SQLite Database — Query, Analyze & Manage Local Databases

Why SQLite MCP?

SQLite is the world's most deployed database — it powers your browser, your phone, and millions of apps. The SQLite MCP lets your AI agent query, analyze, and modify local databases without writing a single line of SQL. It's the simplest way to give your agent structured memory.

• Zero Setup: No server, no credentials, no network. Just point to a .db file.
• Natural Language SQL: "How many users signed up last week?" → The agent writes and executes the SQL.
• Data Analysis: Aggregate, filter, join, and visualize data from any SQLite database.
• Schema Management: Create tables, add columns, manage indexes through conversation.

Configuration

"mcpServers": {
  "sqlite": {
    "command": "npx",
    "args": [
      "-y", "@modelcontextprotocol/server-sqlite",
      "--db-path", "/path/to/your/database.db"
    ]
  }
}

Top Prompts

1. "Show me all tables in the database and their row counts."
2. "Find the top 10 customers by total order value in the last 90 days."
3. "Create a 'bookmarks' table with url, title, tags, and created_at columns."
4. "Export all orders from March as a CSV file."
5. "What's the average response time per endpoint from the api_logs table?"

Pairs Well With

Combine with the Filesystem MCP to load CSV/JSON data into SQLite for analysis, or with the Memory MCP to give your agent persistent structured memory backed by SQL.