memcp is a Model Context Protocol (MCP) server that provides persistent memory capabilities for AI assistants like Claude. It enables storing and retrieving information across conversations using a local SQLite database.
Features
Persistent Storage: Store information that persists between conversations
Keyword-Based Search: Efficiently find stored memories using keyword associations
Simple Key-Value Store: Easy to use get/set operations with additional keyword metadata
Local SQLite Database: All data stored locally in a SQLite database you control
MCP Integration: Seamlessly integrates with Claude Desktop and other MCP clients
Installation
Install from PyPI:
pip install memcp
Or install from source:
git clone https://github.com/moshez/memcp.git
cd memcp
pip install -e .
Quick Start
Configure memcp in Claude Desktop by adding it to your claude_desktop_config.json:
{
"mcpServers": {
"memcp": {
"command": "/path/to/python",
"args": ["-m", "memcp", "--db", "/path/to/memory.db"]
}
}
}
See the full documentation for detailed configuration instructions.
Documentation
Full documentation is available at memcp.readthedocs.io.
Development
To set up a development environment:
# Clone the repository
git clone https://github.com/moshez/memcp.git
cd memcp
# Create virtual environment
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
# Install in development mode
pip install -e .
# Install development dependencies
pip install nox
# Run tests
nox -e tests
# Run linting
nox -e lint
# Build documentation
nox -e docs
License
MIT License - see LICENSE file for details.
Metadata
Release files for memcp 2025.6.28.7206
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| memcp-2025.6.28.7206.tar.gz | 18.3 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| memcp-2025.6.28.7206-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 39.5 kB
Release files / memcp-2025.6.28.7206.tar.gz
| Download URL | memcp-2025.6.28.7206.tar.gz |
|---|---|
| Size | 18.3 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
023ad5abcecb38dd43ba5919be2e7aa3341a9df685f59fe1457e38638d831ba5
|
|
BLAKE2b-256 checksum How to use checksums |
e9cad7e780204eb011abcd2532ceff6e32ea9adc764a29cf88641274daa0dde0
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.12.9
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jun 28, 2025.
Transparency logRelease files / memcp-2025.6.28.7206-py3-none-any.whl
| Download URL | memcp-2025.6.28.7206-py3-none-any.whl |
|---|---|
| Size | 21.2 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
31eec658a3771a4076fe87da3c17937b052842a5bd01584e5b10c7f953c58f6a
|
|
BLAKE2b-256 checksum How to use checksums |
4008b0ad6415410957d70da4e25ddbf5b94f00a8bdec926712998c413f89be6c
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.12.9
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jun 28, 2025.
Transparency log