Skip to main content
Glama
paulet4a-commits

webdatatools-social-mcp

by paulet4a-commits
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

substack_scraper

Extract per-post metadata from any Substack publication's public archive API: title, author, date, paywall status, word count, likes, comments, with optional full article text.

Instructions

Scrapes any Substack publication's own public JSON archive API — title, author, publish date, paywall status, word count, likes and comments per post, one row per post, with an RSS fallback and optional full article text. Billed to your own Apify account: ~$0.0005 per Post (Apify free-plan price, lower on paid plans).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
freeOnlyNoFree posts only — Keep this on to skip posts marked paywalled/subscriber-only (isPaywalled) and only return posts anyone can read.
maxPostsNoMax posts per publication — Enter how many of the most recent posts to fetch per publication, e.g. 50. The Actor pages through the publication's own archive API in batches of 50 until this many posts are collected.
includeBodyNoInclude full article text — Keep this off for metadata only (fast). Turn it on to also fetch each post's own page and extract its full article text into bodyText — one extra request per post.
publicationsYesPublications — Enter one Substack publication per row: a subdomain handle (bariweiss), a full subdomain (bariweiss.substack.com), or any post/publication URL on a custom domain (https://www.thefp.com or https://www.thefp.com/p/some-post). Example: ["bariweiss"].

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and does well: it discloses billing to the user's own Apify account with a per-post price estimate, reveals the RSS fallback path, and warns that includeBody costs one extra request per post. It does not mention auth requirements or rate limits, but 'public JSON archive API' implies no credentials are needed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with output scope and followed by cost/billing context. Every clause earns its place by either describing returned data or setting cost expectations.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema or annotations exist, so the description must describe returns — and it enumerates the per-post fields and the one-row-per-post shape, which is adequate. Minor gaps remain around pagination limits and auth, though those are partially covered by the schema and the 'public API' phrasing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so each parameter already has a rich description (freeOnly, maxPosts, includeBody, publications formats). The description adds only marginal mapping, e.g. 'optional full article text' to includeBody and 'paywall status' to freeOnly, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource — scraping a Substack publication's public JSON archive API — and enumerates the returned fields (title, author, publish date, paywall status, word count, likes, comments). This clearly distinguishes it from the YouTube/Google/Telegram/Bluesky scrapers among its siblings, which target entirely different platforms.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the resource (use this to scrape Substack publications) and it notes an RSS fallback, but it never states when to prefer this over adjacent tools like podcast_lookup or when it is inappropriate. No explicit when/when-not framing is present.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools