A
licenseNot graded
qualityC
maintenanceMCP server for Substack that enables reading articles, comments, feed, and subscriptions from AI clients like Cursor and Claude, with optional authentication for paid content.
20 npm
2
MIT
substack-saved-mcp
by toniher
Related Servers
Alternatives to substack-saved-mcp
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityBmaintenanceMCP server that ingests Substack newsletters from Zoho Mail, archives them locally, and provides search and cross-author topic analysis tools for reading and comparing articles.MIT
- AlicenseBqualityDmaintenanceAn MCP server that gives Copilot access to Substack posts from your authenticated reader account, including paid subscriptions, enabling daily summary generation by syncing, caching, and summarizing posts.13MIT
- AlicenseAqualityBmaintenanceA credential-free MCP server that turns a Substack publication's public RSS archive and official analytics snapshots into a durable, queryable local SQLite ledger. It provides 12 MCP tools for browsing posts, tracking versions, recording metric snapshots, and analyzing content patterns.12Apache 2.0
- AlicenseAqualityDmaintenanceStandalone Substack CLI + 26-tool MCP server. Your IDE drafts the replies. Zero AI API keys.261MIT
- AlicenseNot gradedqualityBmaintenancePrivate MCP server for validating, previewing, creating, and updating Substack newsletter drafts through an MCP-compatible client.832 npm1Apache 2.0
TDQS
A3.7/5.0
Scored across 17 tools
Disambiguation4/5
Tools are clearly separated by resource type (posts vs notes) and action (save, unsave, search, list, get, sync). The main ambiguity is between get_saved_post and get_post_content, which both return post content, and search_saved_posts vs list_saved_posts could be confused without reading descriptions closely.
Naming Consistency4/5
The naming follows a mostly consistent snake_case verb_noun pattern: save_post, unsave_note, list_saved_posts, sync_saved_notes. The main deviation is saved_posts_status, which is a noun phrase rather than verb-first, and get_saved_post/get_post_content are slightly inconsistent in object phrasing.
Tool Count3/5
17 tools is slightly heavy, and the 16-25 range is considered borderline. However, the count is justified by having two parallel content domains (posts and notes) plus cache metadata status, publications, and audiences.
Completeness4/5
The tool set covers the full lifecycle for both saved posts and notes: save, unsave, search, list, get, content fetch, and sync. Minor gaps include no explicit tool to update read progress or manage cached deletion beyond soft-delete, but these are workable.
Maintenance
ActivityMaintained
ResponsivenessNo issues