agentmods.dev

pexels-mcp-server: Instructions file for Claude Code

CLAUDE.md

pexels-mcp-server CLAUDE.md is an instructions file for Claude Code from hanoak/pexels-mcp-server. It costs 2,113 tokens per session, scanned A, original, MIT.

Project instructions for building an MCP server, a small program that lets AI tools use outside services, to expose the Pexels stock photo and video API.

In plain words
What is it for?
Use it when developing, testing, maintaining, or releasing this TypeScript and Node.js Pexels integration.
Why use it?
It gives the coding agent the project's fixed technology choices, folder rules, release process, and relevant SDK facts in one place.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

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

not rated 2repo 6d ago A scan 2,113 tokens original MIT
View source ↗ hanoak/pexels-mcp-server npmjs.com
Reuse

Borrowing it

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

README.md
[![agentmods](https://agentmods.dev/badge/instructions/hanoak/pexels-mcp-server/claude-md.svg)](https://agentmods.dev/instructions/hanoak/pexels-mcp-server/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/hanoak/pexels-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/hanoak/pexels-mcp-server/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,113 This file is loaded in full into every session.
When invoked 2,113 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 $0.02113 $0.02113
Opus 5 $0.01056 $0.01056
Sonnet 5 $0.00423 $0.00423
Haiku 4.5 $0.00211 $0.00211

Measured 8d ago against content hash 3ae79f524ff0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

pexels-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 8d 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 · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

pexels-mcp-server — project instructions

Production-ready, open-source npm package: an MCP (Model Context Protocol) server exposing the Pexels stock photo/video API as tools for LLM clients (Claude Desktop, Cursor, etc.), distributed via npx. Same quality bar as the author's prior @hanoak/unsplash-mcp-server (shipped v1→v3, 2026-07-22 to 2026-08-08): production-ready, legally sound, robust, easy to maintain, expected to get real community traction.

This file absorbs the one-time bootstrap doc that seeded this project (originally docs/PEXELS_MCP_BOOTSTRAP.md, transplanted from lessons learned building unsplash-mcp-server) as living, ongoing instructions rather than a disposable kickoff note. Project status and the forward-looking roadmap live at docs/ROADMAP.md.

Tech stack (settled, don't relitigate)

  • TypeScript + Node, ESM-only (MCP SDK is ESM), Node 20+ target.
  • Build: tsup (ESM output + .d.ts + shebang banner).
  • Validation: zod, lenient/passthrough on API responses — only validate fields actually consumed, so an unknown/renamed upstream field degrades gracefully instead of breaking a tool.
  • Transport: stdio.
  • SDK: @modelcontextprotocol/sdk (currently 1.30.0 — re-check current version periodically).
  • Distributed via npm, run via npx. Package: @hanoak/pexels-mcp-server (scoped — unscoped pexels-mcp-server is taken by an unrelated low-effort package), bin pexels-mcp-server.

Folder & architecture conventions

  • src/index.ts — bin entry + crash guards (SIGINT/SIGTERM/uncaughtException/unhandledRejection → stderr, never stdout).
  • src/server.ts — createServer(ctx) + runServer() composition root; holds SERVER_INSTRUCTIONS.
  • src/config.ts, src/version.ts — app-level, stay at root. version.ts reads from package.json via createRequire.
  • src/lib/ — generic infra: logger.ts (stderr-only leveled logger), redact.ts (secret redaction), node-guard.ts (Node-version guard).
  • src/pexels/ — domain layer: HTTP client, typed errors. Keep the client's get() generic; no typed endpoint methods (searchPhotos()) until real duplication appears. No post/put/delete — Pexels' API is entirely read-only, there is nothing to write.
  • src/schemas/ — response/wire schemas only, one file per resource type (photo.ts, video.ts, collection.ts, pagination.ts). Never put tool-input schemas here.
  • src/tools/ — MCP interface layer, one file per resource domain (photos.ts, videos.ts, collections.ts — no search.ts; Pexels splits search per media type at the endpoint level, so search lives inside each domain file). Each domain file holds that domain's input schemas + handlers + a register<Domain>Tools(server, ctx) registrar. src/tools/index.ts just calls each domain registrar. src/tools/result.ts holds one shared toToolError(err, redact). src/tools/format.ts holds shared compact-output mappers.
  • src/resources.ts, src/prompts.ts.
  • Tests mirror src/ 1:1 under test/.

Read the full file on GitHub · 70 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. 8d ago First seen · 70 lines · 2,113 tokens per session scan A 3ae79f524ff0

Subscribe to this mod's changes

pexels-mcp-server CLAUDE.md is an instructions file published in the GitHub repository hanoak/pexels-mcp-server (2 stars, last pushed 6d ago), licensed MIT. It adds 2,113 tokens to every session, about $0.0106 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.

LLMaiclaudeclaude-desktopmcpmcp-client
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