🎉 First public release of Substak‑MCP
Substak‑MCP is an open‑source Model Context Protocol (MCP) server for Substack. It lets AI clients such as Claude Desktop, Claude Code, Cursor, Codex, Windsurf, and Antigravity draft, publish, schedule, analyze, and research Substack publications from natural‑language prompts.
If this project saves you time, please consider sponsoring its development. ❤️
✨ Highlights
- Full publishing workflow: create, update, publish, schedule, preview, duplicate, and analyze posts.
- Public Substack research: RSS feeds, integration options, profile lookup, topic research, post / publication analysis, study plans, coding‑lesson extraction.
- Content strategy: post analysis, idea generation, repurposing, gap analysis, title/hook optimization, series planning.
- Safety first: confirmation‑token flow for high‑risk write actions (
create_formatted_post,update_post,publish_post,schedule_post,duplicate_post,delete_draft). - Encrypted local browser session storage under
~/.substack-mcp-plus/. - Works with any MCP client that supports a stdio server definition.
📦 Install
npm install -g github:IgnazioDS/Substak-MCP
substack-mcp-plus-setupThen point your MCP client at the substack-mcp-plus command. See the README for full setup, client config, and example prompts.
🔧 Requirements
- Node.js ≥ 16
- Python ≥ 3.10
- A Substack publication URL such as
https://yourpublication.substack.com
🛠️ Tools included
Publishing & account: create_formatted_post, update_post, publish_post, schedule_post, list_drafts, list_published, list_scheduled_posts, get_post_content, get_post_analytics, duplicate_post, preview_draft, upload_image, delete_draft, get_sections, get_subscriber_count.
Developer & public research: get_publication_rss_feed, get_substack_integration_options, search_substack_profiles_by_linkedin, research_substack, research_substack_post, research_substack_publication, study_topic_on_substack, extract_coding_lessons.
Strategy: analyze_my_posts, generate_post_ideas, repurpose_post, content_gap_analysis, title_and_hook_optimizer, series_planner.
📝 Notes
This project is unofficial and is not affiliated with Substack Inc. See the README’s Known Limitations section for an honest list of current edge cases.
💖 Sponsor & support
- ❤️ Sponsor on GitHub
- ⭐ Star the repo so other Substack writers and AI builders can find it
- 🐛 File an issue
- 🔀 PRs welcome
Thanks for trying Substak‑MCP! Feedback and contributions are very welcome.