Skip to main content

memorious-mcp

Memorious-MCP is a minimal Model Context Protocol (MCP) server that provides a persistent key-value memory store with vector-similarity lookup using ChromaDB.

Features

  • FastMCP-based MCP stdio server exposing three tools: store, recall, and forget.
  • ChromaDB backend (ChromaMemoryBackend) persisting data on disk using Chroma's PersistentClient.
  • Tests (integration) that exercise store/recall/forget behavior.
  • Standard Python package layout for easy installation and distribution.

Getting Started

  1. Install the package (recommended in a virtual environment):
# Install in development mode
uv sync

# Or install from source
pip install .
  1. Run the server (stdio transport, suitable for local/CLI integrations):
# Using uv
uv run memorious-mcp --collection memories

# Or if installed globally
memorious-mcp --collection memories
  1. Call tools using an MCP client (FastMCP client or a compatible MCP client) over stdio.

Example Tool Signatures

  • store(key: str, value: str) -> {"id": str}
  • recall(key: str, top_k: int = 3) -> {"results": [...]} where each result includes id, key, value, distance, timestamp
  • forget(key: str, top_k: int = 3) -> {"deleted_ids": [...]}

Testing

Run tests with:

# Using uv
uv run python -m pytest tests/ -v

# Or if pytest is available globally
pytest tests/ -v

Package Structure

The project follows the standard Python package layout:

memorious-mcp/
├── src/
│   └── memorious_mcp/
│       ├── __init__.py
│       ├── main.py                 # MCP server entry point
│       └── backends/
│           ├── __init__.py
│           ├── memory_backend.py   # Abstract base class
│           └── chroma_backend.py   # ChromaDB implementation
├── tests/
│   └── test_chroma_backend.py      # Integration tests
├── pyproject.toml                  # Package configuration
└── README.md

Notes

  • By default memory persistence is enabled and stored under ./.memorious. You can override persist_directory when creating ChromaMemoryBackend in code.
  • The backend uses Chroma's default embedding function when available.
  • The package is configured with a console script entry point for easy command-line usage.

Contributing

Contributions are welcome. Open a PR with tests.

Metadata

Release files for memorious-mcp 0.0.2

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for memorious-mcp 0.0.2
File Size Uploaded Provenance
memorious_mcp-0.0.2.tar.gz 5.6 kB Without provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for memorious-mcp 0.0.2
File Interpreter ABI Platform
memorious_mcp-0.0.2-py3-none-any.whl Python 3 none any Details

Total release size: 13.5 kB

Release files / memorious_mcp-0.0.2.tar.gz

Download URL memorious_mcp-0.0.2.tar.gz
Size 5.6 kB
Tags Source
SHA-256 checksum
How to use checksums
35d5dccd0961a74dbbc89e40748f7a392f96f2b969f55a52425d255889d879b4
BLAKE2b-256 checksum
How to use checksums
f1cf2f0dea2f9f6013dc6d218ac3163d750558e33dd966fb8b0b0583f09b7005
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.12.3

Release files / memorious_mcp-0.0.2-py3-none-any.whl

Download URL memorious_mcp-0.0.2-py3-none-any.whl
Size 7.9 kB
Tags Python 3
SHA-256 checksum
How to use checksums
7b3766774843aa64f379e3eba761319bdb4ee8c88482ec8fb68ab765f491b0df
BLAKE2b-256 checksum
How to use checksums
8fc675a299ead1ae990f344d1e4a34ac447ed47051cda4455357d39ef9513632
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.12.3

Security for memorious-mcp 0.0.2

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.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

0.0.2 This release

2 release files No provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page