Skip to main content

An MCP server that provides AI with direct access to SQLite databases.

Project description

MCP SQLite Tool

PyPI version License: MIT

An MCP server that provides AI with secure and direct access to SQLite databases.

🌟 Features

  • Secure Access: Allows AI to interact with SQLite databases while validating file paths to prevent unauthorized access.
  • Single-File Server: The core logic is contained in a single Python file, making it easy to understand and maintain.
  • Standard I/O (stdio) Transport: Implements the official MCP protocol using standard I/O for seamless integration with tools like VS Code.
  • Pythonic & Easy to Use: Built with the fastmcp framework, which uses decorators to simplify tool creation.

🚀 Installation

This tool is available as a package on PyPI. You can install it using pip.

pip install mcp-sqlite-tool

Note: This tool requires Python 3.10 or higher. The mcp[cli] dependency will be installed automatically.

🤖 Usage with VS Code

To use this tool with an MCP-compatible client like VS Code, you need to configure your workspace to discover and run the server.

  1. Install the package: Ensure you have the mcp-sqlite-tool package installed in the Python environment that VS Code is using.

    pip install mcp-sqlite-tool
    
  2. Configure settings.json: Open the Command Palette in VS Code (Ctrl+Shift+P), search for "Open Workspace Settings (JSON)", and add the following configuration:

    {
     "mcpServers": {
      "sqlite-query": {
       "command": "mcp-sqlite-tool"
      }
     }
    }
    
    • "sqlite-query": This name identifies the server. It must match the name specified in the Python tool's code (FastMCP("sqlite-query")).
    • "command": "mcp-sqlite-tool": This is the command-line entry point installed by pip. VS Code will use this to launch your server.
  3. Interact with the AI: Once configured, the AI client will be able to use the tool execute_sqlite_query. You can now prompt the AI to interact with your SQLite files.

Example Prompt

"Using the sqlite-query tool, tell me the names and emails of all users in the users table of C:\Users\John\Documents\project.db."

The AI will interpret this request and call your tool with the appropriate arguments.

🛠️ Tool Documentation

The core tool provided by this server is:

execute_sqlite_query

Executes a given SQL query on a specified SQLite database file.

Parameter Type Description
db_path str The absolute path to the SQLite database file.
sql_query str The SQL query to execute.

Returns: A dictionary containing the query results or an error message if the operation fails.

🤝 Contributing

Contributions, issues, and feature requests are welcome! If you have any issues, please contact me directly on Telegram (@mrbeandev).

📄 License

Distributed under the MIT License. See LICENSE for more information.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

mcp_sqlite_tool-0.1.2.tar.gz (4.3 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

mcp_sqlite_tool-0.1.2-py3-none-any.whl (5.0 kB view details)

Uploaded Python 3

File details

Details for the file mcp_sqlite_tool-0.1.2.tar.gz.

File metadata

  • Download URL: mcp_sqlite_tool-0.1.2.tar.gz
  • Upload date:
  • Size: 4.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.10.6

File hashes

Hashes for mcp_sqlite_tool-0.1.2.tar.gz
Algorithm Hash digest
SHA256 2cea9c33c98e291e3e4b2e5beaecb00b1fb02b1f3081d97cbbc2e0bdadc77dd3
MD5 15396e5ffd1cdce1d8d177afd09ac5c9
BLAKE2b-256 f06c82b33e92180d53122e7007435c79ec663454f0f457c83ad9c8c51253d471

See more details on using hashes here.

File details

Details for the file mcp_sqlite_tool-0.1.2-py3-none-any.whl.

File metadata

File hashes

Hashes for mcp_sqlite_tool-0.1.2-py3-none-any.whl
Algorithm Hash digest
SHA256 32ed69bcf7ed49e460565763d44b26a01b3fb543c85306beaffc069d2bb2fe89
MD5 431b665637992c3e6f55c54b6329735f
BLAKE2b-256 3ad030ce9972b7f6b629cac9e3fbe772afc52532348d850bd565faafe5b28f99

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page