doi-mcp: Instructions file for Claude Code

CLAUDE.md

doi-mcp CLAUDE.md is an instructions file for Claude Code from tfscharff/doi-mcp. It costs 1,922 tokens per session, scanned A, original, MIT.

Repository instructions for an MCP server that checks academic citations against nine scholarly databases. MCP is a standard way for AI tools to use external functions.

In plain words
What is it for?
Use it when developing, testing, or changing the citation-checking server, including its database adapters, validation, caching, and citation-search tools.
Why use it?
It helps prevent made-up or incorrect paper references by checking citations against trusted sources.

Instructions file for Claude Code

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

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

Reuse

Borrowing it

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

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/tfscharff/doi-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/tfscharff/doi-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,922 This file is loaded in full into every session.
When invoked 1,922 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 $0.01922 $0.01922
Opus 5.5 $0.00769 $0.00769
Sonnet 5.5 $0.00384 $0.00384
Haiku 4.5 $0.00192 $0.00192

Measured 9d ago against content hash 6ad6d2ff80a8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

doi-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 · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 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

MCP server (stdio) that prevents citation hallucination by verifying academic citations against 8 databases: CrossRef, OpenAlex, PubMed, zbMATH, ERIC, HAL, INSPIRE-HEP, Semantic Scholar. ESM TypeScript, Zod 4 for tool input schemas. Runtime supports Node >=18, but development needs Node >=22.12 (vitest 5).

Commands

npm install
npm run build                          # tsc -> dist/
npm run dev                            # tsc --watch
npm test                               # vitest run (all tests)
npx vitest run tests/unit/scoring.test.ts   # single file
npx vitest run -t "crossref adapter"        # by test name
npm run test:coverage                  # v8 coverage -> coverage/ (gitignored)

No linter is configured.

Releasing (every change is a release)

Don't git commit / git tag by hand. Finish the change, then:

npm run ship -- "fix(scope): short imperative description" --body-file notes.md
npm run ship -- "feat: x" --dry-run   # preview the version bump and changelog entry

scripts/ship.mjs (ported from the zoteamo repo) checks the Conventional Commit header, runs npm test, rebuilds dist/, bumps package.json (feat → minor; fix/docs/chore/etc. → patch; ! or BREAKING CHANGE: → major), prepends CHANGELOG.md, commits, tags vX.Y.Z, pushes, and runs gh release create. It refuses to run off main or with a clean tree; --as X.Y.Z forces a version. Pure helpers live in scripts/lib/release.mjs (tested in tests/unit/release.test.ts).

Treat any change to what gets verified or returned, or to tool inputs/outputs, as breaking (!).

dist/ is committed

dist/ is checked in so npx doi-mcp works without a build step. After changing src/, run npm run build and commit the updated dist/ too. tsc never deletes outputs, so when removing or renaming a source file, delete its dist/ counterparts by hand.

Read the full file on GitHub · 92 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 Changed · -28 lines · +1,092 tokens per session 6ad6d2ff80a8
  2. 2mo ago First seen · 120 lines · 830 tokens per session scan A 3b408a50c405

Subscribe to this mod's changes

doi-mcp CLAUDE.md is an instructions file published in the GitHub repository tfscharff/doi-mcp (18 stars, last pushed 9d ago), licensed MIT. It adds 1,922 tokens to every session, about $0.0077 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 2026-08-30.

Related

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

doi-mcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
doi-mcp CLAUDE.mdtfscharff/doi-mcpInstructions file189d agoMITA1,922Claude 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