pixabay-mcp-server: Instructions file for Claude Code

CLAUDE.md

pixabay-mcp-server CLAUDE.md is an instructions file for Claude Code from hanoak/pixabay-mcp-server. It costs 3,594 tokens per session, scanned A, original, MIT.

Repository instructions for contributors to an MCP server, a program that lets AI tools access Pixabay images and videos. They describe the project, chosen technologies, folder structure, and coding standards.

In plain words
What is it for?
Keeping work aligned with the server’s TypeScript and Node.js setup, its validation and testing approach, and its rules for architecture, files, and code quality.
Why use it?
They give contributors one shared reference for how the project should be built and maintained, reducing inconsistent decisions and repeated questions.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is hanoak/pixabay-mcp-server's own configuration. It tells Claude Code how to work on pixabay-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 pixabay-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to hanoak/pixabay-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/hanoak/pixabay-mcp-server/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/hanoak/pixabay-mcp-server

Made for: Claude Code.

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 pixabay-mcp-server CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/hanoak/pixabay-mcp-server/claude-md/github.svg)](https://agentmods.dev/instructions/hanoak/pixabay-mcp-server/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/hanoak/pixabay-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/hanoak/pixabay-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.

agentmods 80×15 button for pixabay-mcp-server CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/hanoak/pixabay-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/hanoak/pixabay-mcp-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,594 This file is loaded in full into every session.
When invoked 3,594 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 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 5.1 $0.03594 $0.03594
Opus 5 $0.01797 $0.01797
Sonnet 5 $0.00719 $0.00719
Haiku 4.5 $0.00359 $0.00359

Measured 9d ago against content hash 694c5ca35258, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

pixabay-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 9d 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.

CLAUDE.md · 244 lines

How it starts

The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Guidance for Claude Code (and any contributor) working in this repository.

Project overview

@hanoak/pixabay-mcp-server is a production-ready Model Context Protocol (MCP) server for the Pixabay API — search and fetch royalty-free images and videos. Unofficial; not affiliated with or endorsed by Pixabay.

Quality bar: production-ready, legal/safe, community-maintained open-source npm package — not a prototype. Every decision should be defensible to a stranger reading the repo cold. This bar and most of the conventions below are carried over as-is from the author's prior unsplash-mcp-server project; deviations exist only where Pixabay's API genuinely differs (see "Where this differs from unsplash-mcp-server" at the end).

Tech stack (decided — do not relitigate without discussion)

  • Language/runtime: TypeScript, Node.js >=20, ESM-only.
  • MCP SDK: @modelcontextprotocol/sdk.
  • Validation: zod for both tool input schemas and Pixabay response schemas.
  • Transport: stdio only. No HTTP/SSE unless a concrete client need appears.
  • Build: tsup → single ESM bundle in dist/, #!/usr/bin/env node banner, .d.ts output.
  • Test runner: vitest (+ @vitest/coverage-v8).
  • Lint/format: ESLint flat config (typescript-eslint + eslint-config-prettier); Prettier (semi: false, singleQuote: true, printWidth: 100, trailingComma: all).
  • Release: Changesets → GitHub Actions → npm publish with provenance.
  • Commits: Conventional Commits, enforced by commitlint on a commit-msg hook.
  • npm package: @hanoak/pixabay-mcp-server, bin pixabay-mcp-server, mcp registry name io.github.hanoak/pixabay-mcp-server. First release is 1.0.0, not 0.1.0.

Pixabay API facts that drive design (verify against current docs before relying on exact numbers)

  • Auth: a single API key passed as the key query parameter — Pixabay has no header option. This is an upstream constraint, not a choice; see Security below for how it's compensated for.
  • No OAuth, no write endpoints. Pixabay's public API is search/read-only (images + videos). There is no user-authenticated tier-2 surface, so this project has no auth/ directory, no login/logout CLI, no credential store — a deliberate simplification versus unsplash-mcp-server.
  • Two resource domains only: images (GET https://pixabay.com/api/) and videos (GET https://pixabay.com/api/videos/). No users/collections/topics/stats endpoints.
  • Rate limit: ~100 requests / 60 seconds per key, surfaced via X-RateLimit-Limit / X-RateLimit-Remaining / X-RateLimit-Reset response headers; exceeding it returns 429 with an "API rate limit exceeded" message.
  • Mandatory 24-hour response caching. Unlike Unsplash (where caching was explicitly skipped), Pixabay's terms require callers to cache results for 24 hours to keep the API fast for everyone. This is a required architecture component here, not an optimization — see the cache layer below.
  • No permanent hotlinking. Pixabay's terms disallow using Pixabay CDN URLs as permanent image sources in an app; images displayed persistently should be downloaded to your own server first (videos may be embedded directly). An MCP server returns URLs to an LLM client for a single, ephemeral display in conversation — arguably not the "permanent hotlinking in an app" the term targets — but this is a genuine gray area, not a settled fact. Do not treat this as legally resolved; flag it in the ROADMAP for an explicit, documented policy decision before v1 ships, and revisit if Pixabay clarifies.
  • No systematic mass downloads. The API is "made for real human requests." Don't build a tool that auto-paginates through an entire result set or fires many requests per user turn.
  • Attribution is optional, not required — all content is under the Pixabay License (free for commercial and noncommercial use). Surface a courtesy credit ("by {user} via Pixabay" + a link to the pageURL) when convenient; never gate functionality on it, and never claim it's legally mandatory in docs/instructions text.
  • Content safety: the safesearch boolean param exists; default it to true on search/lookup tools, mirroring Unsplash's content_filter=high default.

Read the full file on GitHub · 244 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. 9d ago First seen · 244 lines · 3,594 tokens per session scan A 694c5ca35258

Subscribe to this mod's changes

pixabay-mcp-server CLAUDE.md is an instructions file published in the GitHub repository hanoak/pixabay-mcp-server (1 stars, last pushed 13d ago), licensed MIT. It adds 3,594 tokens to every session, about $0.0180 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

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

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens