Install DB MCP

Pick your client, copy the command, done.

Manual setup required. The maintainer's config contains paths only you know - edit the placeholders below before adding it to Claude Code.

Run this once before adding it to Claude Code.

git clone https://github.com/daviddata-cloud/MCP_DB
cd MCP_DB

Then follow the repository README for any remaining dependency or build steps.

claude mcp add db-mcp-6421 -- python /path/to/db_mcp_server.py

Replace any placeholder paths in the command with the real path on your machine.

Environment Variables

Set these before running DB MCP.

VariableDescriptionRequired

HR_CSV_PATHPath to the HR CSV file to be loaded into the database.No

Once configured, DB MCP gives your AI agent access to:

hr_metadataReturn the 3-line metadata header read from the HR CSV file.

hr_schemaReturn SQLite schema information for the employees table.

hr_queryExecute a read-only SQL query (SELECT/WITH only) against the in-memory SQLite database.

sqllimit

hr_find_peoplePerform a structured search on employee data without writing SQL.

After setup, try these prompts with your AI agent:

→What is the metadata for the current HR dataset?

→Show me the schema for the employees table.

→Run a query to count how many employees are in each department.

→Find all employees with the last name Smith.

Prerequisites & system requirements

An MCP-compatible client (Claude Code, Cursor, Windsurf, Claude Desktop, or Codex)
Python 3.8+ with pip installed

Conare · memory for coding agents

Save the docs, env vars, and workflow around DB MCP in Conare so Claude Code, Codex, and Cursor remember it next time.