substack-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CACHE_TTL_MS | No | Cache time-to-live in milliseconds (default: 1800000 = 30 minutes) | 1800000 |
| SUBSTACK_FEED_URL | Yes | The RSS feed URL for your Substack publication (required) |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_postsB | Search blog posts by keywords across title, content, and description |
| list_recent_postsC | List the most recent blog posts |
| get_post_by_titleC | Get a specific post by exact or partial title match |
| get_post_by_urlC | Retrieve a specific post by its URL |
| get_posts_by_date_rangeC | Get posts published within a date range |
| generate_citationB | Generate a formatted citation for a blog post |
| export_to_markdownC | Export blog posts to a markdown file |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 7 tools
The five retrieval tools differ by access pattern (keyword, recency, title, URL, date range), which is mostly clear. However, get_post_by_title and search_posts can overlap when a title is used as a keyword, and generate_citation vs export_to_markdown both consume posts, creating mild boundary blur.
All tools follow a consistent snake_case verb_noun pattern (search_posts, list_recent_posts, get_post_by_title, export_to_markdown). The convention is predictable and readable throughout.
Seven tools is well-scoped for a blog reading/search server, with each tool earning its place by covering a distinct retrieval or output mode.
Core read workflows (search, recency, by title, by URL, by date, cite, export) are well covered. Minor gaps exist around author/subscription or comment retrieval, but these are workable given the reading-focused scope.