Skip to main content

A FastMCP-based service for storing and retrieving project files in a SQLite database

Project description

Memory Bank

A FastMCP-based service for storing and retrieving project files in a SQLite database.

Overview

Memory Bank provides a simple file storage system organized by projects, allowing you to:

  • List all available projects
  • List files within a project
  • Read file contents
  • Write new files
  • Update existing files

All data is stored in a SQLite database for persistence.

Installation

From PyPI

pip install memory-bank-mcp

From Source

  1. Clone this repository
  2. Install dependencies:
uv sync --dev

Configuration

Environment variables can be set in a .env file in the project root:

# .env file
DB_PATH=./data/memory_bank.db

Running the Server

python main.py

By default, the server runs on stdio. To run on SSE (Server-Sent Events) over network, modify main.py:

mcp.run(transport="sse", host="0.0.0.0", port=8000)

API Tools

List Projects

Lists all projects in the memory bank.

List Project Files

Lists all files in a specific project.

Read File

Reads the content of a specific file from a project.

Write File

Creates a new file in a project. Will not overwrite existing files.

Update File

Updates the content of an existing file in a project.

Project Structure

memory_bank/
├── .env                    # Environment variables configuration
├── README.md               # Project documentation 
├── main.py                 # Application entry point
├── db_init.py              # Database initialization scripts
├── config.py               # Configuration settings
├── database/
│   └── database.py         # Database connection and operations
└── api/
    ├── __init__.py         # API package initialization
    └── tools.py            # FastMCP tool definitions

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

memory_bank_mcp-0.0.1.tar.gz (52.1 kB view details)

Uploaded Source

Built Distribution

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

memory_bank_mcp-0.0.1-py3-none-any.whl (10.5 kB view details)

Uploaded Python 3

File details

Details for the file memory_bank_mcp-0.0.1.tar.gz.

File metadata

  • Download URL: memory_bank_mcp-0.0.1.tar.gz
  • Upload date:
  • Size: 52.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.2

File hashes

Hashes for memory_bank_mcp-0.0.1.tar.gz
Algorithm Hash digest
SHA256 4f9727044b7d759068195632bf1a5d8df4878a7618d08d3bfcf55425f206679f
MD5 72630a86ad89e62d49823f451c6e2c98
BLAKE2b-256 71d09e6f65808e483825bb9cac8678f056a1105dc49b472c18a674ca6a8e6a15

See more details on using hashes here.

File details

Details for the file memory_bank_mcp-0.0.1-py3-none-any.whl.

File metadata

File hashes

Hashes for memory_bank_mcp-0.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 6b71f63645246e5959cadd98481699514781dd71e300d6c11d0bea887e94f39a
MD5 46b778fd6eeff9fac1ce9ac7da9d9fbc
BLAKE2b-256 106395111e8789d4976fc918b0366e6fa3c17881dacee5581ed0d0113dcf8111

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