Docker Container with Useful MCP Servers
Docker Container with Useful MCP Servers
This project provides a Docker container image that includes several MCP servers that might be useful to a variety of projects. This is early days for this project and not all of these servers have been thoroughly tested, use with caution. 🧯 Right now the following functionality is provided...
Once MCP Servers is connected, these are the calls the assistant has available:
PostgreSQL — When you run start-mcp-servers in your project directory the .env file at the root of that directory will be read. The PostgreSQL MCP server isCompare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
{
"mcpServers": {
"git": {
"type": "sse",
"url": "http://localhost:9099/sse"
},
"postgres": {
"type": "sse",
"url": "http://localhost:9098/sse"
},
"ddg-search": {
"type": "sse",
"url": "http://localhost:9097/sse"
},
"knowledge-graph": {
"type": "sse",
"url": "http://localhost:9096/sse"
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| MEMORY_FILE_PATH | Filesystem location the server is allowed to use. | Optional |
Stop letting your assistant hallucinate n8n node parameters — this server hands it the real schemas, templates and validation.
AWS Labs' official server suite — current AWS docs, CDK guidance, cost analysis and service tools.
Cloud browsers for AI agents — automation sessions that run in Browserbase's fleet, not on your machine.
Workers, KV, R2 and D1 by conversation — Cloudflare's official remote servers for building and observability.
Dashboards, Prometheus and Loki queries, incidents and alerts — observability by conversation.
kubectl with a conversational interface — inspect pods, read logs, diagnose clusters and manage workloads.