Metadata-Version: 2.4
Name: folios
Version: 0.5.0
Summary: MCP server for versioned document retrieval, metadata access, and diff capabilities
Project-URL: Homepage, https://github.com/alex-pradas/folios
Project-URL: Repository, https://github.com/alex-pradas/folios
Project-URL: Documentation, https://alex-pradas.github.io/folios
Author-email: Alejandro Pradas Gómez <alex@pradas.eu>
License: MIT
License-File: LICENSE
Keywords: documents,fastmcp,mcp,versioning
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Programming Language :: Python :: 3.14
Requires-Python: >=3.12
Requires-Dist: fastmcp>=2.0.0
Requires-Dist: pydantic>=2.0.0
Description-Content-Type: text/markdown

# Folios

<p align="center">
  <img src="folio_logo.png" alt="Folios Logo" width="120">
</p>

[![PyPI version](https://badge.fury.io/py/folios.svg)](https://badge.fury.io/py/folios)
[![Tests](https://github.com/alex-pradas/folios/actions/workflows/publish.yml/badge.svg)](https://github.com/alex-pradas/folios/actions/workflows/publish.yml)
[![codecov](https://codecov.io/gh/alex-pradas/folios/branch/main/graph/badge.svg)](https://codecov.io/gh/alex-pradas/folios)
[![Python 3.12+](https://img.shields.io/badge/python-3.12+-blue.svg)](https://www.python.org/downloads/)
[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
[![Docs](https://img.shields.io/badge/docs-GitHub%20Pages-blue)](https://alex-pradas.github.io/folios/)

A lightweight Model Context Protocol (MCP) server for querying your local library of documents.

![Example](example.png)

**[Documentation](https://alex-pradas.github.io/folios/)**

## What problem solves folios?

When working in engineering applications, AI agents often need access to a variety of internal documents such as design practices, guidelines, and specifications that are stored in a local, document-based knowledge management system. While Retreival Augmented Generation (RAG) implementation can provide such functionality, setting it up and maintaining it up to date can be complex and time-consuming. Why not accessing the documents directly? If the master information is stored in documents, Agentic AI is not going to change the quality processes that are already in place to manage knowledge in companies, so I believe in giving agents read-only access to the document library is a more straightforward approach. However, giving agent access to those system repositories con be challenging due to the restricted nature of their APIs or the lack of privileged access.

If you are developing agentic workflows, in order to mock the functionality to give agents the access to such complex management systems, Folios provides a simple MCP server that can be pointed to a folder of properly formatted Markdown files. This allows AI assistants to perform the same query behaviour with a very low setup cost from the user/developer side.

## Features

- **Zero Config** - Just point to a folder of Markdown files and go
- **Local First** - Your documents stay on your machine or network, no cloud dependencies
- **Flexible Metadata** - Use any frontmatter fields your workflow needs
- **Versioned Documents** - Store multiple versions with simple `{id}_v{version}.md` naming

## One-liner to install, run and configure

```bash
uvx folios --path /path/to/your/documents
```

## Quick guide to get started

### 1. Create your documents folder

Any normal local folder will do. Documents follow the naming convention `{id}_v{version}.md`:

```folder
documents/
├── 123456_v1.md
├── 123456_v2.md
└── 789012_v1.md
```

### 2. Add YAML frontmatter to each document

Frontmatter is flexible - include any fields your workflow requires:

```markdown
---
author: "J. Smith"
date: "2025-01-15"
document_type: "Design Practice"
status: "Approved"
reviewer: "A. Johnson"
---

# Stress Analysis Design Practice

Lorem ipsum dolor sit amet, consectetur adipiscing elit.

## Background

More text here...
```

Only the `---` delimiters and an H1 title are required. Missing fields show "NA" in responses.

### 3. Run the server

you can run folios directly with one terminal command

```bash
uvx folios --path /path/to/your/documents
```

alternatively, you can add it to your LLM Client MCP configuration:

```json
{
  "mcpServers": {
    "folios": {
      "command": "uvx",
      "args": ["folios", "--path", "/path/to/your/documents"],
      }
    }
  }
```

We have tested it with [Claude Desktop](https://claude.ai/desktop) and the [GitHub Copilot Extension for VS Code](https://code.visualstudio.com/docs/copilot/overview), but it should work with any MCP-compatible client.

## MCP Tools

| Tool | Parameters | Description |
|------|------------|-------------|
| `get_document_content` | `document_id`, `version?` | Retrieve document content (latest if version omitted) |
| `get_document_metadata` | `document_id`, `version?` | Get metadata including auto-parsed chapters |
| `diff_document_versions` | `document_id`, `from_version`, `to_version` | Diff between two versions |
| `list_documents` | `status?`, `document_type?`, `author?` | List documents with optional filters |
| `list_document_versions` | `document_id` | List all versions of a document |

## Document Schema

### Core Metadata Fields

These fields are always present in metadata responses:

| Field | Type | Description |
|-------|------|-------------|
| `id` | int | Unique document identifier (from filename) |
| `version` | int | Version number (from filename) |
| `title` | str | Document title (from H1 heading) |
| `author` | str | Document author ("NA" if not in frontmatter) |
| `date` | str | Publication date ("NA" if not in frontmatter) |
| `chapters` | list | Auto-parsed from H2 headings |

### Dynamic Fields

Any additional frontmatter fields are included in metadata responses. Common examples:

- `document_type` - Document type (Design Practice, Guideline, etc.)
- `status` - Document status (Draft, Approved, etc.)
- `reviewer`, `approver` - Approval workflow fields
- Custom fields for your specific workflow

## Configuration

### Documents Path

Provide the documents folder path via CLI flag or environment variable:

| Option | Description |
|--------|-------------|
| `--path` | Path to documents folder (CLI flag) |
| `FOLIOS_PATH` | Path to documents folder (environment variable) |

### Field Configuration (Optional)

Create a `folios.toml` in your documents folder to define allowed values for fields:

```toml
[fields.status]
values = ["Draft", "In Review", "Approved", "Withdrawn"]

[fields.document_type]
values = ["Design Practice", "Guideline", "Best Practice", "TRS"]

[fields.department]
values = ["Engineering", "Manufacturing", "HR"]
```

This helps agents understand what values are valid for each field.

## Development

```bash
git clone https://github.com/alex-pradas/folios
cd folios
uv sync

# Run locally
FOLIOS_PATH=./examples/documents uv run folios

# Run tests
uv run pytest
```

## License

This project is licensed under the terms of the MIT license.
