Airtreks Mcp

Created By

SEKeener2 months ago

Overview

AirTreks MCP Server

Complex flight routing intelligence for AI agents. Validates multi-city itineraries, suggests proven RTW routing templates, identifies dead legs, and recommends fare products.

Tools

Tool	Description
`route_validate`	Validate a multi-city routing — checks alliance rules, dead legs, poison carriers, bookability
`route_suggest`	Get 3 suggested routings by region, direction, and alliance
`hub_check`	Best connection between two airports — dead leg detection + hub fixes
`fare_product_match`	Recommend fare type: RTW, Circle Pacific/Atlantic, Open Jaw, or Custom

Run

# Development
npm run dev

# Production
npm run build && npm start

Add to Claude Code

Already configured in ~/.claude.json. Restart Claude Code to pick up.

Add to any MCP client

{
  "mcpServers": {
    "airtreks": {
      "type": "stdio",
      "command": "node",
      "args": ["/Users/supernova/projects/airtreks-mcp/dist/index.js"]
    }
  }
}

Data Sources

Alliance members and poison carriers from AirTreks routing intelligence (April 2026)
Dead legs and hub rules from RTW pricing analysis (53 dead legs, 1,400+ failures)
20 proven routing templates from top AirTreks bookings
Fare product rules from consultant knowledge

Architecture

src/
  index.ts          — MCP server entry point (stdio transport)
  data/
    alliances.ts    — Star Alliance (26) + oneworld (14) carrier data
    hubs.ts         — Dead legs, hub rules, known connections
    fare-products.ts — RTW, CP, CA, OJ, Custom fare product definitions
    routes.ts       — 20 routing templates
  tools/
    route-validate.ts
    route-suggest.ts
    hub-check.ts
    fare-product-match.ts

Try in Playground

Server Config

{
  "mcpServers": {
    "airtreks": {
      "url": "https://mcp.airtreks.com/mcp"
    }
  }
}

Project Info

Created At

2 months ago

Updated At

2 months ago

Author Name

SEKeener

Star

Language

License

Recommend Servers

View All

EdgeOne Pages MCP

@TencentEdgeOne

An MCP service designed for deploying HTML content to EdgeOne Pages and obtaining an accessible public URL.

TypeScript

a year ago

Georgia Payments Mcp

@junter1989k-ai

10 days ago

Australia Payments Mcp

10 days ago

10 days ago

Playwright MCP server

TypeScript

a year ago

Framelink Figma MCP Server

@GLips

MCP server to provide Figma layout information to AI coding agents like Cursor

TypeScript

a year ago

10 days ago

MCP Advisor & Installation - Use the right MCP server for your needs

TypeScript

a year ago

Songcheck Ai Music Detector

@afghanfansmedia-ai

Is this song AI or human? SongCheck detects AI-generated music (Suno, Udio, and more) and media from any AI agent. Point it at an audio file, an image/video, or a whole music folder and it returns a verdict (LIKELY AI-GENERATED / UNCERTAIN / LIKELY HUMAN), an AI-probability score, confidence, and provenance signals (Content Credentials / SynthID watermark, generator hints). Tools: detect_ai_music, detect_ai_media, scan_catalog (audit an entire catalog), and songcheck_health. Free tier is 5 checks/day; a paid key unlocks unlimited catalog scans. Powered by SongCheck (Khaled Media), a self-hosted v9 ensemble detector.

5 days ago

Switzerland Payments Mcp

@junter1989k-ai

10 days ago

Redis

@modelcontextprotocol

A Model Context Protocol server that provides access to Redis databases. This server enables LLMs to interact with Redis key-value stores through a set of standardized tools.

a year ago

10 days ago

10 days ago

10 days ago

10 days ago

10 days ago

10 days ago

10 days ago

One API for Search, Crawling, and Sitemaps

a year ago

ContextBridge

@tijuthomas5

ContextBridge (CB) is a local-first retrieval layer that sits between your codebase and your AI coding agent. Instead of pasting raw source files into context or letting the AI guess which files matter, CB indexes your codebase's real structure (via Graphify) and returns a compact, ranked result — owner file, related files, key symbols, and dependency chains — grounded in your actual code. A typical response is ~4–8 KB instead of the 100+ KB of raw source an AI would otherwise need to read to answer the same question — roughly a 96% cut in input tokens sent to your cloud AI, with zero hallucinated file paths or method names.

10 days ago

Frontrun

@jongall45

VC follow intelligence for AI agents. Track what top investors follow on X — detect new follows, convergence signals, and trending companies before they're announced.

5 days ago

Israel Payments Mcp

@junter1989k-ai

10 days ago

EverArt

@modelcontextprotocol

AI image generation using various models

a year ago

Aws Kb Retrieval Server

@modelcontextprotocol

An MCP server implementation for retrieving information from the AWS Knowledge Base using the Bedrock Agent Runtime.

a year ago