Skip to main content

MCP server for Lore Framework - AI-readable project memory with task/ADR/wiki management

Project description

Lore Framework MCP (Python)

MCP server for Lore Framework - AI-readable project memory with task/ADR/wiki management.

Important: This MCP server is just one component of Lore Framework. For the complete experience (skills, hooks, agents), install the full plugin: lore-framework plugin

Installation

# Using uvx (recommended)
uvx lore-framework-mcp

# Using pip
pip install lore-framework-mcp

Usage

As MCP Server

Add to your .mcp.json:

{
  "mcpServers": {
    "lore-framework": {
      "command": "uvx",
      "args": ["lore-framework-mcp"]
    }
  }
}

As CLI

# Set current user
lore-framework-mcp set-user <user_id>
lore-framework-mcp set-user --env  # from LORE_SESSION_CURRENT_USER

# Set current task
lore-framework-mcp set-task <task_id>

# Show session state
lore-framework-mcp show-session

# List available users
lore-framework-mcp list-users

# Clear current task
lore-framework-mcp clear-task

# Regenerate indexes
lore-framework-mcp generate-index
lore-framework-mcp generate-index --next-only --quiet

MCP Tools

Tool Description
lore_framework_set_user Set current user from team.yaml
lore_framework_set_task Set current task by ID (creates symlink)
lore_framework_show_session Show current session state (user and task)
lore_framework_list_users List available users from team.yaml
lore_framework_clear_task Clear current task symlink
lore_framework_generate_index Regenerate lore/README.md and next-tasks.md

Why Lore?

LLMs need "why", not just "what".

Without history, LLMs treat existing code patterns as gospel—replicating legacy hacks, undocumented workarounds, and accidental complexity. Lore provides AI-readable project memory: tasks capture requirements, worklogs show reasoning, ADRs explain decisions.

Read more: Full motivation

Lore Directory Structure

lore/
├── 0-session/           # Session state (gitignored)
│   ├── team.yaml        # Team members definition
│   ├── current-user.md  # Active user (generated)
│   ├── current-task.md  # Symlink to active task
│   └── next-tasks.md    # Auto-generated task queue
├── 1-tasks/             # Task management
│   ├── active/          # In-progress tasks
│   ├── blocked/         # Blocked tasks
│   ├── backlog/         # Planned tasks
│   └── archive/         # Completed tasks
├── 2-adrs/              # Architecture Decision Records
├── 3-wiki/              # Project documentation
└── README.md            # Auto-generated index

Documentation

See full documentation: Lore Framework Plugin

Author

License

MIT

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

lore_framework_mcp-1.2.8.tar.gz (8.9 kB view details)

Uploaded Source

Built Distribution

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

lore_framework_mcp-1.2.8-py3-none-any.whl (10.5 kB view details)

Uploaded Python 3

File details

Details for the file lore_framework_mcp-1.2.8.tar.gz.

File metadata

  • Download URL: lore_framework_mcp-1.2.8.tar.gz
  • Upload date:
  • Size: 8.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for lore_framework_mcp-1.2.8.tar.gz
Algorithm Hash digest
SHA256 08b75dfd50066b8a40deeac463df5a447fa0c08e3aeb9b84fb830412c3afc1dd
MD5 70fe03714d42548c440c2a8d3137759f
BLAKE2b-256 1800a1afd887cc243372df00d1564bcf1686e90b99ce61c04b42330906f2af2e

See more details on using hashes here.

Provenance

The following attestation bundles were made for lore_framework_mcp-1.2.8.tar.gz:

Publisher: publish-lore-framework-mcp-py.yml on maledorak/maledorak-marketplace

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file lore_framework_mcp-1.2.8-py3-none-any.whl.

File metadata

File hashes

Hashes for lore_framework_mcp-1.2.8-py3-none-any.whl
Algorithm Hash digest
SHA256 db545fa1da9ce85da065b60b012163bbb20f4eb063fb22d0fc55addd3fd4709b
MD5 a5abf05cd9e4cc83df931ac7588d08c1
BLAKE2b-256 6a68937243bd3a754b2b7b200515091fbb6228154bdb9cdc7227079a95dcc8f9

See more details on using hashes here.

Provenance

The following attestation bundles were made for lore_framework_mcp-1.2.8-py3-none-any.whl:

Publisher: publish-lore-framework-mcp-py.yml on maledorak/maledorak-marketplace

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

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