StackMCP

Data Science Stack for Claude Code

Intermediate5 servers15.4K tokens

Configuration

{
  "mcpServers": {
    "postgres-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-postgres",
        "postgresql://localhost/mydb"
      ],
      "env": {
        "POSTGRES_CONNECTION_STRING": "YOUR_POSTGRES_CONNECTION_STRING"
      }
    },
    "sqlite-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "sqlite-mcp"
      ]
    },
    "filesystem-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-filesystem",
        "/path/to/allowed/directory"
      ]
    },
    "exa-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "exa-mcp-server"
      ],
      "env": {
        "EXA_API_KEY": "YOUR_EXA_API_KEY"
      }
    },
    "sequential-thinking-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-sequential-thinking"
      ]
    }
  }
}

CLI Commands

Alternatively, add each server via the Claude Code CLI:

claude mcp add postgres-mcp -e POSTGRES_CONNECTION_STRING=YOUR_POSTGRES_CONNECTION_STRING -- npx -y @modelcontextprotocol/server-postgres postgresql://localhost/mydb
claude mcp add sqlite-mcp -- npx -y sqlite-mcp
claude mcp add filesystem-mcp -- npx -y @modelcontextprotocol/server-filesystem /path/to/allowed/directory
claude mcp add exa-mcp -e EXA_API_KEY=YOUR_EXA_API_KEY -- npx -y exa-mcp-server
claude mcp add sequential-thinking-mcp -- npx -y @modelcontextprotocol/server-sequential-thinking

Where to save

Paste the config above into:

~/.claude.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

EXA_API_KEYrequired

Exa API key

Used by: Exa Search 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.

Query production databases directly from your AI assistant. Essential for exploratory data analysis without writing one-off scripts.

SQLite MCP6 tools

Query and manage SQLite databases. Create tables, run queries, and inspect data directly from your AI editor.

Spin up lightweight local databases for experiments and intermediate results. Perfect for prototyping data pipelines before scaling to Postgres.

Filesystem MCP11 tools

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

Read CSVs, write outputs, and manage Jupyter notebooks. Data science lives and dies by file I/O.

Exa Search MCP3 tools

AI-powered web search and crawling with Exa. Get semantically relevant results, extract content, and find similar pages.

Find research papers, datasets, and methodology references with semantic search. Speeds up the literature review phase significantly.

Sequential Thinking MCP1 tools

Enable structured, step-by-step reasoning for complex problem solving. Helps AI break down problems into logical sequences.

Statistical analysis and pipeline design require step-by-step reasoning. Prevents your AI from skipping critical assumptions in complex analyses.

Other editors

CursorVS CodeWindsurfClaude DesktopContinue