literateMCP

Universal Source Management System

A flexible system for managing various types of sources (papers, books, webpages, etc.) and integrating them with knowledge graphs.

Features

Core Features

Universal source identification with internal UUID system
Support for multiple source types (papers, webpages, books, videos, blogs)
Multiple identifier support per source (arxiv, DOI, semantic scholar, ISBN, URL)
Structured note-taking with titles and content
Status tracking (unread, reading, completed, archived)

Entity Integration

Link sources to knowledge graph entities
Track relationships between sources and entities
Flexible relation types (discusses, introduces, extends, etc.)
Integration with memory graph

Prerequisites

This system integrates with the MCP Memory Server for persistent knowledge graph storage.

Quick Start

Create a new SQLite database with our schema:

# Create a new database
sqlite3 sources.db < create_sources_db.sql

Install the source management server:

# Install for Claude Desktop with your database path
fastmcp install source-manager-server.py --name "Source Manager" -e SQLITE_DB_PATH=/path/to/sources.db

Schema

Core Tables

-- Sources table
CREATE TABLE sources (
    id UUID PRIMARY KEY,
    title TEXT NOT NULL,
    type TEXT CHECK(type IN ('paper', 'webpage', 'book', 'video', 'blog')) NOT NULL,
    identifiers JSONB NOT NULL,
    status TEXT CHECK(status IN ('unread', 'reading', 'completed', 'archived')) DEFAULT 'unread'
);

-- Source notes
CREATE TABLE source_notes (
    source_id UUID REFERENCES sources(id),
    note_title TEXT NOT NULL,
    content TEXT NOT NULL,
    created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
    PRIMARY KEY (source_id, note_title)
);

-- Entity links
CREATE TABLE source_entity_links (
    source_id UUID REFERENCES sources(id),
    entity_name TEXT,
    relation_type TEXT CHECK(relation_type IN ('discusses', 'introduces', 'extends', 'evaluates', 'applies', 'critiques')),
    notes TEXT,
    PRIMARY KEY (source_id, entity_name)
);

Usage Examples

1. Managing Sources

Add a paper with multiple identifiers:

add_source(
    title="Attention Is All You Need",
    type="paper",
    identifier_type="arxiv",
    identifier_value="1706.03762",
    initial_note={
        "title": "Initial thoughts",
        "content": "Groundbreaking paper introducing transformers..."
    }
)

# Add another identifier to the same paper
add_identifier(
    title="Attention Is All You Need",
    type="paper",
    current_identifier_type="arxiv",
    current_identifier_value="1706.03762",
    new_identifier_type="semantic_scholar",
    new_identifier_value="204e3073870fae3d05bcbc2f6a8e263d9b72e776"
)

Add a webpage:

add_source(
    title="Understanding Transformers",
    type="webpage",
    identifier_type="url",
    identifier_value="https://example.com/transformers",
)

2. Note Taking

Add notes to a source:

add_note(
    title="Attention Is All You Need",
    type="paper",
    identifier_type="arxiv",
    identifier_value="1706.03762",
    note_title="Implementation details",
    note_content="The paper describes the architecture..."
)

3. Entity Linking

Link source to entities:

link_to_entity(
    title="Attention Is All You Need",
    type="paper",
    identifier_type="arxiv",
    identifier_value="1706.03762",
    entity_name="transformer",
    relation_type="introduces",
    notes="First paper to introduce the transformer architecture"
)

Query sources by entity:

get_entity_sources(
    entity_name="transformer",
    type_filter="paper",
    relation_filter="discusses"
)

Best Practices

Source Management
- Use consistent titles across references
- Provide as many identifiers as available
- Keep notes structured with clear titles
- Use appropriate source types
Entity Linking
- Be specific with relation types
- Add contextual notes to relationships
- Verify entity names against memory graph
- Keep entity relationships focused

Technical Details

Source Identification
- Internal UUID system for consistent referencing
- Multiple external identifiers per source
- Flexible identifier types (arxiv, doi, url, etc.)
- Title and type based fuzzy matching
Data Organization
- Structured notes with titles
- Clear source type categorization
- Entity relationship tracking
- Status management

Contributing

Fork the repository
Create a feature branch
Add tests for new features
Submit a pull request

This server cannot be installed

security - not tested

license - permissive license

quality - not tested

How are these scores calculated?

Server for managing academic literature with structured note-taking and organization, designed for seamless interaction with Claude. Built with SQLite for simplicity and portability.

Related MCP Servers

Needle MCP Serverofficial
needle-ai
A
security
A
license
A
quality
A server that allows users to manage documents and perform Claude-powered searches using Needle through the Claude Desktop application.
Last updated -
7
67
Python
MIT License
ClickUp Operator
noah-vh
-
security
F
license
-
quality
A Claude-compatible MCP server that enables storing and summarizing notes through a simple note storage system with custom URI scheme.
Last updated -
4
Python
MCP Database Server
JuanYin1
-
security
A
license
-
quality
Provides Claude with direct access to databases including SQLite, SQL Server, PostgreSQL, and MySQL, enabling execution of SQL queries and table management through natural language.
Last updated -
542
1
TypeScript
MIT License
jrnl MCP Server
yostos
A
security
A
license
A
quality
A server that enables Claude to access and search through command-line journal entries, offering features like searching entries, listing tags, and viewing journal statistics.
Last updated -
6
7
TypeScript
MIT License

View all related MCP servers