Cyan Eclipse Marquee MCP
OfficialProvides read-only event and listing discovery over a local stub feed shaped like SeatGeek Platform responses, including normalized listing details and all-in pricing for price-watch evaluation.
Provides read-only event and listing discovery over a local stub feed shaped like Ticketmaster Discovery responses, normalizing event, section/row/seat, fee, and all-in price data for search and price-watch evaluation.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Eclipse Marquee MCP
Powered by Cyan Eclipse Technologies — https://cetech.ai
Eclipse Marquee — the live-events agent: it finds the event, watches the price, buys only inside your mandate, and keeps the receipt for every ticket. It does not scalp, bypass, or bet.
Why this exists
Event discovery is fragmented across marketplaces, prices move constantly, and fees often surface only after a headline price has done its work. Marquee F0 fixes the read-only half of that problem: one normalized event model that preserves section, row, and seat truth; fee components kept separate from face value; and a Price Watcher that compares only the all-in price against an owner's ceiling.
Related MCP server: OpenAgenda MCP
Status — honest labels
v0.1.0, phase F0 only (discovery + Price Watcher). Read-only. Local stdio transport, Python stdlib only. Data comes from shipped fixtures and a local stub feed shaped like Ticketmaster Discovery and SeatGeek Platform responses. No live marketplace call exists in the code, no API keys are used, and no certification is claimed — bench pending.
Explicitly NOT in v0.1, by spec and by design: purchase or checkout tools, transfer tools, resale tools, group coordination, entry credential handling, organizer-side tools, odds, and betting. Buying is phase F1 and stays behind owner/API-key gates.
Tools (6)
Tool | What it does |
| Search the local stub feed by artist, team, keyword, city, category, and date range. |
| Read one listing, or an event and all its listings. Section, row, and seats remain nested and intact. Face value, each fee, total fees, and all-in price remain separate fields. |
| Create a Price Watcher: event, section constraints, per-ticket all-in ceiling, quantity, and expiry. A successor watch may only tighten the prior watch. |
| List watches and alert records, optionally by event. |
| Evaluate watches against the latest fixture price snapshot at or before |
| List the append-only receipt chain and verify it. |
Fee truth + the tightening rule
A watcher's ceiling is per ticket, all-in: face value plus service, facility, and processing fees. A listing below the ceiling before fees but above it after fees does not alert.
A successor watch created with supersedes_watch_id may only tighten: lower ceiling, narrower section set, no later expiry, same event and quantity. Any loosening is rejected as a Marquee tightening rule violation.
Fixtures + stub feed
fixtures/ticketmaster_feed.json carries a concert and a theater production in a Ticketmaster Discovery-shaped envelope. fixtures/seatgeek_feed.json carries an NBA game in a SeatGeek Platform-shaped envelope. Every listing ships a four-point price-snapshot series. The concert's Section 112, Row F series moves all-in from 151 to 146 to 141 and finally to 136, creating one dip under a 140 ceiling. Its Section 108 listing is the fee trap: the face value is under 140 while the all-in price is not.
Receipts + watch exhaust
Watch creation, tightening, evaluations, and alerts append hash-chained receipts. Evaluations also store first-party price-history points with per-source provenance: source, feed file, source listing ID, and snapshot index. The shipped data is explicitly a local stub; no retention or live-source claim is made.
Run it
python3 server.py # MCP over stdio, stdlib only, no dependencies
python3 smoke.py # end-to-end smoke over real stdio (temp state)
python3 -m unittest discover tests
python3 make_icon.py # regenerate icon-512.pngState persists in data/state.json beside the server (override with ECLIPSE_MARQUEE_STATE). data/ is gitignored.
Roadmap (per spec)
F1 — buy-under-mandate through official checkout rails, only after owner/API-key gates and first-party use on CETech's own event workflow.
F2 — group logistics, chain-of-custody receipts, official transfers, entry-day readiness.
O — organizer side only under signed partner terms.
License / attribution
A Cyan Eclipse Technologies product. The "Powered by Cyan Eclipse Technologies" attribution travels with it.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Live ticket prices, listings and seat maps for AI agents.
Live-event ticket exchange for agents: quote, buy, make offers, bid, and sell, with escrow.
Find live events, ticket price trends and each seller's tickets. Some links are affiliate links.
Travel & commerce intelligence for AI agents: search, book & price-track hotels, events, retail.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables agents to discover events, purchase tickets, and set reminders through MCP tools.MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to search event calendars by keyword and list upcoming or date-filtered events from a chosen calendar, returning titles, dates, venues, coordinates, and keywords.91 npmMIT

SyncSoofficial
AlicenseNot gradedqualityBmaintenanceEnables agents to search and retrieve live local happenings in New York City — music, theater, comedy, film, art, sports, festivals, markets, food and drink, classes, tours and nightlife — each with dates, times, prices, booking links and images. Two tools, search_directions and get_details, let assistants answer time-sensitive questions about what is happening nearby and return bookable results.2MIT- AlicenseNot gradedqualityCmaintenanceEnables AI agents to discover upcoming events in a given city, optionally filtered by category slug or free-text keyword. It also retrieves full detail for a single event, including description, timing, venue, organizer, and ticket price range and availability.75 npmMIT