agentmods.dev

academic-tools-mcp: Instructions file for Claude Code

CLAUDE.md

academic-tools-mcp CLAUDE.md is an instructions file for Claude Code from hunter-heidenreich/academic-tools-mcp. It costs 781 tokens per session, scanned A, original, MIT.

Development instructions for an MCP server that provides academic-paper tools. It connects to sources such as OpenAlex, arXiv, bioRxiv and medRxiv, which publish or index research papers and preprints.

In plain words
What is it for?
Use it when changing this academic research server, including its paper-search tools, metadata checks, author and institution lookups, BibTeX citations, and citation or reference graphs.
Why use it?
It gives coding agents clear rules for running tests, formatting and type-checking code, and maintaining versions while working on the server.

Instructions file for Claude Code

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

This is hunter-heidenreich/academic-tools-mcp's own configuration. It tells Claude Code how to work on academic-tools-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 academic-tools-mcp configures →

not rated 5repo changed 1mo ago A scan 781 tokens original MIT
View source ↗ hunter-heidenreich/academic-tools-mcp
Reuse

Borrowing it

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

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/hunter-heidenreich/academic-tools-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/hunter-heidenreich/academic-tools-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 781 This file is loaded in full into every session.
When invoked 781 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 $0.00781 $0.00781
Opus 5.5 $0.00312 $0.00312
Sonnet 5.5 $0.00156 $0.00156
Haiku 4.5 $0.00078 $0.00078

Measured 1mo ago against content hash 99167915fda9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

academic-tools-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 1mo 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 · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

What This Is

A FastMCP-based MCP server wrapping academic APIs (see README.md for the provider table). It exists primarily to support an academic notes/blog workflow: verifying paper metadata, authors, and institutions, generating BibTeX, and exploring reference/citation graphs.

Commands

uv run pytest -v                                                 # Run the test suite
uv run python -m academic_tools_mcp.server                       # Run the MCP server
ENABLE_DEBUG_TOOLS=1 uv run python -m academic_tools_mcp.server  # + the get_server_stats tool

Changelog & versioning

Before opening a PR, add a bullet to ## [Unreleased] in CHANGELOG.md (Keep a Changelog format) under the right Added / Changed / Fixed / Removed heading, referencing the PR number (e.g. ([#12])) with a matching link definition at the bottom of the file. Skip only for changes with no user-facing effect (pure refactors, internal docs, test-only edits).

Releases are cut deliberately, not per-merge. Calendar versioning: rename [Unreleased] to ## [YYYY.MM.DD] — YYYY-MM-DD, bump version in pyproject.toml to match (PEP 440 drops leading zeros: tag v2026.05.29 ↔ version 2026.5.29), and tag the commit vYYYY.MM.DD.

Where the detail lives

Design detail lives in .claude/rules/, each file auto-loading from its own paths: frontmatter when you read a matching file. You never need to go looking for one: open the code and its rules arrive with it.

Where a new file goes, and what to call it, is machine-checked. tests/test_layering.py owns the layer order in its _LAYERS table and asserts it by AST; tests/test_rules_layer.py does the same for the rules layer's own structure. Both fail CI rather than review.

Adding a new API provider or a new OpenAlex entity: use the add-provider skill.

Cross-cutting design decisions

  • One paper tool per job, not one per provider. get_paper_metadata / _authors / _abstract / _bibtex take any identifier and dispatch on identifier shape, not on which provider has richer data — get_paper_metadata("2301.00001") returns arXiv's native response even though OpenAlex also has the paper. Provider-specific data (OpenAlex topics, citations, venue) gets dedicated OpenAlex-only tools.
  • Operational stats are not agent-facing. net/stats.py counters exist for the operator; get_server_stats registers only under ENABLE_DEBUG_TOOLS=1, off by default, so an agent can't see or branch on cache/throttle state.

Read the full file on GitHub · 69 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. 1mo ago Changed · -14 lines · -233 tokens per session 99167915fda9
  2. 1mo ago Changed · +1 lines · +7 tokens per session 9a38060fd0a6
  3. 1mo ago Changed · +26 lines · -388 tokens per session e93825f28a45
  4. 1mo ago Changed · +2 lines · +113 tokens per session 432cebc52491
  5. 2mo ago Changed · +1 lines · +111 tokens per session 5fda2f1b911f
  6. 2mo ago Changed · -100 lines · -3,035 tokens per session 3e1e113dd254
  7. 2mo ago First seen · 153 lines · 4,206 tokens per session scan A 5208caa05ea3

Subscribe to this mod's changes

academic-tools-mcp CLAUDE.md is an instructions file published in the GitHub repository hunter-heidenreich/academic-tools-mcp (5 stars, last pushed 1mo ago), licensed MIT. It adds 781 tokens to every session, about $0.0031 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.

Researchacademic-researchai-agentsarxivbibtexbiorxivcrossref
Related

academic-tools-mcp CLAUDE.md compared with instructions from other repositories

academic-tools-mcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
academic-tools-mcp CLAUDE.mdhunter-heidenreich/academic-tools-mcpInstructions file51mo agoMITA781Claude 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