download_substackLABSCO SUMMARY
One job, and the parsing is the job.
Handing a model a Substack URL and asking it to fetch the page gets you navigation, subscription prompts and comment scaffolding along with the article. Separating title, author, subtitle and body is what makes a summary request land on the actual text. Public posts only — anything behind a paywall is out of scope.
What it is
A single-purpose server for reading Substack posts. Give it a post URL and it downloads and parses the page, returning the structured pieces rather than raw HTML.
What you get
- download_substack takes a Substack post URL and returns its content
- Title, author, subtitle and body are extracted separately rather than handed back as one blob
- Works with public Substack posts
Requirements
Node.js v18 or higher. The package is mcp-substack, version 0.1.0, installed from a checkout with npm install; the client runs it by pointing node at lib/index.mjs. No account, no key.
Setup effort
Build from source — get the source, then follow the steps on this page and add the configuration for your client
USE CASES
01
Summarising an article someone sent you
The post's text arrives parsed, without the page furniture around it.
02
Quoting a piece accurately
Title, author and subtitle come back as separate fields for attribution.
1 tool
Listed in project docs. Your client may show a different list.
BEFORE YOU INSTALL
What to know first
Tools you get
1 tool named in the project's documentation.
Requires
Node.js v18 or later
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
Get the source, then follow the steps on this page and add the configuration for your client. This one is built from source rather than installed with a single command.
Server setup
TERMINAL
git clone https://github.com/michalnaka/mcp-substack
cd mcp-substack
npm install
npm startMCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"mcp-substack": {
"command": "/opt/homebrew/bin/node",
"args": [
"<YOUR_PATH_TO_MCP_SUBSTACK>/lib/index.mjs"
],
"methods": {
"download_substack": {
"description": "Download and parse content from a Substack post"
}
}
}
}
}/opt/homebrew/bin/node is where Homebrew puts Node on Apple Silicon Macs. If yours is elsewhere, use the full path of your own node (run which node, or where node on Windows). <YOUR_PATH_TO_MCP_SUBSTACK> is the folder you cloned.
