zendesk-hc-mcp: Instructions file for Claude Code

CLAUDE.md

zendesk-hc-mcp CLAUDE.md is an instructions file for Claude Code from gschaer/zendesk-hc-mcp. It costs 579 tokens per session, scanned A, original, MIT.

Project instructions for a read-only MCP server that accesses public Zendesk Help Center content without authentication.

In plain words
What is it for?
Working on the Zendesk Help Center MCP server, including its HTTP client, caching, pagination, content conversion, and tool tests.
Why use it?
They explain how the server is structured, developed, and tested, helping an agent make compatible changes.

Instructions file for Claude Code

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

This is gschaer/zendesk-hc-mcp's own configuration. It tells Claude Code how to work on zendesk-hc-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 zendesk-hc-mcp configures →

Reuse

Borrowing it

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

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/gschaer/zendesk-hc-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/gschaer/zendesk-hc-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 579 This file is loaded in full into every session.
When invoked 579 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 $0.00579 $0.00579
Opus 5 $0.00290 $0.00290
Sonnet 5 $0.00116 $0.00116
Haiku 4.5 $0.00058 $0.00058

Measured 9d ago against content hash 156ab4e8e7fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

zendesk-hc-mcp 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 · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Zendesk HC MCP Server

Project Overview

MCP server that provides read-only access to public Zendesk Help Center APIs. No authentication required — works with any public HC.

Development

  • Run tests: uv run pytest -v
  • Run server: uv run zendesk-hc-mcp (stdio transport, will hang waiting for input — that's expected)
  • Add dependency: uv add <package> (dev: uv add --dev <package>)

Architecture

src/zendesk_hc_mcp/
  __init__.py    — package root, exports main()
  helpers.py     — pure functions: html_to_md, pluralize, locale_path, etc.
  client.py      — ZendeskHCClient (HTTP + hishel caching + pagination)
  tools.py       — 9 MCP tool functions + FastMCP instance + global hc_client
  server.py      — entry point: imports tools, calls mcp.run()

tests/
  test_helpers.py — pure function tests (no mocking needed)
  test_client.py  — HTTP client tests (respx-mocked)
  test_tools.py   — MCP tool output tests (respx-mocked, patches hc_client)

doc/oas.yaml     — Zendesk Help Center OpenAPI spec (reference only)

Key design decisions

  • helpers.py has zero I/O — all pure functions, independently testable
  • client.py has no MCP dependency — just httpx + hishel
  • tools.py owns the FastMCP instance and the global hc_client
  • server.py is a thin entry point that imports tools (which registers them) and runs
  • All tools return error strings (not exceptions) so the agent always gets a usable message

Caching

Uses hishel FilterPolicy (SQLite-backed) with 7-day TTL. Cache at .cache/ (project-local, gitignored). All tools accept force_refresh=True which uses a separate non-cached httpx client.

Pagination

  • Articles: cursor-based (page[size], meta.after_cursor, meta.has_more)
  • Everything else: offset-based (page, per_page, page_count)

Testing

All development follows TDD. Tests use respx to mock httpx requests — no network calls.

Running tests

# All tests
uv run pytest -v

# Just helpers
uv run pytest tests/test_helpers.py -v

# Just client
uv run pytest tests/test_client.py -v

# Just tools
uv run pytest tests/test_tools.py -v

# With coverage
uv run pytest --cov=zendesk_hc_mcp --cov-report=term-missing -v

Read the full file on GitHub · 71 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 · 71 lines · 579 tokens per session scan A 156ab4e8e7fb

Subscribe to this mod's changes

zendesk-hc-mcp CLAUDE.md is an instructions file published in the GitHub repository gschaer/zendesk-hc-mcp (0 stars, last pushed 5mo ago), licensed MIT. It adds 579 tokens to every session, about $0.0029 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 2026-09-01.

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

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

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