Fair Fare
io.github.GoodTurnStudiov1.0.0Updated Oct 4, 2026
What a taxi, Uber or Lyft should cost, airport pickup rules, and overcharge checks.
Overview
A remote, read-only helper that estimates what a taxi, Uber or Lyft ride should cost, explains airport pickup rules, and flags possible overcharges.
- What it does
- Fair Fare is a remote MCP server from Good Turn Studio that answers everyday travel-fare questions. Based on its description, it covers what a taxi, Uber or Lyft should cost, airport pickup rules, and overcharge checks. It is part of a family of free, read-only helpers exposed over streamable HTTP, with no sign-in and no stored user data.
- When to use it
- Worth adding when you want an assistant to sanity-check a quoted ride price, look up airport pickup rules, or judge whether a fare seems too high. It is a read-only reference helper, not a booking or payment tool.
- Requirements
- A remote MCP endpoint at the provider's pages.dev host, reached over streamable HTTP. No sign-in, API key, environment variable or header is declared, and no local package or runtime is needed.
Installation
In SourceWeft
- Open Fair Fare in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Other MCP clients
Add this to your client's mcpServers config.
{
"mcpServers": {
"fairfare": {
"type": "http",
"url": "https://goodturn-mcp.pages.dev/fairfare/mcp"
}
}
}README
goodturn-mcp
Remote MCP servers for 25 free, read-only everyday helpers by Good Turn Studio: money, health, jobs, travel, shopping, halal checks, football and scripture reading. One Cloudflare Worker turns each product's public OpenAPI spec into an MCP server, so any assistant that speaks MCP (Claude, ChatGPT, Alexa+, Cursor, VS Code and others) can use them.
- One server per product:
https://goodturn-mcp.pages.dev/<slug>/mcp - All products in one:
https://goodturn-mcp.pages.dev/all/mcp(tool names start with the product slug) - Streamable HTTP, stateless JSON, MCP 2025-11-25 (and 2025-06-18, 2025-03-26), no sign-in
- Every tool is read-only, with a title and annotations (
readOnlyHint: true,destructiveHint: false,idempotentHint: true) - Nothing about the user is stored. Privacy: https://goodturn-mcp.pages.dev/privacy
Products
How it works
build.pyreads each product's liveopenapi.jsonand writesproducts.js: one tool per GET operation, named from itsoperationId, with inputs from its parameters. Descriptions are tidied into plain tool descriptions.worker.mjsis the MCP server:initialize,tools/listandtools/call, which calls the product's own API and returns its answer. Answers with asayfield carry a ready-made summary.servers.jsonlists every server for the official MCP Registry (asio.github.GoodTurnStudio/<slug>). The Publish to the MCP Registry workflow logs in with GitHub OIDC and runspublish.py;publish.ps1does the same from Windows.
Build and test
Deploy deploy/ as a Cloudflare Pages project in advanced mode (_worker.js).
Licence
MIT for this code. Each product's API, data and answers belong to that product and are served under its own terms, linked from its page at https://goodturn-mcp.pages.dev/<slug>.
Source: README.md at commit 8b4ce28
Tools
0Version history
1- v1.0.0LatestOct 4, 2026
