agentmods.dev

seznam-webmaster-mcp: Instructions file for Claude Code

CLAUDE.md

seznam-webmaster-mcp CLAUDE.md is an instructions file for Claude Code from PavelUngr/seznam-webmaster-mcp. It costs 8,976 tokens per session, scanned B, original, MIT.

A project instruction file for a server that connects AI assistants to the Seznam Webmaster API, which provides website indexing data and URL reindexing. It documents the project's purpose, setup, release state, and development rules.

In plain words
What is it for?
Use it when developing or operating the MCP server, configuring client websites, checking indexing status, requesting reindexing, or validating releases.
Why use it?
It gives agents the context needed to work safely with multiple websites, API keys, builds, tests, and continuous integration.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is PavelUngr/seznam-webmaster-mcp's own configuration. It tells Claude Code how to work on seznam-webmaster-mcp 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 seznam-webmaster-mcp configures →

not rated 5repo changed 10d ago B scan 8,976 tokens original MIT
View source ↗ PavelUngr/seznam-webmaster-mcp
Reuse

Borrowing it

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

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 seznam-webmaster-mcp CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/pavelungr/seznam-webmaster-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/pavelungr/seznam-webmaster-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 8,976 This file is loaded in full into every session.
When invoked 8,976 The same file — it is already loaded in full.
Security scan B 1 finding. 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 $0.08976 $0.08976
Opus 5.5 $0.03590 $0.03590
Sonnet 5.5 $0.01795 $0.01795
Haiku 4.5 $0.00898 $0.00898

Measured 10d ago against content hash 76e3f4cae460, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

seznam-webmaster-mcp CLAUDE.md scanned grade B with 1 finding 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- **OpenAI Codex CLI** — `~/.codex/config.toml`, sekce `[mcp_servers.seznam-webmaster]`.
CLAUDE.md · 453 lines

How it starts

The opening of the file, as written. The whole thing — 453 lines — stays where its author put it; the contents beside it link to each section on GitHub.

seznam-webmaster-mcp

MCP server pro Seznam Webmaster API. Umožňuje AI asistentům pracovat s daty indexace, stavem webu a odesíláním URL k reindexaci přímo přes přirozený jazyk.

Projekt

Autor: Pavel Ungr ([email protected]) Repozitář: github.com/pavelungr/seznam-webmaster-mcp (veřejný) Licence: MIT Jazyk README: češtiny i angličtina (dva oddělené soubory: README.md a README.cs.md)

Cíl

Primárně nástroj pro vlastní potřebu — správa více klientských webů z jednoho místa. Zároveň veřejně dostupný pro SEO komunitu. Každý web má vlastní API klíč, konfigurace jde přes proměnné prostředí v konfiguračním souboru příslušného klienta.

Stav

Verze 0.1.5 — veřejně publikovaná (2026-10-07). První vydání přes Trusted Publishing se schvalováním: workflow verzi připravil, uživatel ji schválil na npmjs.com. Ověřeno, že npx @pavelungr/[email protected] nastartuje a hlásí verzi 0.1.5. Verze 0.1.4 existuje jen jako git tag (publikace 2026-06-12 selhala na vypršeném tokenu).

  • npm: @pavelungr/[email protected], tag latest, s provenance
  • GitHub: PavelUngr/seznam-webmaster-mcp, default branch main, tagy v0.1.0 až v0.1.5, GitHub Releases pro všechny kromě v0.1.4
  • CI: GitHub Actions workflow .github/workflows/ci.yml — build + smoke test + npm audit na Node 18/20/22 při každém push do main/dev a každém PR
  • Publikace: .github/workflows/publish.yml — při publikování GitHub Release připraví verzi na npm (npm stage publish, OIDC), živá je po schválení uživatelem. Postup viz Release workflow.
  • Instalace: npx @pavelungr/seznam-webmaster-mcp (standard MCP spouštění přes stdio)
  • Kompatibilní MCP klienti: Claude Desktop, Claude Code, OpenAI Codex CLI, Gemini CLI, Cursor

Hotovo v kódu:

  • 7 MCP nástrojů (status, documents, history, reindex, database-info, sites)
  • HTTP klient s retry na 429/502/503 (500/1000/2000 ms) a timeout 30 s přes AbortSignal
  • Parsing SEZNAM_WM_SITES + SEZNAM_WM_LANG s validací a varováním u duplicit
  • Robustní normalizeDomain — strip scheme, userinfo, path, port, trailing dot (zachovat www.)
  • Lokalizace cs (výchozí) + en, všechny chybové hlášky obsahují návod na řešení
  • Context-aware HTTP 403 (reindex vs. read)
  • Striktní validace vstupů: YYYY-MM-DD jako reálné datum v kalendáři, date_from ≤ date_to, URL musí mít http(s) scheme
  • Redakce API klíče přes redactApiKey ze všech kanálů, kudy by mohl odejít (readErrorDetail, fetch error message)
  • Sanitizace tool name v error hlášce — chrání před ANSI escape sequences a podobnými payloady
  • Lokalizovaná chybová hláška pro interní výjimky (stack jen do stderr, klient dostane generic)
  • TS modely rozšířené o pole přítomná v reálném API (ale ne ve Swagger spec): doc_count, content v history, webserver, ResponseHeader.content
  • Verze serveru se čte z package.json za běhu (žádný hardcoded string)
  • Build čistí dist/ před tsc (žádný shipping stale souborů)
  • README.md (sloučený CS+EN s anchor navigací), LICENSE (MIT), .gitignore, .npmignore
  • CHANGELOG.md (Keep a Changelog formát)
  • docs/architecture.md, docs/conventions.md, docs/gotchas.md
  • tests/smoke.mjs (34 assertů včetně formátu skillu, runable přes npm run smoke)
  • skills/seznam-webmaster/SKILL.md (skill pro AI agenty, zdarma, jen na GitHubu)
  • .github/workflows/ci.yml (build + smoke + audit na Node 18/20/22)
  • .github/workflows/publish.yml (Trusted Publishing, staged publishing)

Read the full file on GitHub · 453 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. 10d ago Changed · +21 lines · +960 tokens per session 76e3f4cae460
  2. 22d ago Changed · +41 lines · +2,053 tokens per session 44f1aaeace9d
  3. 2mo ago First seen · 391 lines · 5,963 tokens per session scan B 31a1ca6a47df

Subscribe to this mod's changes

seznam-webmaster-mcp CLAUDE.md is an instructions file published in the GitHub repository PavelUngr/seznam-webmaster-mcp (5 stars, last pushed 10d ago), licensed MIT. It adds 8,976 tokens to every session, about $0.0359 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

czechindexationmcpmcp-serverseoseznam
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 · 9,715 tokens

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 · 7,461 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, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 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 · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,750 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 · 4,261 tokens