Data Analyst stack

For analysts who pair-program with Claude Code on dbt models, notebooks, and ad-hoc Python scripts. Local filesystem access for CSVs, MCP servers for git + Postgres so the agent can introspect your warehouse, a memory MCP for project context across sessions, and a heavyweight LLM router so you can A/B between Claude and OpenAI for cost-versus-accuracy.

What's in this stack

• Claude Code
  Anthropic's terminal-native coding agent with MCP-native tool use and skills system.
  npm_package
• Anthropic
  Claude model family — the default Claude Code provider. Sonnet, Opus, Haiku.
  env_key
• Filesystem MCP Server
  Official MCP reference server for safe local filesystem access (read/write within allowed paths).
  mcp_npm
• Git MCP Server
  Official MCP reference server for local git operations — log, diff, blame, branch, status.
  mcp_pip
• postgres
  Connect to your PostgreSQL database to query data and schemas.
  external_link
• Memory MCP Server
  Official MCP reference server providing a persistent knowledge-graph memory across sessions.
  mcp_npm
• LiteLLM
  OSS unified-API router for 100+ LLM providers with caching, fallbacks, and budgets.
  pip_package

How to use it

Click any entity above for its install instructions. Most are one-line installs; the MCP servers are JSON-config additions to your Claude Code config file.

The free Arcade tier lists these entities for browsing + per-entity install. Arcade Pro adds 1-click bulk-install: with one button in the desktop app, the entire stack lands configured and ready.

← Browse all arcade categories · data/arcade.json