Featured

Deploy OpenClaw in 60 seconds — 20% off logoDeploy OpenClaw in 60 seconds — 20% off

Launch OpenClaw on Hostinger in about 60 seconds and keep your agent live 24/7. Our referral link gives you 20% off, no coupon code needed.

Launch on Hostinger
Run your Hermes agent on Hostinger, fully managed logoRun your Hermes agent on Hostinger, fully managed

Launch Hermes on Hostinger in one click, fully managed, no VPS knowledge needed. Use code ZACAARON10 for 10% off.

Launch on Hostinger
Crawl and scrape any site into clean data, 10% off logoCrawl and scrape any site into clean data, 10% off

Firecrawl crawls and scrapes any site into clean markdown for your agent. Get 1,000 free credits, and new users get 10% off their first purchase.

Try Firecrawl free
6,000+ web scrapers for your AI agent, start free logo6,000+ web scrapers for your AI agent, start free

Apify gives your agent live web data: 6,000+ prebuilt scrapers and actors, MCP-ready. Sign up free with $5 in usage credits.

Try Apify free
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free
SetupClaw: done-for-you OpenClaw for founders & exec teams logoSetupClaw: done-for-you OpenClaw for founders & exec teams

White-glove OpenClaw for founders and exec teams (4–50+ employees): we install, harden, integrate your tools, and maintain it — secured from day one.

Get it set up for you
SEO data APIs for your agent, $1 free credit logoSEO data APIs for your agent, $1 free credit

DataForSEO gives your agent live access to SERP results, keyword data, backlinks, and on-page SEO data through one API. New accounts get a $1 credit, good for up to 20,000 keyword or backlink lookups.

Try DataForSEO free
Reach 48,000+ AI builders

A flat monthly placement in front of developers actively installing AI tools. No lock-in, cancel anytime.

Advertise here

Works with

Claude CodeClaude DesktopCursorVS CodeClineCodex CLIOpenClaw+ any MCP client

Install to Claude Code

This server doesn't publish a one-line install command. Follow the setup in the source repository.

Summary

An MCP server for automating Meetup event tracking with an AI agent. It equips the agent with tools to browse Meetup.com, detect new events since the last known record, and return structured event data.

README.md

meetup-mcp-server

An MCP server for automating Meetup event tracking with an AI agent. It equips the agent with tools to browse Meetup.com, detect new events since the last known record, and return structured event data — without manual scraping or copy-pasting.

Designed to be paired with a browser-use tool (e.g. Playwright MCP) so the agent can navigate Meetup pages, extract event details, and emit clean structured output.

What it can be used for

  • Tracking new past events from a Meetup group since the last recorded entry
  • Extracting structured event details: title, date, venue, attendees, speakers, and summary
  • Feeding event data into a pipeline, CMS, or data file in a repeatable and automatable way

Tools

load_skill — Loads step-by-step browsing instructions for a named skill (meetUp-events-lookup, meetUp-event-page).

dates_of_interest — Returns the date range of new events to collect — from the last recorded event up to today. Takes no parameters.

submit_meetup_events — Structured output tool: emits the list of new events found.

submit_event_details — Structured output tool: emits full detail for a single event page.

Quick start

Add to your MCP client config:

{
  "mcpServers": {
    "meetup": {
      "command": "npx",
      "args": ["@kwiknordic/meetup-events-scraper-mcp"]
    }
  }
}

To collect only events newer than your last recorded entry, pass EVENTS_JSON_URL:

{
  "mcpServers": {
    "meetup": {
      "command": "npx",
      "args": ["@kwiknordic/meetup-events-scraper-mcp"],
      "env": {
        "EVENTS_JSON_URL": "https://your-host/events.json",
        "START_DATE": "2026-05-15"
      }
    }
  }
}

To add the mcp-server to your Claude CLI via the terminal:

claude mcp add meetupEvents \
  --env EVENTS_JSON_URL=https://your-host/events.json \
  -- npx -y @kwiknordic/meetup-events-scraper-mcp

Configuration

START_DATE (optional) — Explicit start date in YYYY-MM-DD format. When set, the agent collects only events strictly after this date. Takes precedence over EVENTS_JSON_URL.

EVENTS_JSON_URL (optional) — URL to a JSON file containing past events. Used to determine the date of the most recent recorded event, so the agent knows where to start collecting. Ignored when START_DATE is set. If neither is set, the date range has no lower bound and the agent will collect all events up to today.

Events JSON format

If EVENTS_JSON_URL is set, it must return a JSON array of objects where each object has a date field in YYYY-MM-DD format. The server finds the most recent date and uses it as the exclusive lower bound when collecting new events. Any additional fields are ignored.

[{ "date": "2025-11-12" }, { "date": "2026-01-22" }, { "date": "2026-03-05" }]

In practice your array will likely carry more fields — only date is required:

[
  { "id": 314270265, "title": "Tech Night #12", "date": "2026-03-05", "attendees": 87 },
  { "id": 298451032, "title": "Tech Night #11", "date": "2026-01-22", "attendees": 64 }
]

Playbooks

Playbooks are step-by-step instruction sets loaded by load_skill at runtime. Each one guides the agent through a specific browsing task.

meetUp-events-lookup — navigates the Meetup "Past events" tab, determines the relevant date window, and collects new events via submit_meetup_events.

meetUp-event-page — opens a single event page, extracts all detail fields, and emits them via submit_event_details.

How it works

The agent calls load_skill (with meetUp-events-lookup or meetUp-event-page) to receive task-specific browsing instructions, then dates_of_interest to get the exact date window of interest. It then uses its browser tools to navigate Meetup.com and collect events that fall within that window. Finally it calls submit_meetup_events or submit_event_details to return the structured result.

The server itself does not browse the web — it provides the context and boundaries the agent needs to do that reliably.

Requirements

About me

  • Author: Mervin Bratic
  • Website: https://kwik.se

License

MIT © Mervin Bratic — see LICENSE.

See related servers & alternatives →

Related MCP servers

Browse all →

Related guides

Hand-picked reading to help you choose and use Browser & Scraping servers.