Skip to main content

A Memory MCP server for pinning and recalling factoids.

Project description

Pin Memory

A Model Context Protocol (MCP) server for managing factoids across different scopes (global, workspace, and project).

Features

  • Pin: Store factoids in global, workspace-specific, or project-local storage.
  • Recall: Retrieve factoids based on current context.
  • MCP Integration: Exposes tools for LLMs to autonomously remember and recall information.

Installation

Using uv (recommended):

# Install as a global tool
uv tool install .

# Or run directly
uv run pin-memory mcp

Usage

CLI Commands

Pin Memory provides a CLI for managing factoids:

# List all factoids
pin-memory show

# Install agent instructions to AGENTS.md
pin-memory install --workspace my-workspace

# Launch the MCP server
pin-memory mcp

Scopes

  • Global: Stored in ~/.scartill/pin.
  • Workspace: Stored in ~/.scartill/pin/workspaces/<workspace_name>.
  • Project: Stored in .pin in the current working directory.

MCP Configuration

To use this with an MCP client (e.g. Claude Desktop, Gemini CLI), add it to your configuration:

{
  "mcpServers": {
    "pin-memory": {
      "command": "uv",
      "args": [
        "--directory",
        "C:/path/to/pin-memory",
        "run",
        "pin-memory",
        "mcp"
      ]
    }
  }
}

MCP Tools

pin

Stores a factoid in memory.

  • factoid_name: Name of the factoid.
  • factoid: The content of the factoid.
  • location: "global", "project", or "workspace/".

recall

Recalls all pinned factoids from global, requested workspace, and local project scopes.

  • workspace: Optional name of the workspace.

Development

# Clone the repository
git clone https://github.com/scartill/pin-memory.git
cd pin-memory

# Sync dependencies
uv sync

# Run tests (if applicable)
uv run pytest

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

pin_memory-0.1.0.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.

pin_memory-0.1.0-py3-none-any.whl (5.3 kB view details)

Uploaded Python 3

File details

Details for the file pin_memory-0.1.0.tar.gz.

File metadata

  • Download URL: pin_memory-0.1.0.tar.gz
  • Upload date:
  • Size: 52.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.5

File hashes

Hashes for pin_memory-0.1.0.tar.gz
Algorithm Hash digest
SHA256 8cbd1025f82e5867af79eff4860f1fe69d76a657b7bcb0e268647f1a40a379a4
MD5 8486a5d73f7c886e69289cb73dc03ff6
BLAKE2b-256 22feeb7cb22dad72dcdf356fca0eac7f7c8fbb901083e540c0a4a304b0c47028

See more details on using hashes here.

File details

Details for the file pin_memory-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: pin_memory-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 5.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.5

File hashes

Hashes for pin_memory-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 ec391e35382f4833bc136163f5152d213cbd22fb0c85760be04fd0ac1fb1feb0
MD5 0ad98fae9ac61b016fb833a4baef1c03
BLAKE2b-256 3fac3f56c99ba403bea9ce30e256fa1e108d7c6367060db0b77427937f37bd7c

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