MCP Servers
@cmiles74
About MCP Servers
Docker Container with Useful MCP Servers
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"mcp-servers-cmiles74": {
"command": "docker",
"args": [
"run",
"-it",
"--rm",
"\\"
]
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is MCP Servers?
MCP Servers is a Docker container image that bundles several MCP servers for use with AI coding tools like Cursor. It provides Git repository access, PostgreSQL database connectivity, internet search via DuckDuckGo, and a memory/knowledge graph tool for persisting information across sessions.
How to use MCP Servers?
Pull and run the published Docker image, mapping the required ports and mounting your project directory and a .env file for database credentials. Alternatively, clone the repository, build the image locally with ./build.sh, and use the provided start-mcp-servers script. Once running, configure Cursor by adding the MCP server URLs (e.g., http://localhost:9099/sse for Git) in the MCP settings JSON file.
Key features of MCP Servers
- Bundles Git, PostgreSQL, DuckDuckGo Search, and Knowledge Graph MCP servers.
- Runs in a single Docker container with exposed ports.
- Includes an inspector tool at port 6274 for debugging.
- Provides a proxy for wrapping STDIO-based tools.
- Designed for easy integration with Cursor and similar tools.
Use cases of MCP Servers
- Manipulate a Git repository’s history and code directly from your AI assistant.
- Query and manage a PostgreSQL database using natural language prompts.
- Perform internet searches via DuckDuckGo during AI-assisted coding sessions.
- Store and retrieve structured data (e.g., project notes) between LLM sessions.
FAQ from MCP Servers
What MCP servers are included?
The container includes Git (with history), PostgreSQL database server, Internet Search (DuckDuckGo), and a knowledge graph for remembering stuff between sessions.
How do I connect PostgreSQL from the container?
Set the environment variable MCP_DATABASE_URI in your .env file to a PostgreSQL connection string, using host.docker.internal as the hostname. The container reads this file when started.
Does the Git server require any special configuration?
Yes, the Git server expects the project directory to be mapped to /project inside the container. You may need to remind the LLM that the project path is /project.
How can I test the MCP servers after starting the container?
Open the inspector at http://localhost:6274/ to see available tools and test them.
What ports are used by the different servers?
Port 6274 for the inspector, 9099 for Git, 9098 for PostgreSQL, 9097 for DuckDuckGo Search, and 9096 for Knowledge Graph.
Frequently asked questions
What MCP servers are included?
The container includes Git (with history), PostgreSQL database server, Internet Search (DuckDuckGo), and a knowledge graph for remembering stuff between sessions.
How do I connect PostgreSQL from the container?
Set the environment variable `MCP_DATABASE_URI` in your `.env` file to a PostgreSQL connection string, using `host.docker.internal` as the hostname. The container reads this file when started.
Does the Git server require any special configuration?
Yes, the Git server expects the project directory to be mapped to `/project` inside the container. You may need to remind the LLM that the project path is `/project`.
How can I test the MCP servers after starting the container?
Open the inspector at [http://localhost:6274/](http://localhost:6274/) to see available tools and test them.
What ports are used by the different servers?
Port 6274 for the inspector, 9099 for Git, 9098 for PostgreSQL, 9097 for DuckDuckGo Search, and 9096 for Knowledge Graph.
Basic information
More Cloud & Infrastructure MCP servers
Azure DevOps MCP Server
Tiberriver256An MCP server for Azure DevOps
🐳 docker-mcp
QuantGeekDevA docker MCP Server (modelcontextprotocol)
Supabase MCP Server
coleam00Supabase MCP server created in Python.
container-use
daggerDevelopment environments for coding agents. Enable multiple agents to work safely and independently with your preferred stack.
aws-finops-mcp-server
ravikiranvmAn MCP (Model Context Protocol) server that brings powerful AWS FinOps capabilities directly into your AI assistant. Analyze cloud costs, audit for waste, and get budget insights using natural language, all while keeping your credentials secure on your local machine.
Comments