nytimes-mcp: Instructions file for Claude Code

CLAUDE.md

nytimes-mcp CLAUDE.md is an instructions file for Claude Code from jeffmm/nytimes-mcp. It costs 1,292 tokens per session, scanned A, original, MIT.

A Claude Code repository guide for nytimes-mcp, a FastMCP server that provides access to New York Times APIs. It documents the server's five API tools, three reference resources, setup commands, and required NYT_API_KEY.

In plain words
What is it for?
Use it when developing, testing, or running nytimes-mcp, including configuring its New York Times API key and starting the MCP server.
Why use it?
It tells a coding agent how this repository is structured, installed, run, and tested instead of making it infer those details.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

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

Reuse

Borrowing it

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

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/jeffmm/nytimes-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/jeffmm/nytimes-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,292 This file is loaded in full into every session.
When invoked 1,292 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 $0.01292 $0.01292
Opus 5.5 $0.00517 $0.00517
Sonnet 5.5 $0.00258 $0.00258
Haiku 4.5 $0.00129 $0.00129

Measured 2mo ago against content hash 63ad8e662764, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

nytimes-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 2mo 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 · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 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

This is a FastMCP-based Model Context Protocol (MCP) server that provides access to the New York Times APIs. The server exposes 5 tools (one per NYT API endpoint) and 3 reference resources to MCP clients like Claude Desktop.

Development Commands

Environment Setup

# Install dependencies
uv sync

# Install as editable package
uv tool install .

Running the Server

# Development mode with MCP Inspector UI (interactive testing)
uv run fastmcp dev src/nytimes_mcp/server.py:mcp

# Production mode (for use with MCP clients)
uvx nytimes-mcp

# Alternative production mode
fastmcp run src/nytimes_mcp/server.py:mcp

Testing

# Run tests
uv run pytest

Environment Variables

Required environment variable: NYT_API_KEY

Architecture

Core Components

server.py - FastMCP server initialization and tool/resource registration

  • Initializes FastMCP instance with dependencies
  • Loads environment variables and validates NYT_API_KEY
  • Registers all MCP tools (5 total) and resources (3 total)
  • Each @mcp.tool() decorator wraps a corresponding function from tools.py
  • Each @mcp.resource() decorator wraps a corresponding function from resources.py
  • Main entry point handles cleanup of HTTP client on shutdown

tools.py - NYT API tool implementations

  • Defines type aliases for Literal types (NewsSource, SortOrder, PopularityType, PopularityPeriod)
  • Implements 5 primary tools: search_articles, get_news_wire, get_most_popular, get_archive, get_bestseller_list
  • Also provides helper functions: get_news_sections, get_bestseller_list_names, get_bestseller_lists_overview
  • Uses module-level singleton _nyt_client instance for HTTP connection pooling
  • Calls formatting utilities from utils.py for most endpoints (archive and bestseller return raw responses)
  • Provides cleanup_http_client() for proper resource cleanup

Read the full file on GitHub · 121 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. 2mo ago First seen · 121 lines · 1,292 tokens per session scan A 63ad8e662764

Subscribe to this mod's changes

nytimes-mcp CLAUDE.md is an instructions file published in the GitHub repository jeffmm/nytimes-mcp (1 stars, last pushed 10mo ago), licensed MIT. It adds 1,292 tokens to every session, about $0.0052 per session on Opus 5.5. 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.

Related

nytimes-mcp CLAUDE.md compared with instructions from other repositories

nytimes-mcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
nytimes-mcp CLAUDE.mdjeffmm/nytimes-mcpInstructions file110mo agoMITA1,292Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode