Substack
This MCP server implementation enables downloading and parsing of Substack posts for integration with Claude's desktop app. Developed as an open-source Node.js project, it provides a streamlined interface for retrieving article content, including title, author, and full text. The server leverages libraries like Cheerio for HTML parsing and the Model Context Protocol SDK for standardized communication. It stands out by focusing specifically on Substack content extraction, making it particularly useful for researchers, writers, and analysts who want to easily incorporate Substack articles into their AI-assisted workflows for tasks like summarization, content analysis, or trend identification.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- productivity
- Source
- PulseMCP
- Repository
- github.com/michalnaka/mcp-substack
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Substack from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.