mcp-luma

@pipeworx/luma

Public event discovery from Luma (lu.ma): curated city feeds, one event's full detail, and an organizer's public calendar — the same data a browser sees on lu.ma/discover and on each event's own public page.

Part of Pipeworx — an MCP gateway connecting AI agents to 1800+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.

Tools

• luma_places(query?, limit?) — list Luma's curated discover cities, with place_id, coordinates, timezone and live event_count. Use to find a place_id for luma_events, or just pass a city name directly.
• luma_events(city? | place_id?, query?, limit?, cursor?) — list public upcoming events for a discover city. Pass a city name (resolved for you against luma_places) or a place_id. An optional keyword filters on event name/venue/organizer, matched client-side.
• luma_event(event_id) — full public detail for one event: description, timing, venue, categories, ticket types, FAQs, hosts and calendar.
• luma_calendar_events(calendar_id, limit?, cursor?) — public upcoming events on an organizer's calendar page (a company's or community's event series).

None of these return guest lists or attendee data — see "Privacy" below.

Auth

Keyless. No account, API key or registration needed — these are Luma's own public discovery endpoints, the same ones a signed-out browser calls.

Data sources

• Luma, public event-discovery feed — city "discover" pages, individual event pages, and organizer calendar pages, all served to any visitor without an account.

Privacy

Luma's own payload for an event carries per-event attendee signal: a guest count, and for well-attended events a "featured guests" list naming and showing avatars for people who RSVP'd, plus (for an authenticated caller) their own RSVP record. This pack strips all of it before returning anything — guest_data, featured_guests, guest_info, host_info and manager_info are dropped in every tool. Only the event itself, its public organizer/host listing (the people or orgs who publicly listed themselves as running the event — a different thing from attendees), and its calendar are returned.

Notes

• luma_events's query filters client-side. Luma's own query parameter on the discover-events endpoint does not actually filter server-side (verified live: identical result sets with and without it for the same place), so this pack paginates the upstream itself (up to 200 events) and matches on event name, venue and organizer name instead.
• Place/city resolution (luma_events given a city) matches against the live discover-places list by exact name/slug first, then by substring. There is no local cache of places — each resolution is a fresh call, since the list is small (under 100 cities) and changes as Luma launches new ones.
• Event and calendar IDs (evt-..., cal-...) are opaque Luma identifiers. The easiest way to get one is from a prior luma_events or luma_calendar_events call — every returned event carries its own event_id, and its calendar.url leads to the organizer's public page.

Quick Start

Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):

{
  "mcpServers": {
    "luma": {
      "url": "https://gateway.pipeworx.io/luma/mcp"
    }
  }
}

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/luma/mcp returns the tools in the table above plus the shared Pipeworx meta-tools — ask_pipeworx, discover_tools, search_within, remember/recall and the rest of the gateway-wide set. So the tool count you see is larger than this table: a single-pack endpoint currently lists roughly 30 shared tools alongside the pack's own. The connection's initialize response states its exact scope, and is the authoritative answer for a given day.

This is deliberate, not multiplexing by accident. The meta-tools are what let a scoped connection answer a question this pack does not cover — via ask_pipeworx, which routes across the whole catalog — without you adding a second MCP server. There is currently no way to mount a pack endpoint without them; if the extra schemas cost you more context than the routing is worth, connect to the full gateway once rather than to several pack endpoints.

Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:

{
  "mcpServers": {
    "pipeworx": {
      "url": "https://gateway.pipeworx.io/mcp"
    }
  }
}

Both URLs reach the same gateway and the same 1800+ data sources. The only difference is which pack's tools are listed directly; ask_pipeworx reaches all of them from either one.

No MCP client? Call it over HTTP

curl -X POST https://gateway.pipeworx.io/v1/tools/luma_places \
  -H 'Content-Type: application/json' \
  -d '{"query":"san","limit":10}'

No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/luma_places. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.

Standalone (no gateway account)

This package also runs as a local stdio MCP server — no Pipeworx account, no gateway round-trip:

{
  "mcpServers": {
    "luma": {
      "command": "npx",
      "args": ["-y", "@pipeworx/mcp-luma"]
    }
  }
}

Or run it directly to confirm it starts:

npx -y @pipeworx/mcp-luma

It speaks MCP over stdin/stdout and answers initialize/tools/list/tools/call for only this pack's tools — none of the shared meta-tools the gateway connection above adds. Same source, same tools, no ask_pipeworx routing.

Using with ask_pipeworx

Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:

ask_pipeworx({ question: "your question about Luma data" })

The gateway picks the right tool and fills the arguments automatically.

More

• Docs and guides
• pipeworx.io

License

MIT