Data Engineer Stack
Build, maintain, and optimize data pipelines with direct access to databases, file systems, and containerized workflows.
Token Budget
Moderate token usage. You will have good room for prompts but watch if adding more servers.
Config
Paste in ~/.claude.json
{
"mcpServers": {
"github-mcp": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-github"
],
"env": {
"GITHUB_PERSONAL_ACCESS_TOKEN": "YOUR_GITHUB_PERSONAL_ACCESS_TOKEN"
}
},
"docker-mcp": {
"command": "npx",
"args": [
"-y",
"docker-mcp"
]
},
"filesystem-mcp": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-filesystem",
"/path/to/allowed/directory"
]
},
"postgres-mcp": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-postgres",
"postgresql://localhost/mydb"
],
"env": {
"POSTGRES_CONNECTION_STRING": "YOUR_POSTGRES_CONNECTION_STRING"
}
},
"redis-mcp": {
"command": "npx",
"args": [
"-y",
"redis-mcp"
],
"env": {
"REDIS_URL": "YOUR_REDIS_URL"
}
},
"mongodb-mcp": {
"command": "npx",
"args": [
"-y",
"mongodb-mcp"
],
"env": {
"MONGODB_URI": "YOUR_MONGODB_URI"
}
}
}
}Included Servers
PostgreSQL MCP
Anthropic
Query and interact with PostgreSQL databases, inspect schemas, and run SQL directly from your AI editor.
Queries and manages your primary relational data warehouse where structured data lives and transforms happen.
MongoDB MCP
Community
Query MongoDB databases, inspect collections, and analyze documents directly from your AI editor.
Handles unstructured and semi-structured data ingestion from APIs, logs, and event streams.
Redis MCP
Community
Interact with Redis databases. Get, set, and manage keys, run commands, and monitor your Redis instances from your AI editor.
Provides high-speed caching and message queuing for real-time data pipeline orchestration.
Filesystem MCP
Anthropic
Read, write, search, and manage files on your local filesystem with secure directory-scoped access for your AI editor.
Reads and writes CSV, JSON, and Parquet files for batch processing and data staging between pipeline steps.
GitHub MCP
Anthropic
Access the GitHub API to manage repositories, issues, pull requests, branches, and workflows directly from your AI editor.
Version-controls your pipeline code, dbt models, and transformation scripts with proper review workflows.
Docker MCP
Community
Manage Docker containers, images, volumes, and networks. Run, stop, inspect, and monitor containers from your AI editor.
Containerizes pipeline jobs for consistent execution across development, staging, and production environments.
Recommended Skills
Skills that pair with the servers in this stack. Learn more
For PostgreSQL MCP
PostgreSQL optimization guide covering query performance, connection management, indexing strategies, and schema design.
npx skillsadd supabase/agent-skills/supabase-postgres-best-practicesPostgreSQL table design patterns including normalization, indexing, partitioning, and data type selection.
npx skillsadd wshobson/agents/postgresql-table-designFor Redis MCP
Official Redis skill with 29 rules across 11 categories covering Redis Query Engine, vector search, semantic caching, and pub/sub.
npx skillsadd redis/agent-skills/redis-developmentFor GitHub MCP
Use gh CLI for all GitHub operations including stacked PR workflows, issue management, and CI/CD automation.
npx skillsadd callstackincubator/agent-skills/githubDebug and fix failing GitHub PR checks in GitHub Actions. Automatically diagnoses CI issues and suggests fixes.
npx skillsadd openai/skills/gh-fix-ciAddress PR review comments using GitHub CLI. Streamlines the code review response workflow.
npx skillsadd openai/skills/gh-address-commentsAutomated code review for TypeScript, JavaScript, Python, Go. Analyzes PRs for complexity, SOLID violations, and code smells.
For Docker MCP
Multi-stage builds, image optimization, container security, Compose orchestration, and production deployment patterns.
npx skillsadd sickn33/antigravity-awesome-skills/docker-expertCI/CD pipelines, infrastructure automation, containerization, and cloud platform expertise. Pairs with Docker MCP for hands-on container management.