Luma Events MCP Server
A FastMCP server that discovers events from Luma — combining the Discover feed and subscribed calendars — with distance filtering and ICS export. No API key required for basic discovery.
Agenten stärken
Der eigene Befehl des Herausgebers. Kein PlugMCP-Endpunkt.
Host a copy with our keys and logs.
uvx luma-mcp==0.1.0Claude Code hat keinen Installationslink für einen lokalen Befehl. Kopieren Sie den Befehl unten und führen Sie ihn in einem Terminal aus.
claude mcp add io.github.alx1p-luma-mcp -- uvx luma-mcp==0.1.0In einem Terminal ausführen.
{ "mcpServers": { "io.github.alx1p-luma-mcp": { "command": "uvx", "args": [ "luma-mcp==0.1.0" ] } }}claude_desktop_config.json
Remote-URL oder ein Befehl auf Ihrem Rechner? Worin sich die beiden Installationen unterscheiden
Auf PlugMCP ausführen
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
StartenVom Herausgeber
A FastMCP server that discovers events from Luma — combining the Discover feed and subscribed calendars — with distance filtering and ICS export. No API key required for basic discovery.
Discover events from Luma — search by category, city, distance, and keywords with calendar export
Luma's Discover API has two endpoints that behave very differently:
This MCP uses both via two search modes:
city param) — searches your preferred categories via the Category API. Deep, rich results filtered by address and distance.city) — fetches the curated top events for that city via the Place API.On first run, the server returns popular events near you (geo-biased by IP), then walks you through setting up categories, address, and login for progressively richer results.
git clone <this-repo>
cd "Luma Cal MCP"
uv venv .venv --python 3.12
source .venv/bin/activate
uv pip install -e .
To access events from calendars you follow on Luma, install the optional auth dependencies:
uv pip install -e ".[auth]"
playwright install chromium
On first use, the raw Discover feed returns hundreds of popular events near you (geo-biased by IP). The server then walks you through setup one prompt at a time to narrow results:
Each prompt appears after returning results, so you see events immediately. After you configure a preference, the search reruns automatically and the next prompt appears. You can respond "not now" (prompt reappears next time) or "never" (permanently dismissed).
Use set_preferences to save defaults that persist across restarts:
set_preferences(address="3180 18th St, San Francisco", max_distance_miles=15)
set_preferences(categories=["ai", "tech"])
# stdio transport (for Cursor, Claude Desktop, etc.)
fastmcp run src/luma_mcp/server.py
# or directly
python -m luma_mcp.server
Subscribed calendars require a Luma session cookie. The server handles this automatically via an inline login flow.
How it works:
search_events with login=true. A Chromium browser opens to lu.ma/signin; log in normally. The session cookie is stored in the local SQLite DB.search_events with skip_login_days=N to defer (0 = ask next time, -1 = never).The server maintains a local SQLite database (~/.luma-mcp/events.db by default) that records the first time each event is seen. This enables two filters on search_events:
added_within_days — only return events first seen within the last N days.new_only — only return events that have never been seen before.Every result also includes first_seen_at (ISO timestamp) and is_new (boolean).
Add to your Cursor MCP settings (.cursor/mcp.json):
{
"mcpServers": {
"luma-events": {
"command": "uv",
"args": [
"run",
"--directory", "/path/to/Luma Cal MCP",
"fastmcp", "run", "src/luma_mcp/server.py"
],
"env": {
"PYTHONPATH": "/path/to/Luma Cal MCP/src"
}
}
}
}
Without logging in, the server still works — Discover is fully available with no authentication.
Set a home address via set_preferences(address="...") with max_distance_miles. In home mode, events beyond the radius are excluded. Events without location data are included by default (with distance_miles: null). In travel mode, distance filtering uses the city center at 25 miles automatically.
Geocoding uses Nominatim (free, OpenStreetMap) by default. For higher volume, set GEOCODING_PROVIDER=google or mapbox with the corresponding GEOCODING_API_KEY in your environment.
Event times (start_at, end_at) are returned in the user's system timezone. The timezone field from Luma is included in every result for reference.
get_event returns the RSVP URL; there's no headless registration path. Use export_event_ics to add events to your calendar.api.lu.ma), which can change without notice. Breakage is isolated to luma_web_client.py.Discover events from Luma — search by category, city, distance, and keywords with calendar export
{ "mcpServers": { "io.github.alx1p-luma-mcp": { "command": "uvx", "args": [ "luma-mcp==0.1.0" ] } }}Tools
Noch keine Tool-Liste. Remote-Server erhalten eine nach dem ersten Health-Check.
FAQ
Kopieren Sie auf dieser Seite die stdio-Konfiguration für Cursor, Claude Desktop, Claude Code oder VS Code. Sie nutzt die Installation des Herausgebers, keinen PlugMCP-Proxy.
In diesem Eintrag ist keine erforderliche Umgebungsvariable aufgeführt.
Luma Events läuft lokal über stdio.
Zuletzt geprüft: 2026-11-09. Discover events from Luma — search by category, city, distance, and keywords with calendar export