mcp-server CLAUDE.md

mcp-server CLAUDE.md is an instructions file for coding agents from kontent-ai/mcp-server. It costs 2,362 tokens per session, scanned A, original, MIT.

A repository instruction file for a TypeScript server that lets AI models use Kontent.ai, a content-management platform, through natural-language requests. It documents installation, development, production startup, formatting, and debugging commands.

In plain words
What is it for?
Use it when installing dependencies, compiling TypeScript, running the server in development or production, checking formatting, or inspecting MCP communication.
Why use it?
It records the project's required commands and structure in one place. This helps an agent build and inspect the server without guessing how its standard-input or web-based connections work.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/kontent-ai/mcp-server/claude-md
Clone the repo
git clone --depth 1 https://github.com/kontent-ai/mcp-server

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 mcp-server CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kontent-ai/mcp-server/claude-md.svg)](https://agentmods.dev/instructions/kontent-ai/mcp-server/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/kontent-ai/mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/kontent-ai/mcp-server/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,362 This file is loaded in full into every session.
When invoked 2,362 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.02362 $0.02362
Opus 5 $0.01181 $0.01181
Sonnet 5 $0.00472 $0.00472
Haiku 4.5 $0.00236 $0.00236

Measured 5d ago against content hash a2e30c68ca19, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 5d 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 · 260 lines

How it starts

The opening of the file, as written. The whole thing — 260 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.

Essential Commands

Development Commands

# Install dependencies
npm ci

# Build the project (TypeScript compilation)
npm run build

# Start development server with auto-reload (no build required)
npm run dev:stdio   # For STDIO transport
npm run dev:shttp   # For Streamable HTTP transport

# Start production server (requires build)
npm run start:stdio  # For STDIO transport
npm run start:shttp  # For Streamable HTTP transport

Code Quality Commands

# Run formatter and linter check
npm run format

# Auto-fix formatting and linting issues
npm run format:fix

Debugging

# Debug with MCP inspector
npx @modelcontextprotocol/inspector -e KONTENT_API_KEY=<key> -e KONTENT_ENVIRONMENT_ID=<env-id> node build/bin.js

# Or inspect streamable HTTP server
npx @modelcontextprotocol/inspector

Architecture Overview

This is a Model Context Protocol (MCP) server for Kontent.ai that enables AI models to interact with Kontent.ai's APIs through natural language. The project follows a modular architecture:

Core Components

  1. Transport Layer (src/bin.ts): Single entry point supporting two transport protocols:

    • STDIO: Direct process communication (single-tenant only)
    • Streamable HTTP: Request-response based HTTP communication (supports multi-tenant)
  2. Server Core (src/server.ts): Central server instance that:

    • Registers all available tools
    • Manages MCP server lifecycle
    • Coordinates tool execution
  3. Tools Directory (src/tools/): Each tool is a separate module that:

    • Implements a specific Kontent.ai operation
    • Uses standardized error handling via errorHandler.ts
    • Returns responses using createMcpToolSuccessResponse
    • Must call get-patch-guide before any patch operation — the patch tool's own description must say "Always call get-patch-guide(entityType='…') first" with that exact "Always" emphasis. A weaker phrasing ("Call… first" without "Always") is regularly ignored by the agent in practice. All patch-* tool descriptions must use this exact phrasing — check for drift when adding or editing one.

Read the full file on GitHub · 260 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. 5d ago First seen · 260 lines · 2,362 tokens per session scan A a2e30c68ca19

Subscribe to this mod's changes

mcp-server CLAUDE.md is an instructions file published in the GitHub repository kontent-ai/mcp-server (9 stars, last pushed yesterday), licensed MIT. It adds 2,362 tokens to every session, about $0.0118 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.