Substack/Medium MCP Server

An MCP server that connects Claude to your Substack and Medium publications, enabling semantic search and analysis of your published content through RSS feeds and embeddings.

Installation

From source with uv

git clone https://github.com/yourusername/writer-context-tool.git
cd writer-context-tool
curl -LsSf https://astral.sh/uv/install.sh | sh
uv venv
source .venv/bin/activate
uv pip install -r requirements.txt

From source with pip

git clone https://github.com/yourusername/writer-context-tool.git
cd writer-context-tool
python -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt

Configuration

Claude Desktop

{
  "mcpServers": {
    "writer-tool": {
      "command": "${UV_PATH}",
      "args": [
        "--directory",
        "$(pwd)",
        "run",
        "writer_tool.py"
      ]
    }
  }
}

Platform Configuration

{
  "platforms": [
    {
      "type": "substack",
      "url": "https://yourusername.substack.com",
      "name": "My Substack Blog"
    },
    {
      "type": "medium",
      "url": "https://medium.com/@yourusername",
      "name": "My Medium Blog"
    }
  ],
  "max_posts": 100,
  "cache_duration_minutes": 10080,
  "similar_posts_count": 10
}

Available Tools

Tool	Description
search_writing	A semantic search tool that finds the most relevant essays using embeddings
refresh_content	Refreshes and recaches your content from all configured platforms

Features

• Fetches and persistently caches your blog posts from Substack and Medium
• Uses embeddings to find the most relevant essays based on your queries
• Makes individual essays available as separate resources for Claude
• Performs semantic search across your writing
• Pre-loads all content and generates embeddings on startup

Usage Examples

Find essays where I discuss [specific topic]

What have I written about [subject]?

Show me the full text of [essay title]

Refresh my writing content

Resources

• GitHub Repository

Notes

Requires Python 3.10 or higher and a Substack or Medium account with published content. The tool connects via RSS feeds and uses persistent disk caching with embeddings for semantic search.