This MCP server provides a flexible system for managing various types of sources like papers, books, and webpages, integrating them with knowledge graphs. It allows you to track source information, take notes, and establish connections between sources and entities in your knowledge base.
Before installing, ensure you have access to the MCP Memory Server for persistent knowledge graph storage.
First, create a new SQLite database using the provided schema:
# Create a new database
sqlite3 sources.db < create_sources_db.sql
Install the source management server using fastmcp:
# 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
The system supports various source types and multiple identifiers per source.
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_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_source(
title="Understanding Transformers",
type="webpage",
identifier_type="url",
identifier_value="https://example.com/transformers",
)
Add structured notes to your sources:
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..."
)
Connect your sources to knowledge graph 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"
)
Retrieve sources related to specific entities:
get_entity_sources(
entity_name="transformer",
type_filter="paper",
relation_filter="discusses"
)
To add this MCP server to Claude Code, run this command in your terminal:
claude mcp add-json "source-manager" '{"command":"python","args":["source-manager-server.py"],"env":{"SQLITE_DB_PATH":"/path/to/sources.db"}}'
See the official Claude Code MCP documentation for more details.
There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json
file so that it is available in all of your projects.
If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json
file.
To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".
When you click that button the ~/.cursor/mcp.json
file will be opened and you can add your server like this:
{
"mcpServers": {
"source-manager": {
"command": "python",
"args": [
"source-manager-server.py"
],
"env": {
"SQLITE_DB_PATH": "/path/to/sources.db"
}
}
}
}
To add an MCP server to a project you can create a new .cursor/mcp.json
file or add it to the existing one. This will look exactly the same as the global MCP server example above.
Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.
The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.
You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.
To add this MCP server to Claude Desktop:
1. Find your configuration file:
~/Library/Application Support/Claude/claude_desktop_config.json
%APPDATA%\Claude\claude_desktop_config.json
~/.config/Claude/claude_desktop_config.json
2. Add this to your configuration file:
{
"mcpServers": {
"source-manager": {
"command": "python",
"args": [
"source-manager-server.py"
],
"env": {
"SQLITE_DB_PATH": "/path/to/sources.db"
}
}
}
}
3. Restart Claude Desktop for the changes to take effect