SQLite Explorer MCP server for AI agents

SQLite Explorer MCP Server is a tool that allows Large Language Models (LLMs) to safely explore and query SQLite databases through the Model Context Protocol (MCP). It provides read-only access with built-in safety features and query validation, making it ideal for data exploration tasks.

System Requirements

Python 3.6+
SQLite database file (specified via environment variable)

Installation

Install the required dependencies:

# Using pip
pip install -r requirements.txt

Dependencies

fastmcp: Framework for building Model Context Protocol servers

MCP Tools

The server provides these tools for database interaction:

read_query

read_query(query: str, params: Optional[Dict] = None, row_limit: int = 100) -> List[Dict]

Executes a SELECT query on the database with safety validations:

Query validation and sanitization
Parameter binding support
Row limit enforcement
Results formatted as dictionaries

list_tables

list_tables() -> List[str]

Lists all available tables in the database.

describe_table

describe_table(table_name: str) -> Dict

Returns detailed schema information for a specific table, including:

Column names and types
NULL constraints
Default values
Primary key information

Setup Options

Option 1: Install for Claude Desktop

# Clone the repository
git clone https://github.com/hannesrudolph/sqlite-explorer-fastmcp-mcp-server.git
cd sqlite-explorer-fastmcp-mcp-server

# Install using FastMCP
fastmcp install sqlite_explorer.py --name "SQLite Explorer" -e SQLITE_DB_PATH=/path/to/db

Replace /path/to/db with the path to your SQLite database file.

Option 2: Install for Cline VSCode Plugin

To use with the Cline VSCode plugin:

Clone the repository:

git clone https://github.com/hannesrudolph/sqlite-explorer-fastmcp-mcp-server.git

In VSCode, click the server icon (☰) in the Cline plugin sidebar
Click the "Edit MCP Settings" button (✎)
Add this configuration to the settings file:

{
  "sqlite-explorer": {
    "command": "uv",
    "args": [
      "run",
      "--with",
      "fastmcp",
      "--with",
      "uvicorn",
      "fastmcp",
      "run",
      "/path/to/repo/sqlite_explorer.py"
    ],
    "env": {
      "SQLITE_DB_PATH": "/path/to/your/database.db"
    }
  }
}

Replace:

/path/to/repo with the full path to the cloned repository
/path/to/your/database.db with the full path to your SQLite database file

Environment Variables

The following environment variable is required:

SQLITE_DB_PATH: Full path to the SQLite database file you want to explore

Usage Examples

Listing Tables

To list all tables in the database:

tables = list_tables()
print(tables)  # Returns a list of all table names

Describing Table Schema

To get schema information for a specific table:

schema = describe_table("users")
print(schema)  # Returns detailed column information

Executing Queries

To run a simple SELECT query:

results = read_query("SELECT * FROM users LIMIT 10")
print(results)  # Returns a list of dictionaries, each representing a row

To use parameter binding for safe queries:

results = read_query(
    "SELECT * FROM users WHERE age > :min_age",
    params={"min_age": 25},
    row_limit=50
)
print(results)

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "sqlite-explorer" '{"command":"uv","args":["run","--with","fastmcp","--with","uvicorn","fastmcp","run","/path/to/repo/sqlite_explorer.py"],"env":{"SQLITE_DB_PATH":"/path/to/your/database.db"}}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "sqlite-explorer": {
            "command": "uv",
            "args": [
                "run",
                "--with",
                "fastmcp",
                "--with",
                "uvicorn",
                "fastmcp",
                "run",
                "/path/to/repo/sqlite_explorer.py"
            ],
            "env": {
                "SQLITE_DB_PATH": "/path/to/your/database.db"
            }
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "sqlite-explorer": {
            "command": "uv",
            "args": [
                "run",
                "--with",
                "fastmcp",
                "--with",
                "uvicorn",
                "fastmcp",
                "run",
                "/path/to/repo/sqlite_explorer.py"
            ],
            "env": {
                "SQLITE_DB_PATH": "/path/to/your/database.db"
            }
        }
    }
}

3. Restart Claude Desktop for the changes to take effect