Flait Mcp

by corteslabsxyz

176 downloads
Not rated
GitHub

About

Is this flight price actually good? Deal oracle for AI agents — remote MCP + REST, backed by real price history on nomad corridors.

Details

Author
corteslabsxyz
Downloads
176
Categories
Other

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name Flait Mcp
    Command (node, npx, python, etc.)

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

Connect any MCP-compatible client (Claude Desktop, Claude Code, Hermes, OpenClaw) by adding the remote endpoint https://flait-agent-production.up.railway.app/mcp/. Once configured, you can invoke the tools find_deals, is_good_deal, pos_arbitrage, and `route

find_deals

Current best flight deals across nomad corridors, ranked by deal score (how far below the route's historical typical price).

is_good_deal

Judge whether a fare is a good deal for a route (IATA city codes, e.g. LAX, BKK). Returns verdict (excellent/good/typical/expensive) vs historical baseline.

pos_arbitrage

Point-of-sale arbitrage: routes where the same flight is cheaper when priced from another country's market. Returns savings in USD and %.

route_history

Daily minimum price history for a route (IATA city codes). Useful for buy/wait reasoning.

set_watch

Create a standing watch: Flait monitors the route 24/7 and emails the user when a fare drops under max_price_usd. Watching a route starts price collection on it, so ANY route works (give it a day to build data). With auto_book=true (requires given_name, family_name, born_on YYYY-MM-DD, phone_number in intl format), Flait books automatically when the price hits — the user always gets a warning email with a stop button first, spend is capped at max_price_usd, and one watch books at most one flight. Optional webhook_url (public https) receives lifecycle events: hit / booking_scheduled / booked / booking_failed / booking_stopped. Returns a status_key — keep it to poll watch_status.

watch_status

Status of a watch created with set_watch, including any booking attempts (with confirmation references). Pass the status_key set_watch returned.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "flait mcp": {
            "flait": {
                "type": "http",
                "url": "https://flait-agent-production.up.railway.app/mcp/"
            }
        }
    }
}

McpServers

{
    "flait": {
        "type": "http",
        "url": "https://flait-agent-production.up.railway.app/mcp/"
    }
}

Flait — flight deal intelligence for nomads & their agents

Live board: https://flait-agent-production.up.railway.app

Not another flight-search wrapper. Flait watches prices 24/7 on nomad corridors
(US/EU ↔ Latin America, US/EU ↔ Southeast Asia, and the hops between) and builds
the price history needed to answer the question every traveler — and every booking
agent — actually has: "is this price good for this route?"

GET /v1/score?origin=LAX&destination=BKK&price_usd=430
→ {"verdict":"good","pct_vs_typical":24.2,"typical_price_usd":567,"days_of_history":11,...}

History can't be scraped retroactively. Every day the collector runs, the oracle
gets harder to replicate — and more useful to you.

Connect your agent (30 seconds)

Remote MCP endpoint (Claude, Hermes, OpenClaw, anything MCP):

https://flait-agent-production.up.railway.app/mcp/

Claude Desktop / Claude Code:

{"mcpServers": {"flait": {"type": "http", "url": "https://flait-agent-production.up.railway.app/mcp/"}}}

Tools: find_deals · is_good_deal · pos_arbitrage · route_history

Per-platform setup (Hermes config, OpenClaw, example agent missions): see
AGENTS.md.

REST API

Full OpenAPI schema at /openapi.json — agent-readable by design.

| Endpoint | What it answers |
|---|---|
| GET /v1/score?origin=&destination=&price_usd= | Is this price good? (the oracle) |
| GET /v1/deals | Best current deals vs each route's typical price |
| GET /v1/history/{origin}/{destination} | Daily price history for a route |
| POST /v1/intents | Standing intent: watch a route, get emailed when it drops |

Humans welcome too

The deal board shows the same
intelligence visually — and you can set a standing watch ("BKK under $450")
and get an email the moment it hits.

Honest notes

- Verdicts are backed by our own collected history. Routes without ≥3 days of
data return "verdict": "unknown" — we don't guess.
- Prices come from cached airline-search data: great for deal intelligence,
always verify the live fare at booking.
- Free during beta. Be reasonable (≤1 req/sec). Building on Flait? Say hi —
high-volume keys and webhooks are coming.

---

Built in public by one human + Claude.

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.