MCP.so
Sign In

MCP Docker Compose Setup

@guanghuang

About MCP Docker Compose Setup

Docker Compose setup for multiple MCP servers (Oracle, PostgreSQL, Jira, etc.) with Nginx proxy, enabling AI assistants to access databases and services via SSE interface.

Basic information

Category

Cloud & Infrastructure

Transports

stdio

Publisher

guanghuang

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "mcp-docker-compose": {
      "command": "docker",
      "args": [
        "pull",
        "guang1/jdbc-mcp:latest"
      ]
    }
  }
}

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 Docker Compose Setup?

MCP Docker Compose Setup provides a Docker Compose configuration for running multiple MCP (Model Context Protocol) SSE services locally. It includes database services (Oracle, PostgreSQL, SQL Server), DevOps and collaboration tools (Azure DevOps, Jira, Confluence, Figma), and a search service (OpenSearch). This setup is intended for developers who want to use AI coding assistants that support SSE-based MCP servers, such as Cursor and Windsurf.

How to use MCP Docker Compose Setup?

Clone the repository, copy docker-compose.yml.sample to docker-compose.yml, configure DNS to resolve *-mcp.localhost to 127.0.0.1, edit configuration files in the mcp-configs directory with your credentials, then run docker-compose up -d to start all services. Access each service at http://{service-name}-mcp.localhost:8088 and add the SSE URLs to your AI assistant’s MCP configuration.

Key features of MCP Docker Compose Setup

  • Runs eight MCP services in Docker containers
  • Uses Nginx as a reverse proxy on port 8088
  • Supports SSE transport for MCP communication
  • Compatible with Cursor, Windsurf, and similar AI editors
  • All Docker images available on Docker Hub
  • Provides sample configuration files for each service
  • Recommends router-level wildcard DNS for simplicity

Use cases of MCP Docker Compose Setup

  • Run local MCP database servers for AI-assisted SQL queries
  • Integrate Azure DevOps, Jira, or Confluence with AI coding assistants
  • Enable AI tools to search documents via OpenSearch
  • Test and develop MCP-based integrations in an isolated environment
  • Provide a portable, containerized MCP server setup for teams

FAQ from MCP Docker Compose Setup

Which AI assistants are compatible with this setup?

Tools that support the SSE (Server-Sent Events) interface of MCP, such as Cursor and Windsurf. Tools that only support STDIO (e.g., current versions of Claude Desktop) are not compatible.

What are the prerequisites for running this setup?

You need Docker and Docker Compose installed, plus a DNS configuration that resolves all *-mcp.localhost hostnames to 127.0.0.1. Router-level DNS is recommended but host file entries also work.

How do I customize the configuration for each service?

Edit the corresponding .config files in the mcp-configs directory (e.g., postgres.config for PostgreSQL) with your connection credentials and parameters. You can also modify docker-compose.yml to add, remove, or update services.

How do I update the MCP Docker images?

Run docker-compose pull to fetch the latest images, then docker-compose down followed by docker-compose up -d to restart services. For a single service, use docker pull <image> and `docker-compose up -d --no-deps

Comments

More Cloud & Infrastructure MCP servers