StackMCP

Python + FastAPI Stack for Claude Desktop

Intermediate5 servers33.5K tokens

Configuration

{
  "mcpServers": {
    "postgres-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-postgres",
        "postgresql://localhost/mydb"
      ],
      "env": {
        "POSTGRES_CONNECTION_STRING": "YOUR_POSTGRES_CONNECTION_STRING"
      }
    },
    "docker-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "docker-mcp"
      ]
    },
    "context7-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@upstash/context7-mcp"
      ]
    },
    "github-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-github"
      ],
      "env": {
        "GITHUB_PERSONAL_ACCESS_TOKEN": "YOUR_GITHUB_PERSONAL_ACCESS_TOKEN"
      }
    },
    "filesystem-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-filesystem",
        "/path/to/allowed/directory"
      ]
    }
  }
}

Where to save

Paste the config above into:

~/Library/Application Support/Claude/claude_desktop_config.json

Environment Variables

Replace the YOUR_ placeholders with your actual values.

POSTGRES_CONNECTION_STRINGrequired

PostgreSQL connection string (e.g. postgresql://user:pass@localhost:5432/mydb)

Used by: PostgreSQL MCP

GITHUB_PERSONAL_ACCESS_TOKENrequired

GitHub personal access token

Used by: GitHub MCP

What’s in this stack

PostgreSQL MCP8 tools

Query and interact with PostgreSQL databases, inspect schemas, and run SQL directly from your AI editor.

FastAPI apps almost always use Postgres via SQLAlchemy or Tortoise. Query your database and inspect schemas without a separate tool.

Docker MCP14 tools

Manage Docker containers, images, volumes, and networks. Run, stop, inspect, and monitor containers from your AI editor.

Python dependency management is notoriously fragile. Docker gives you reproducible environments from dev to production.

Context7 MCP2 tools

Pull up-to-date documentation and code examples for any library directly into your prompt context using the Context7 API.

FastAPI, Pydantic, and SQLAlchemy docs at your fingertips. These libraries have breaking changes between versions — current docs matter.

GitHub MCP20 tools

Access the GitHub API to manage repositories, issues, pull requests, branches, and workflows directly from your AI editor.

Manage your API repo, CI workflows, and code reviews. Python projects benefit from PR-based review to catch type issues early.

Filesystem MCP11 tools

Read, write, search, and manage files on your local filesystem with secure directory-scoped access for your AI editor.

Read config files, write generated code, and manage project structure. Essential for scaffolding FastAPI's route-heavy file layout.

Other editors

Claude CodeCursorVS CodeWindsurfContinue