transitland-mcp-server: Instructions file for Claude Code

AGENTS.md

transitland-mcp-server AGENTS.md is an instructions file for Claude Code, Codex, OpenCode from cyanheads/transitland-mcp-server. It costs 6,643 tokens per session, scanned A, a copy of obsidian-mcp-server AGENTS.md, Apache-2.0.

A project instruction file for a Transitland MCP server, which accesses a public registry of transit feeds, routes, stops, and departures.

In plain words
What is it for?
Use it when developing or maintaining the server, especially when working with Transitland IDs, geographic inputs, or its six tools and two resources.
Why use it?
It gives developers the server's required tools, data conventions, framework rules, and identifier formats in one place.

Instructions file for Claude CodeCodexOpenCode

Written for Claude Code and Codex and OpenCode: Claude Code plugin machinery, but also the file is AGENTS.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is cyanheads/transitland-mcp-server's own configuration. It tells Claude Code, Codex and OpenCode how to work on transitland-mcp-server itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything transitland-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to cyanheads/transitland-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/cyanheads/transitland-mcp-server/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/cyanheads/transitland-mcp-server

Made for: Claude Code, 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 transitland-mcp-server AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/cyanheads/transitland-mcp-server/agents-md.svg)](https://agentmods.dev/instructions/cyanheads/transitland-mcp-server/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/cyanheads/transitland-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/cyanheads/transitland-mcp-server/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 6,643 This file is loaded in full into every session.
When invoked 6,643 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 83% copy Near-identical to another mod 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 5.1 $0.06643 $0.06643
Opus 5 $0.03321 $0.03321
Sonnet 5 $0.01329 $0.01329
Haiku 4.5 $0.00664 $0.00664

Measured 7d ago against content hash f215afaa0edc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

transitland-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 7d 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.

Origin

This is a copy

83% identical to obsidian-mcp-server AGENTS.md — 342 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

AGENTS.md · 425 lines

How it starts

The opening of the file, as written. The whole thing — 425 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Developer Protocol

Server: transitland-mcp-server Version: 0.1.1 Framework: @cyanheads/mcp-ts-core ^0.12.3 Engines: Bun ≥1.3.0, Node ≥24.0.0 MCP SDK: @modelcontextprotocol/server ^2.0.0 Zod: ^4.4.3

Read the framework docs first: node_modules/@cyanheads/mcp-ts-core/CLAUDE.md contains the full API reference — builders, Context, error codes, exports, patterns. This file covers server-specific conventions only.


Overview

Wraps the Transitland v2 REST API — the open registry aggregating GTFS, GTFS-Realtime, and GBFS feeds from thousands of transit operators worldwide. Six tools and two resources over a single upstream: operators → feeds → routes → stops → departures.

  • Onestop IDs are the identifier spine. Every output surfaces the stable, public Onestop ID (o-/f-/r-/s-); every ID input also accepts an internal integer ID. Internal integers are instance-mutable and never the primary output identifier.
  • No geocoding. Transitland takes lat+lon+radius or a bbox, never a place name. Geography-capable tools name a geocoding pre-step (openstreetmap_geocode) in their descriptions and empty-result notices.
  • find_feeds is the standout — fetch URL + license terms + freshness for open transit data. License fields normalize to explicit yes/no/unknown and are never inferred from a blank registry field.
  • Real-time is structural. get_departures sets a per-departure realtime boolean and scheduleRelationship, plus a top-level realtimeAvailable, so a static timetable time is never mistaken for a live GTFS-RT prediction.
  • The meta.next pagination URL embeds the API key in plaintext — the service discards it and returns only the opaque integer after cursor, so the key never reaches tool output or logs.

Full design rationale, verified response shapes, and the decisions log live in docs/design.md.

Read the full file on GitHub · 425 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. 7d ago First seen · 425 lines · 6,643 tokens per session scan A f215afaa0edc

Subscribe to this mod's changes

transitland-mcp-server AGENTS.md is an instructions file published in the GitHub repository cyanheads/transitland-mcp-server (1 stars, last pushed 17d ago), licensed Apache-2.0. It adds 6,643 tokens to every session, about $0.0332 per session on Opus 5. A static security scan graded it A with 0 findings. It is 83% identical to obsidian-mcp-server AGENTS.md, differing in 342 lines, and is treated as a copy.

Related

Other instructions, from other repositories

next.js AGENTS.md

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

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 · 5,153 tokens

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

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

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 · 4,469 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