Voyscout Price History

Historical flight and package price series for Czech origins.

CommunityOnlineNo sign-inGlobalFreeRead-only

What it can do

    What data it sees

    Do you need an account

    No: the server works without sign-in

    Historical flight and package price series for Czech origins. Honest stats, no verdicts. CC BY 4.0

    How to connect

    How to connect Voyscout Price History to Claude

    The server address to paste into Claude settings:

    https://voyscout.com/mcp

    1. Open Claude (claude.ai or the desktop app).
    2. Go to Settings → Connectors.
    3. Click Add custom connector.
    4. Paste the server address copied below into Remote MCP server URL and click Add.
    5. In a chat, click + → Connectors and switch the new connector on.

    Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

    Authorization

    After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

    How to connect Voyscout Price History to ChatGPT

    The server address to paste into ChatGPT settings:

    https://voyscout.com/mcp

    1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
    2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
    3. Open Settings → Connectors and click Create.
    4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
    5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
    6. In a new chat open + → Apps/Connectors and enable the connector.

    OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

    Authorization

    On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

    How to connect Voyscout Price History to Cursor

    The server address to paste into Cursor settings:

    https://voyscout.com/mcp

    Fastest: click Open in Cursor below and confirm the prompt.

    Manually:

    1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
    2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
    3. Save the file. The server appears in the MCP list; authorize it there if asked.

    Authorization

    If the service needs sign-in, an authorize button appears next to the server in the MCP list.

    Server tool list (5)

    Raw names from tools/list. Only developers need these.

    list_destinationsList every destination with a published price series, with how many days each rail was actually measured and the calendar span those measurements fall in. Historical observations only.
    price_historyPrice series for one destination: measured span, stats, a downsampled sample of points and any regime breaks. Historical observations only, never a live quote or a recommendation.
    current_vs_historyStats for one destination (min, median, and what share of the TRACKED DAYS were dearer than the last measurement) without the sample points. Percentages are over observed days, not over the calendar span. Descriptive only: it does not say whether to buy.
    find_opportunitiesRank every published rail by how its LAST measurement compares with its own tracked history, so a caller can ask 'where is it unusually cheap right now?' in one call instead of one call per destination. Percentages are over observed days, not the calendar span. `latest_cheaper_than_pct_of_days` is the same number as `cheaper_than_pct` under a name that states its direction (higher = cheaper than more of the tracked days). `stale_rails` says how many of the rails THIS call matched are past their own freshness boundary today, with the day it was judged (`as_of`), so the caller need not subtract dates per row. Descriptive only: it ranks observations and gives no verdict. Rails with too little history are returned under `excluded`, never dropped silently.
    compare_destinationsPut 2-8 named destinations side by side on the same snapshot, each with the stats current_vs_history reports (last measurement, median, min, share of TRACKED DAYS that were dearer). Numbers are for the WHOLE party, not per person, and percentages are over observed days rather than the calendar span. Rows come back in the order you asked for - it does not rank, and gives no verdict; use find_opportunities to rank. A destination that yields no row is returned under `excluded` with the reason.