tfl-mcp-server AGENTS.md

tfl-mcp-server AGENTS.md is an instructions file for Codex, OpenCode from oneill9/tfl-mcp-server. It costs 2,511 tokens per session, scanned A, original, MIT.

Project instructions for a server that connects AI assistants to Transport for London's live transport API. TfL is London's public transport authority, and an API is a service that provides data to software.

In plain words
What is it for?
Use them when developing or maintaining tools for London line status, stop arrivals, stop searches, journey planning, and service disruptions.
Why use it?
They give an agent the project purpose, available transport data, configuration details, and development workflow. This reduces guesswork when working on the server.

Instructions file for CodexOpenCode

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/oneill9/tfl-mcp-server/agents-md
Clone the repo
git clone --depth 1 https://github.com/oneill9/tfl-mcp-server

Made for: Codex, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for tfl-mcp-server AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/oneill9/tfl-mcp-server/agents-md.svg)](https://agentmods.dev/instructions/oneill9/tfl-mcp-server/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/oneill9/tfl-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/oneill9/tfl-mcp-server/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,511 This file is loaded in full into every session.
When invoked 2,511 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.02511 $0.02511
Opus 5 $0.01256 $0.01256
Sonnet 5 $0.00502 $0.00502
Haiku 4.5 $0.00251 $0.00251

Measured 4d ago against content hash 2eb0a4bb9a0b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tfl-mcp-server AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

AGENTS.md · 180 lines

How it starts

The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — TFL MCP Server

Project Purpose

This is an MCP (Model Context Protocol) server that wraps the TfL (Transport for London) Unified API, making live London transport data accessible to AI assistants such as Claude.

The server exposes TfL capabilities as MCP tools so an assistant can answer questions like:

  • "Is the Central line running normally?"
  • "When is the next bus from stop ABC?"
  • "How do I get from King's Cross to Canary Wharf right now?"
  • "Are there any disruptions on the Elizabeth line?"

TfL API

  • Base URL: https://api.tfl.gov.uk
  • Docs / Swagger: https://api.tfl.gov.uk/swagger/ui/index.html
  • Key registration: https://api-portal.tfl.gov.uk/
  • API key is passed as query param app_key=<key> or via TFL_APP_KEY env var
  • No key required for low-volume usage; key raises rate limits

Key TfL API areas (each maps to one or more MCP tools):

TfL API area Example endpoint Planned tool
Line status GET /Line/{ids}/Status line_status
Stop arrivals GET /StopPoint/{id}/Arrivals arrivals
Stop search GET /StopPoint/Search/{query} stop_search
Journey planner GET /Journey/JourneyResults/{from}/to/{to} journey
Disruptions GET /Line/Mode/{modes}/Disruption disruptions
Bike points GET /BikePoint bike_points

Architecture

The server has one Node.js implementation that exposes the same 6 tools over both supported transports.

  • Language: TypeScript (compiled to ESM)
  • Runtime: Node.js 22
  • Build: tsc via npm scripts
  • MCP SDK: @modelcontextprotocol/server 2.x and @modelcontextprotocol/node 2.x
  • MCP protocol: 2026-07-28 for modern stdio and HTTP; stdio also serves 2025-era desktop clients, while HTTP rejects legacy requests
  • MCP transports: stdio and stateless Streamable HTTP at /mcp
  • Entry point: node/src/index.tsnode/dist/index.js
  • HTTP entry point: node/src/http.ts, selected with --http
  • Tests: Vitest unit/acceptance tests, official MCP conformance, and live TfL contract tests
  • MCPB manifest: node/manifest.json
  • OCI image: Node.js 22; stdio by default and Streamable HTTP with --http

Read the full file on GitHub · 180 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 180 lines · 2,511 tokens per session scan A 2eb0a4bb9a0b

Subscribe to this mod's changes

tfl-mcp-server AGENTS.md is an instructions file published in the GitHub repository oneill9/tfl-mcp-server (1 stars, last pushed yesterday), licensed MIT. It adds 2,511 tokens to every session, about $0.0126 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens