Borrowing it
Nothing to install: this file belongs to matheusgalvao1/travel-planner-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.
curl -O https://raw.githubusercontent.com/matheusgalvao1/travel-planner-mcp-server/main/CLAUDE.mdgit clone --depth 1 https://github.com/matheusgalvao1/travel-planner-mcp-serverWrote 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.
[](https://agentmods.dev/instructions/matheusgalvao1/travel-planner-mcp-server/claude-md)<a href="https://agentmods.dev/instructions/matheusgalvao1/travel-planner-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/matheusgalvao1/travel-planner-mcp-server/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/matheusgalvao1/travel-planner-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/matheusgalvao1/travel-planner-mcp-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.01142 | $0.01142 |
| Opus 5 | $0.00571 | $0.00571 |
| Sonnet 5 | $0.00228 | $0.00228 |
| Haiku 4.5 | $0.00114 | $0.00114 |
Grade A, and why
travel-planner-mcp-server CLAUDE.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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What this is
A deliberately thin stdio MCP server for an LLM travel-planning agent. It exposes exactly two tools — search_flights and search_hotels — backed by Google Flights and Google Hotels via SerpApi. The product principle: the agent may only recommend flights/hotels actually returned by these tools; everything else (destination facts, itinerary reasoning) is the LLM's own job via its built-in web search. Do not add tools for web search, booking, payments, cancellations, itineraries, ranking, or maps unless explicitly asked.
Commands
npm run build # tsc -> build/ (the MCP client runs build/index.js)
npm run dev # run from TS via tsx (live, needs SERPAPI_API_KEY)
npm run mock # TRAVEL_MCP_MOCK=1 + tsx — no API key needed
npm start # node build/index.js
npm test # all tests (node:test via tsx)
# Run a single test file:
node --import tsx --test test/normalizers.test.ts
# Run tests matching a name:
node --import tsx --test --test-name-pattern "milli" test/*.test.ts
There is no linter configured. After any source change, npm run build is required before the registered MCP server picks it up — clients launch the compiled build/index.js, not the TS source.
Architecture
Strict three-layer separation — keep logic in the right layer:
src/index.ts registers the two tools on McpServer, wires stdio transport
-> src/tools.ts orchestration: provider -> normalizer -> JSON tool response;
owns applyFlightConstraints() post-filtering and error shaping
-> src/providers/ ADAPTERS: build the SerpApi request, talk to the network
-> src/normalizers/ translate raw SerpApi JSON into FlightOption / HotelOption
- Adapters (
providers/):serpapi.tsis the shared GET client (oneSERPAPI_API_KEYpowers bothengine=google_flightsandengine=google_hotels).flights.ts/hotels.tsmap our input schema to SerpApi query params and own the supplier-specific quirks (cabin/stops/rating enum mappings, IATA codes, free-text hotelq). Each checksisMockMode()first. - Normalizers (
normalizers/): pure functions, no I/O. They must stay tolerant of missing/variant fields and always return the stableFlightOption/HotelOptionshape (full raw payload preserved underraw). This is the contract the LLM reasons over — keep normalization minimal, don't invent a canonical ontology. - Cross-cutting:
config.ts(env access,isMockMode, defaults),errors.ts(singleTravelMcpErrorwith acode),http.ts(the onlyfetchcall site — owns timeouts and turns HTTP/transport failures intoTravelMcpError).tools.tscatches errors and returns a structured{ status: "failed", error: { code, message, http_status } }response withisError: truerather than throwing.
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.
- 10d ago First seen · 53 lines · 1,142 tokens per session scan A e323ffc6be05
travel-planner-mcp-server CLAUDE.md is an instructions file published in the GitHub repository matheusgalvao1/travel-planner-mcp-server (0 stars, last pushed 2mo ago), licensed MIT. It adds 1,142 tokens to every session, about $0.0057 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.
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.
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.
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).
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.
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.
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).