What is article-mcp CLAUDE.md?

Project instructions for Article MCP, a server that searches research papers across sources such as arXiv, PubMed, and Europe PMC. They describe its Python structure, search tools, and supporting services.

Use them when developing, reviewing, or debugging Article MCP's literature search, reference-management, quality-evaluation, configuration, or command-line code.

They give a coding agent the project context needed to change the right layer and follow the repository's design. This reduces accidental changes that conflict with how the server is organized.

How gqy20/article-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to gqy20/article-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/gqy20/article-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/gqy20/article-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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/gqy20/article-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/gqy20/article-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/gqy20/article-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/gqy20/article-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/gqy20/article-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/gqy20/article-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,254 This file is loaded in full into every session.

When invoked 2,254 The same file — it is already loaded in full.

Security scan A 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.

Model	Per session	Once invoked
Fable 5.1	$0.02254	$0.02254
Opus 5.5	$0.00902	$0.00902
Sonnet 5.5	$0.00451	$0.00451
Haiku 4.5	$0.00225	$0.00225

Measured 2mo ago against content hash 8c814c3a2b66, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

article-mcp CLAUDE.md scanned grade A 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 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.

Reads agent configuration directorieslowAgent snooping

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

**Configuration paths searched:** `~/.config/claude-desktop/config.json`, `~/.config/claude/config.json`, `~/.claude/config.json`

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

CLAUDE.md · 272 lines

How it starts

The opening of the file, as written. The whole thing — 272 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

Article MCP is a high-performance literature search server based on FastMCP framework that integrates multiple academic databases including Europe PMC, arXiv, PubMed, CrossRef, and OpenAlex. It provides comprehensive literature search, reference management, and quality evaluation tools for academic research.

Architecture

The project follows a standard Python src layout with layered architecture:

CLI Layer (cli.py): Main CLI entry point and MCP server creation via create_mcp_server()
Tool Layer (tools/core/): 6 core MCP tool registrations
Service Layer (services/): API integrations using dependency injection pattern
Middleware Layer (middleware/): Error handling, logging, and performance monitoring
Resource Layer (resources/): MCP resources for config and journal data
Compatibility Layer (main.py): Backward-compatible CLI entry point

The 5 Core Tools

All tools are registered in cli.py:create_mcp_server() with their respective service dependencies:

search_literature (tools/core/search_tools.py): Multi-source literature search
get_article_details (tools/core/article_tools.py): Article details by identifier
get_references (tools/core/reference_tools.py): Reference list retrieval
get_literature_relations (tools/core/relation_tools.py): Citation relationship analysis
get_journal_quality (tools/core/quality_tools.py): Journal quality assessment

Note: The test file test_six_tools.py is a legacy name - it tests these 5 core tools.

Service Injection Pattern

Services are created in create_mcp_server() and passed to tool registrars:

pubmed_service = create_pubmed_service(logger)
europe_pmc_service = create_europe_pmc_service(logger, pubmed_service)
# ... other services
register_search_tools(mcp, {"europe_pmc": europe_pmc_service, ...}, logger)

Read the full file on GitHub · 272 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.

2mo ago First seen · 272 lines · 2,254 tokens per session scan A 8c814c3a2b66

Subscribe to this mod's changes

article-mcp CLAUDE.md is an instructions file published in the GitHub repository gqy20/article-mcp (18 stars, last pushed 10mo ago), licensed MIT. It adds 2,254 tokens to every session, about $0.0090 per session on Opus 5.5. A static security scan graded it A with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

mcp

article-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
article-mcp CLAUDE.mdgqy20/article-mcp	Instructions file	18	10mo ago	MIT	A	2,254	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,685	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

article-mcp: Instructions file for Claude Code