Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/darekrossman/contentstack-mcp/claude-mdgit clone --depth 1 https://github.com/darekrossman/contentstack-mcpWrote 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/darekrossman/contentstack-mcp/claude-md)<a href="https://agentmods.dev/instructions/darekrossman/contentstack-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/darekrossman/contentstack-mcp/claude-md.svg" alt="Measured on agentmods" 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 | $0.00737 | $0.00737 |
| Opus 5 | $0.00368 | $0.00368 |
| Sonnet 5 | $0.00147 | $0.00147 |
| Haiku 4.5 | $0.00074 | $0.00074 |
Grade A, and why
contentstack-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 3d 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 — 112 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.
Project Overview
Contentstack MCP Server is a Model Context Protocol server that integrates with Contentstack's Content Management API. It enables AI assistants like Claude to interact with Contentstack CMS through a standardized protocol.
Development Commands
# Install dependencies
npm install
# Development mode
npm run dev
# Build the project
npm run build
# Clean build artifacts
npm run clean
# Start the server (after building)
npm start
# Code Quality
npm run lint # Check and fix code with Biome
npm run typecheck # Type check with TypeScript
Architecture
The project is a TypeScript application structured around the Model Context Protocol (MCP):
-
Server Definition (
src/index.ts): Creates and configures the MCP server with resources, tools, and prompts. -
Type Definitions (
src/types.ts): TypeScript interfaces for Contentstack API requests and responses. -
Main Components:
- Resources: URI-based endpoints to fetch content from Contentstack
- Tools: Functions to perform operations on Contentstack content
- Prompts: Guided workflows for content operations
-
Configuration:
- The server requires Contentstack API credentials (API Key and Management Token)
- Credentials are loaded from environment variables
- Optional branch specification for multi-branch setups
-
Build System:
- Uses esbuild (
lib/build.js) to bundle the application - Outputs to
dist/bundle.js
- Uses esbuild (
Environment Variables and CLI Options
Required environment variables:
CONTENTSTACK_API_KEY: Your Contentstack stack API keyCONTENTSTACK_MANAGEMENT_TOKEN: Management token with necessary permissions
Optional environment variables:
CONTENTSTACK_BRANCH: Branch name (if using branches)
Command Line Usage
The server can be run directly via CLI with the following options:
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.
- 3d ago First seen · 112 lines · 737 tokens per session scan A d63231125391
contentstack-mcp CLAUDE.md is an instructions file published in the GitHub repository darekrossman/contentstack-mcp (2 stars, last pushed 1y ago), licensed MIT. It adds 737 tokens to every session, about $0.0037 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
payload CLAUDE.md
Claude Code instructions for payloadcms/payload, covering claude.md, project structure, key directories, architecture notes and quick start.
payload AGENTS.md
AGENTS.md instructions for payloadcms/payload, a project described as: Payload is the open-source, fullstack Next.js framework, giving you instant backend superpowers. Get a full TypeScript backend and admin panel instantly. Use Payload as a headless CMS or for building powerful applications.
reearth-cms-mcp AGENTS.md
Instructions for reearth/reearth-cms-mcp, covering re:earth cms mcp server, project structure, how to build, requirements and build.
npi-providers-mcp-server AGENTS.md
AGENTS.md instructions for cyanheads/npi-providers-mcp-server, covering developer protocol, core rules, patterns, tool and resource.
npi-providers-mcp-server CLAUDE.md
Claude Code instructions for cyanheads/npi-providers-mcp-server, covering developer protocol, core rules, patterns, tool and resource.
reearth-cms-mcp CLAUDE.md
Instructions for reearth/reearth-cms-mcp, a project described as: MCP server for Re:Earth CMS.