Medium Articles Scraper

Medium stories by tag, author, or publication with claps, responses, and tags.

Documentation

Medium Articles Scraper MCP Server

Glama score MCP Registry npm version npm downloads license

An MCP server for the Mamba Labs Medium Articles Scraper actor on Apify. Medium stories as rows.

What's Inside

What it does

Takes Medium tags, authors, publications, or story links and returns one row per story with title, link, author, publication, publish date, reading time, claps, responses, member-only flag, and tags, optionally the story text, plus a free summary row per source.

All of the work runs on Apify. This package is a thin client that starts the actor run, waits for it, and hands back the dataset rows.

Quick start

You need Node.js 18 or newer and an Apify account with an API token.

Add this to your Claude Desktop config (claude_desktop_config.json), Cursor, or any MCP client:

{
  "mcpServers": {
    "mamba-medium-articles-scraper": {
      "command": "npx",
      "args": [
        "-y",
        "@mambalabsdev/mcp-medium-articles-scraper"
      ],
      "env": {
        "APIFY_TOKEN": "your-apify-token"
      }
    }
  }
}

Restart the client. The get_medium_articles tool appears.

Prerequisites

Example prompts

  • "Get the 50 newest Medium stories tagged python with their claps."
  • "Which stories did the Netflix Technology Blog publish on Medium since October 1, and which got the most claps?"

Tool

get_medium_articles. One tool. Example arguments:

{
  "tags": [
    "python"
  ],
  "max_stories_per_source": 10
}

Inputs

Every buyer facing input of the actor. Omitted inputs take the actor's own defaults.

InputTypeRequiredDescription
tagsarraynoMedium tags such as python or data-engineering, or tag links such as https://medium.com/tag/python.
authorsarraynoMedium usernames (netflixtechblog or @netflixtechblog) or profile links (https://medium.com/@netflixtechblog, https://name.medium.com).
publicationsarraynoPublication slugs (better-programming), links (https://medium.com/better-programming), or the publication's own domain (netflixtechblog.com).
story_urlsarraynoLinks to single Medium stories, on medium.com or a publication's own domain. The story ID at the end of the link is what is read.
max_stories_per_sourcenumbernoStories to read from each tag, author, or publication. Default 25, maximum 2000.
since_datestringnoOptional. A date such as 2026-11-01, or a number of days back such as 7. Older stories are skipped and not charged.
include_textbooleannoyes to add each story's body as plain text, billed as a story with text. Member-only stories return the preview a logged-out reader sees, marked incomplete. Default no.
max_charge_usdnumbernoOptional. The run stops before a charge that would pass this amount. Summary rows are always returned.

Pricing

Pay per event on Apify, billed to your Apify account. Prices in USD.

EventFree planBronzeSilverGold
story-row, one story$0.003$0.00285$0.0027$0.00255
story-text-row, one story with its text$0.005$0.00475$0.0045$0.00425
apify-actor-start, per run start$0.005$0.005$0.005$0.005

Source summaries, missing names, blocked reads, and refused input are free. Mamba Labs pays the platform costs of the run, Apify proxy traffic included.

Full actor documentation

apify.com/mambalabs/medium-articles-scraper

License

MIT. See LICENSE.