http://localhost:9002/sse"]
},
"notion": {
"command": "npx",
"args": ["-y", "supergateway", "--sse", "http://localhost:9003/sse"]
},
"filesystem": {
"command": "npx",
"args": ["-y", "supergateway", "--sse", "http://localhost:9004/sse"]
},
"memory": {
"command": "npx",
"args": ["-y", "supergateway", "--sse", "http://localhost:9005/sse"]
},
"sequential-thinking": {
"command": "npx",
"args": ["-y", "supergateway", "--sse", "http://localhost:9006/sse"]
},
"context7": {
"command": "npx",
"args": ["-y", "supergateway", "--sse", "http://localhost:9007/sse"]
},
"prisma": {
"command": "npx",
"args": ["-y", "supergateway", "--sse", "http://localhost:9009/sse"]
}
}
}
Zed Editor Configuration
{
"context_servers": {
"github": {
"command": {
"path": "npx",
"args": ["-y", "supergateway", "--sse", "http://localhost:9001/sse"]
}
},
"filesystem": {
"command": {
"path": "npx",
"args": ["-y", "supergateway", "--sse", "http://localhost:9004/sse"]
}
}
}
}
Service Details
GitHub MCP Server (Port 9001)
- Repository operations (clone, create, update)
- Issue and PR management
- File operations within repositories
- Requires:
GITHUB_TOKEN,GITHUB_OWNER
Linear MCP Server (Port 9002)
- Issue creation and management
- Project and team operations
- Integration with GitHub repositories
- Requires:
LINEAR_API_KEY,GITHUB_TOKEN
Notion MCP Server (Port 9003)
- Database queries and updates
- Page creation and modification
- Block-level operations
- Requires:
NOTION_TOKEN
Filesystem MCP Server (Port 9004)
- File and directory operations
- Mounted to
/workspace(maps to/home/vagrant/projects) - Read, write, create, delete operations
Memory MCP Server (Port 9005)
- Persistent memory across sessions
- Data stored in
/home/vagrant/.shared-memory - Key-value storage for context retention
Sequential Thinking MCP Server (Port 9006)
- Step-by-step reasoning and planning
- Multi-step problem solving
- No external dependencies
Context7 MCP Server (Port 9007)
- Fetches up-to-date, version-specific documentation
- Pulls code examples straight from the source
- Helps avoid outdated training data and hallucinated APIs
- Usage: Add "use context7" to your prompts
- Environment:
DEFAULT_MINIMUM_TOKENS(default: 10000)
Prisma MCP Server (Port 9009)
- Prisma database management and schema operations
- Database instance management for Postgres
- Schema migrations and database operations
- Early access features for Prisma Platform
- No API key required (uses Prisma CLI authentication)
Troubleshooting
Check container status:
docker-compose ps
View logs from all services:
docker-compose logs -f
View logs from specific service:
docker-compose logs -f mcp-github # GitHub server logs
docker-compose logs -f mcp-filesystem # Filesystem server logs
# etc.
Test individual server connectivity:
curl http://localhost:9001/sse # Should return SSE stream
curl http://localhost:9004/sse # Filesystem server
Full restart:
docker-compose down
docker-compose up -d
Shell into specific container:
docker-compose exec mcp-github sh
docker-compose exec mcp-filesystem sh
Development
Add a new MCP server:
- Add service to
docker-compose.yml - Choose next available port (9007+)
- Add environment variables to
.env.exampleif needed - Update this README with server details
Monitor all services:
docker-compose up -d && docker-compose logs -f
Recommend Servers
TraeBuild with Free GPT-4.1 & Claude 3.7. Fully MCP-Ready.
Zhipu Web SearchZhipu Web Search MCP Server is a search engine specifically designed for large models. It integrates four search engines, allowing users to flexibly compare and switch between them. Building upon the web crawling and ranking capabilities of traditional search engines, it enhances intent recognition capabilities, returning results more suitable for large model processing (such as webpage titles, URLs, summaries, site names, site icons, etc.). This helps AI applications achieve "dynamic knowledge acquisition" and "precise scenario adaptation" capabilities.
Playwright McpPlaywright MCP server
ChatWiseThe second fastest AI chatbot™
MiniMax MCPOfficial MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs.
Baidu Map百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
WindsurfThe new purpose-built IDE to harness magic
AiimagemultistyleA Model Context Protocol (MCP) server for image generation and manipulation using fal.ai's Stable Diffusion model.
CursorThe AI Code Editor
Howtocook Mcp基于Anduin2017 / HowToCook (程序员在家做饭指南)的mcp server,帮你推荐菜谱、规划膳食,解决“今天吃什么“的世纪难题;
Based on Anduin2017/HowToCook (Programmer's Guide to Cooking at Home), MCP Server helps you recommend recipes, plan meals, and solve the century old problem of "what to eat today"
TimeA Model Context Protocol server that provides time and timezone conversion capabilities. This server enables LLMs to get current time information and perform timezone conversions using IANA timezone names, with automatic system timezone detection.
Context7Context7 MCP Server -- Up-to-date code documentation for LLMs and AI code editors
Serper MCP ServerA Serper MCP Server
BlenderBlenderMCP connects Blender to Claude AI through the Model Context Protocol (MCP), allowing Claude to directly interact with and control Blender. This integration enables prompt assisted 3D modeling, scene creation, and manipulation.
MCP AdvisorMCP Advisor & Installation - Use the right MCP server for your needs
EdgeOne Pages MCPAn MCP service designed for deploying HTML content to EdgeOne Pages and obtaining an accessible public URL.
Jina AI MCP ToolsA Model Context Protocol (MCP) server that integrates with Jina AI Search Foundation APIs.
DeepChatYour AI Partner on Desktop
Visual Studio Code - Open Source ("Code - OSS")Visual Studio Code
Amap Maps高德地图官方 MCP Server
Tavily Mcp