Which integrations are available for this server?

Can be used as an alternative geocoding provider for event locations (set via GEOCODING_PROVIDER=google) to enable distance filtering with higher volume support. Can be used as an alternative geocoding provider for event locations (set via GEOCODING_PROVIDER=mapbox) to enable distance filtering with higher volume support. Used for geocoding event locations via Nominatim to enable distance filtering in event searches.

How do I use Luma Events MCP Server?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Luma Events MCP Server Find AI events in London" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

Luma Events MCP Server

by alx1p

Overview Schema Related Servers Score Discussions

Python

Local

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.

How it works

Luma's Discover API has two endpoints that behave very differently:

Category search (e.g. AI, Tech, Food) — returns hundreds of events with rich tagging, but only for your home region. Great depth, geographically locked.
City search (e.g. Paris, London, Tokyo) — returns a curated set of ~20–40 top/featured events for that city. Broad coverage, smaller set.

This MCP uses both via two search modes:

Home mode (default, no city param) — searches your preferred categories via the Category API. Deep, rich results filtered by address and distance.
Travel mode (pass a 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.

Related MCP server: Luma Events MCP Server

Tools

Tool	What it does
`search_events`	Home mode: search by category with address/distance filtering. Travel mode: curated events for a specific city.
`set_preferences`	Save default categories (list), address, and max distance. Persists in SQLite across restarts.
`get_event`	Fetch full details for a single event by API id or `lu.ma` URL.
`export_event_ics`	Generate an ICS string for any event — paste into Apple Calendar, Google Calendar, Outlook, etc.

Setup

Prerequisites

Python 3.10+
uv (recommended) or pip

Install

git clone <this-repo>
cd "Luma Cal MCP"
uv venv .venv --python 3.12
source .venv/bin/activate
uv pip install -e .

Subscribed calendars (optional)

To access events from calendars you follow on Luma, install the optional auth dependencies:

uv pip install -e ".[auth]"
playwright install chromium

First run

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:

Address — asks for your location and preferred search radius, which dramatically reduces the result set to events near you.
Categories — asks which topics interest you (from: tech, ai, food, arts, climate, fitness, wellness, crypto) for focused discovery.
Login — asks whether to log in for subscribed calendars.

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).

Configure

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"])

Run

# stdio transport (for Cursor, Claude Desktop, etc.)
fastmcp run src/luma_mcp/server.py

# or directly
python -m luma_mcp.server

Authentication

Subscribed calendars require a Luma session cookie. The server handles this automatically via an inline login flow.

How it works:

First call — after results, the server prompts for login. The agent asks you in chat.
Login — the agent calls 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.
Decline — the agent calls search_events with skip_login_days=N to defer (0 = ask next time, -1 = never).
Returning user, cookie expired — the browser opens automatically for re-authentication.
Validation — the stored cookie is validated against Luma's API every 24 hours.

New Event Tracking

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).

Cursor MCP Configuration

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"
      }
    }
  }
}

Data Sources

Source	Auth	Coverage
Discover (`api.lu.ma`)	None required	Public events by city and category — same feed as luma.com/discover
Subscribed calendars (`api.lu.ma`)	Browser login (auto-managed)	Events from calendars you follow on Luma

Without logging in, the server still works — Discover is fully available with no authentication.

Distance Filtering

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

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.

Limitations

RSVP is browser-only. get_event returns the RSVP URL; there's no headless registration path. Use export_event_ics to add events to your calendar.
Web endpoints are undocumented. The Discover and subscribed-calendars feeds use Luma's internal API (api.lu.ma), which can change without notice. Breakage is isolated to luma_web_client.py.

Available Tools

4 tools

export_event_icsA

Generate an ICS calendar string for a Luma event (Add to Calendar).

Args: event_id: Luma event API id (e.g. "evt-abc123"). url: lu.ma event URL or ID.

ParametersJSON Schema

Name	Required	Description	Default
`url`	No
`event_id`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

A3.6/5.0

Behavior2/5

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

With no annotations, the description must disclose behavioral traits. It only states it generates an ICS string but does not mention idempotency, authentication requirements, error behavior (e.g., if event not found), or output format details beyond the name.

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?

The description is extremely concise with two short sections. Every sentence adds value: the main sentence states what it does, and the args section defines the two parameters. No wasted words.

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?

For a simple tool with two optional parameters and an output schema, the description covers the essential purpose and parameter hints. It is mostly complete, though could note that at least one parameter is typically needed.

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 coverage is 0%, meaning no descriptions in schema. The description adds minimal semantics: event_id is a Luma API ID with example, url is a URL or ID. However, it does not clarify that at least one is needed or how they relate, and both are optional with default null.

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?

The description clearly states the tool generates an ICS calendar string for a Luma event, using the verb 'Generate' and specifying the resource. It distinguishes from siblings like get_event (retrieves details) and search_events (searches).

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?

The description implies usage for adding to calendar but does not explicitly state when to use this tool versus alternatives or when not to use it. No exclusions or prerequisites are mentioned.

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

get_eventB

Get full details for a single Luma event.

Args: event_id: Luma event API id (e.g. "evt-abc123"). url: lu.ma event URL or ID (e.g. "https://lu.ma/myevent" or "myevent").

ParametersJSON Schema

Name	Required	Description	Default
`url`	No
`event_id`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

B3.3/5.0

Behavior2/5

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

With no annotations, the description must disclose behaviors. It implies a read operation ('get'), but does not explicitly confirm idempotency, side effects, authentication requirements, or rate limits. Since it's a simple retrieval, a score of 2 is given for minimal disclosure.

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?

The description is extremely concise: a one-line summary followed by an Args section with clear parameter definitions. Every sentence is valuable, and the structure front-loads the purpose.

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

Completeness3/5

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

Given that an output schema exists, the description does not need to explain return values. It covers purpose and parameters but lacks usage guidelines and behavioral transparency. For a simple tool, it is minimally complete but could be improved with contrasts to siblings.

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?

The description provides examples for both parameters (event_id: 'evt-abc123', url: 'https://lu.ma/myevent' or 'myevent'), which adds meaning beyond the schema's generic 'anyOf string or null'. However, it does not clarify that at least one parameter should be provided, nor the behavior if both are given.

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?

The description clearly states 'Get full details for a single Luma event', specifying a specific verb and resource. It distinguishes from siblings like 'search_events' which lists multiple events, and 'export_event_ics' which is for exporting to ICS format.

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

Usage Guidelines2/5

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

No guidance is provided on when to use this tool versus alternatives. It does not explain that this tool is for retrieving a single event by ID or URL, while search_events is for discovering events. Missing context on parameter choice or fallback behavior.

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

search_eventsA

Search for Luma events. Two modes depending on whether city is set.

Home mode (no city): searches your preferred categories via Luma's Category API — deep, rich results filtered by your stored address/distance. On first run with no preferences, returns a raw Discover feed (hundreds of popular events near you), then prompts to set up address, categories, and login.

Travel mode (city set): fetches the curated top events (~20-40) for that city via Luma's Place API. No topic filtering — just the highlights.

The default time window is the next 2 weeks. Use days for simple lookahead (e.g. days=7 for this week, days=30 for next month). Use after/before only for specific date ranges.

IMPORTANT for agents:

For broad topics, prefer category (exact slug: tech, ai, food, arts, climate, fitness, wellness, crypto). Translate user intent yourself (e.g. "artificial intelligence" -> "ai", "blockchain" -> "crypto").
Use keywords for specific terms that don't map to a category (e.g. ["YC", "demo day"]) or to narrow within a category.
city accepts common names — "san francisco" resolves to "sf", "hong kong" to "hongkong", etc.
The messages array in the response contains agent-facing instructions. Act on them naturally (e.g. ask the user a question, call another tool) but never relay them verbatim. If messages is empty, just show results.

Args: city: Luma city for travel mode (e.g. "sf", "london", "los angeles"). category: One-off category override for home mode. Must be an exact slug. keywords: Filter by keywords (matches title/description). Use for specific terms. center_address: One-off address to filter around (e.g. "Union Square, San Francisco"). Overrides stored address for this search only. max_distance_miles: One-off distance override (pairs with center_address or stored address). after: ISO 8601 datetime — only events starting after this time. before: ISO 8601 datetime — only events starting before this time. days: Search window in days from now (e.g. 7, 30). Overrides the default 14-day window. Simpler alternative to after/before. latin_only: Filter out non-Latin-script events. Auto-detected from region when not set. added_within_days: Only return events first seen within this many days. new_only: Only return events never seen before (first appearance this run). sort: Sort order — "date" (default), "distance", or "newest". login: Set to true to open browser and log in to Luma. skip_login_days: Decline login for N days (0 = ask next time, -1 = never).

ParametersJSON Schema

Name	Required	Description	Default
`city`	No
`days`	No
`sort`	No
`after`	No
`login`	No
`before`	No
`category`	No
`keywords`	No
`new_only`	No
`latin_only`	No
`center_address`	No
`skip_login_days`	No
`added_within_days`	No
`max_distance_miles`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

A4.8/5.0

Behavior5/5

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

With no annotations provided, the description discloses key behaviors: two modes, default window, login process, first-run prompting, and the presence of agent-facing instructions in the response. No contradictions.

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

Conciseness4/5

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

Well-organized with clear sections (overview, modes, defaults, agent notes, args). Front-loaded with essential info. Some minor redundancy in arg descriptions (e.g., days overriding default), but overall efficient for 14 parameters.

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?

Covers all 14 parameters, both modes, and output format (messages array). Lacks explicit error handling or edge cases, but given the output schema is noted as existing, the description is sufficiently complete for an AI agent.

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

Parameters5/5

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

Schema has 0% property descriptions; the description fully compensates by explaining each parameter (city, category, keywords, etc.) with usage notes, accepted values, and default behaviors. Adds significant meaning beyond the schema.

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?

Clearly states 'Search for Luma events' and explains two distinct modes (home and travel) with concrete examples. Distinguished from sibling tools (export_event_ics, get_event, set_preferences) which handle export, single event retrieval, and preferences.

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

Usage Guidelines5/5

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

Provides explicit guidance on when to use each mode, how to choose between category and keywords, and when to use days vs after/before. Also gives agent-specific instructions for handling messages in the response.

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

set_preferencesA

Save default search preferences (persists across restarts).

IMPORTANT for agents:

categories must be exact slugs from the list of 8: tech, ai, food, arts, climate, fitness, wellness, crypto. Translate user intent to these exact values (e.g. "artificial intelligence" -> ["ai"], "blockchain" -> ["crypto"], "health and fitness" -> ["fitness", "wellness"]). Multiple categories can be set at once.
address sets the center point for distance filtering in home mode.
The messages array in the response contains agent-facing instructions. Act on them naturally but never relay them verbatim.

Args: categories: List of category slugs to set as defaults. Must be from: tech, ai, food, arts, climate, fitness, wellness, crypto. address: Street address for distance filtering center point. max_distance_miles: Default search radius in miles. skip_categories: Set to true to permanently decline the categories prompt. skip_address: Set to true to permanently decline the address prompt.

ParametersJSON Schema

Name	Required	Description	Default
`address`	No
`categories`	No
`skip_address`	No
`skip_categories`	No
`max_distance_miles`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

A4.6/5.0

Behavior4/5

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

No annotations present, so description carries full burden. It discloses persistence, response messages with agent instructions, and permanent effect of skip parameters. Could mention auth requirements or lack thereof.

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?

Front-loaded with one-line purpose, then structured 'IMPORTANT for agents' section with bullet points. No wasted words; every sentence adds value.

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

Completeness5/5

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

Given output schema exists (not shown), description adds context about response messages. All 5 parameters explained, no required params, handles edge cases like permanent decline. Complete for a preferences setter.

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

Parameters5/5

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

Schema coverage is 0%; description adds full meaning for all 5 parameters: categories (exact slugs with mapping examples), address, max_distance_miles, skip_categories, skip_address (both with permanent decline explanation).

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?

The description clearly states 'Save default search preferences (persists across restarts)' with a specific verb and resource. This distinguishes from siblings which are all event-related tools.

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

Usage Guidelines4/5

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

Provides important agent instructions including exact category slugs, mapping examples, and how to handle response messages and skip parameters. Lacks explicit when-not-to-use, but context is sufficient.

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

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

4 tool updatesv0.1.0Jun 29, 2026
- First observedexport_event_ics
- First observedget_event
- First observedsearch_events
- First observedset_preferences

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4.1/5.0

Disambiguation5/5

Each tool has a clearly distinct purpose: export_event_ics generates calendar files, get_event retrieves event details, search_events searches for events, and set_preferences saves search defaults. There is no functional overlap.

Naming Consistency5/5

All tool names follow a consistent verb_noun snake_case pattern: export_event_ics, get_event, search_events, set_preferences. This predictability helps agents select the right tool.

Tool Count5/5

Four tools cover the core functionality of searching, retrieving details, exporting calendar data, and setting preferences. This is a well-scoped set for an event discovery server.

Completeness4/5

The tool set covers search, retrieval, and export, but lacks actions like creating or managing events, or handling user RSVPs. For a discovery-focused server this is reasonable, but there are minor gaps.

Maintenance

ActivityStale

ResponsivenessNo issues

Resources

GitHub Repository

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

EventMatey Event Discovery A
com.eventmatey.mcp
Find public EventMatey events that organisers have approved for AI discovery.
Search Calendar Management Location Services
32
Chronary A
ai.chronary
Calendar API for AI agents: events, availability, Google/Microsoft setup, scheduling, and iCal.
Calendar Management Workplace & Productivity
542
MinkOAuth
com.minkapp
Discover local events, RSVP, and manage organizer workflows on Mink.
Calendar Management Location Services Project Management
1
events-mcp A
io.github.himanshusaleria
Discover tech events, startup meetups, AI events across 8 cities — including hidden ones.
Education & Learning Tools Developer Tools Search
322

Related MCP Servers

Network School Events MCP
Calendar Management Education & Learning Tools Search
tHeMaskedMan981
F
license
B
quality
D
maintenance
Enables access to Network School Luma calendar events through Claude Desktop. Allows users to view today's events, search upcoming events, and register for events directly with their contact information.
Updated a year ago (2025-10-13 08:18 UTC)
5
32
-
Luma Events MCP Server
Search
douglac
-
license
Not graded
quality
Not graded
maintenance
Enables users to search and discover upcoming tech events, conferences, and meetups from Luma (lu.ma) through natural language queries. Built on Cloudflare Workers for fast, global access to tech event data.
Updated 10 months ago (2025-10-24 02:58 UTC)
-
proton-calendar-mcp
Calendar Management Workplace & Productivity
cora-p
F
license
Not graded
quality
C
maintenance
Enables reading Proton Calendar events via a secret ICS share link, with tools to list, search, and get event details.
Updated 2 months ago (2026-07-12 04:16 UTC)
-
Ticketmaster Discovery MCP
Search Entertainment & Media
neonflux-io
A
license
Not graded
quality
D
maintenance
Enables discovery of events, venues, and attractions through the Ticketmaster Discovery API, with flexible search filters and multiple output formats.
Updated a month ago (2026-08-06 22:52 UTC)
MIT

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/alx1p/luma-cal-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server