Skip to content
RowHint logo

RowHint MCP server

Which MCP servers are RowHint's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-17

← Back to RowHint

Whose server it is
  • Registry namecom.rowhint/seat-intelligenceverified in the MCP registry

The registry name sits under rowhint.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-17
  • Stateanswerschecked 2026-10-17
  • Tools8
  • Server calls itselfRowHint Seat Intelligence
  • Server version1.0.0
  • Protocol version2025-06-18

On 2026-10-17 the server answered initialize and tools/list without a sign-in. First answer in 449 ms.

Should an agent connect itNot proven either way yet
  • Whether its tools do the product's job has not been judged yet.

Once connected

  • For "Compare individual seats on a specific aircraft before booking", the likely first call is rowhint_compare_seats.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 17, the first on 2026-10-19
  • INITE MCP score95 of 100answers 100 · definitions 83 · context 100 · connects 100
  • Answered100% of days17 of 17 daily checks
  • Median first answer200 ms
  • Space in an agent's context≈ 1,538 tokensthe definitions of all its tools (8), which an agent carries on every turn
  • Tool definitionsB · 83 of 100
  • Typed results0 of 8 toolsdeclared outputSchema: results come typed, read once
  • Not saying whether it only reads or can destroy: 8 of 8

What an agent can do with it

  • not sure · Check which seats on a flight have extra legroom
  • not sure · Avoid seats near the galley or with poor recline
  • can do · Compare individual seats on a specific aircraft before booking

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers8 tools · read 2026-10-17
  • rowhint_get_seat_score

    Get the quality score (1-10), color rating, and detailed notes for a specific airline seat. Returns comfort assessment, recline data, proximity warnings, and window alignment issues. Use when someone asks "Is seat 14A good on the Delta…

  • rowhint_get_best_seats

    Find the highest-rated seats on a specific aircraft configuration. Filter by cabin class (economy, premium, business, first) and number of results. Use when someone asks "What's the best seat on the United 777?" or "Best economy seat on…

  • rowhint_compare_seats

    Compare two specific seats on the same aircraft side by side. Returns scores, notes, dimensions, and a recommendation for which seat is better. Use when someone asks "Should I pick 14A or 22F on the Southwest 737 MAX 8?" or is deciding…

  • rowhint_get_config_overview

    Get a summary of an aircraft configuration including total seats, cabin layout, best and worst seats per cabin, and facility locations (galleys, lavatories). Use when someone asks "Tell me about the American Airlines 787-9" or wants a…

  • rowhint_pick_seat

    Get the best seat recommendations for a specific flight. Takes a flight number (e.g., "UA1234", "DL567") and optionally cabin class, seat position preference (window/aisle), and priority (legroom/recline/quiet). Returns top picks with…

  • rowhint_help_me_pick

    Conversational seat picker. Asks the user a few structured questions (flight, route length, what they care most about, cabin class), then returns the top 3 seat recommendations with notes. Use this when someone wants help choosing but…

  • rowhint_seat_roast

    Roasts a specific airline seat. Returns a one-paragraph, voice-y takedown of the seat based on its quality score, proximity issues, recline/legroom data, and any notes. Use when someone asks 'how bad is seat 31B on the United 787-9?'…

  • rowhint_get_windowless_seats

    List all window-position seats that have no actual window on a specific aircraft. These are seats labeled as window seats in airline booking systems but where the fuselage structure blocks the view. Use when someone asks about window…

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "seat-intelligence": {
      "type": "http",
      "url": "https://mcp.rowhint.com/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http rowhint https://mcp.rowhint.com/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://mcp.rowhint.com/mcp as a custom connector in the settings.

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.