mcpField
W
windsock

windsock

Remote
windsock.aiBusiness & Marketing0Updated 7w ago

About windsock

Windsock provides aircraft intelligence to agents and aviation professionals through a hosted service. Its tools cover valuations, registries, ownership costs, market data, diligence, logbooks, and watchlists; calls require a Windsock account.

Key features

  1. 01Aircraft valuations and comparables
  2. 02FAA and international registry lookups
  3. 03Ownership costs and fleet search
  4. 04Market metrics and forecasts
  5. 05Diligence reports and logbook search
  6. 06Aircraft watchlists

Use cases

  1. 01Assess an aircraft's value and ownership costs
  2. 02Look up registry and compliance information
  3. 03Prepare pre-buy diligence
  4. 04Track aircraft and search logbooks

MCP support

The hosted server at `https://windsock.ai/mcp` exposes 38 aircraft-intelligence tools. Clients connect over OAuth, while headless agents can authenticate with an account API key; npm and Python stdio bridges are also available.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://windsock.ai/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Packages
npmwindsock-mcp0.1.2
pypiwindsock-mcp0.1.1

Tools

Details

From the project README

Windsock MCP

Aircraft intelligence for AI agents. Windsock exposes 38 tools over the Model Context Protocol at https://windsock.ai/mcp: aircraft valuations, FAA registry lookups (US and 17 international registers), cost of ownership, comparable aircraft, fleet search, ADs and STCs, market metrics with forecasts, verified value reports, pre-buy diligence checklists, logbook search and a watchlist. Every call is tied to a Windsock account.

This repository holds the client packages and examples. The server itself is hosted; you never run it.

Docshttps://windsock.ai/mcp
npm bridge (stdio, OAuth or API key)npm/ → npx windsock-mcp
Python client + stdio bridgepython/ → pip install windsock-mcp
Examplesexamples/ — OpenAI Agents API, Anthropic MCP connector, LangChain, LlamaIndex, Claude Code, cURL
Listed onSmithery · official MCP Registry ai.windsock/windsock · ChatGPT app

One-click install

Install in VS Code Install in VS Code Insiders Install in Cursor

Claude Code:

claude mcp add --transport http windsock https://windsock.ai/mcp

or install the plugin (adds the server plus an aircraft pre-buy workflow skill; the repo root follows the Open Plugins layout, so Cursor and other Open Plugins clients can import it too):

/plugin marketplace add team-windsock/windsock-mcp
/plugin install windsock@windsock

Every client above signs you in with OAuth on first use. Headless agents use an API key instead — see the docs.

Quick start (any MCP client)

Remote server, no install:

https://windsock.ai/mcp

Chat assistants connect over OAuth. Agents send an account API key as Authorization: Bearer wsk_… (get one at Integrations → Agents & SDKs).

Plans

Free accounts get 20 of the 38 tools with a monthly call limit. Pro and Enterprise unlock reports, diligence, logbooks and tracking.

Support

[email protected] · https://windsock.ai/contact

MIT © Windsock

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.