What is academia_mcp CLAUDE.md?

Project instructions for Academia MCP, a Python server that searches, downloads, analyzes, and reports on scientific papers and datasets. An MCP server is a service that makes tools and data available to AI assistants.

Use it when setting up, developing, testing, or extending Academia MCP and its academic search, document, dataset, and research-analysis features.

It gives contributors a reliable overview of the project, setup process, supported sources, and development commands. This reduces guesswork when changing or running the repository.

How IlyaGusev/academia_mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to IlyaGusev/academia_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/IlyaGusev/academia_mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/IlyaGusev/academia_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/ilyagusev/academia_mcp/claude-md/github.svg)](https://agentmods.dev/instructions/ilyagusev/academia_mcp/claude-md)

Your own site

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

Per session 2,701 This file is loaded in full into every session.

When invoked 2,701 The same file — it is already loaded in full.

Security scan B 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	$0.02701	$0.02701
Opus 5.5	$0.01080	$0.01080
Sonnet 5.5	$0.00540	$0.00540
Haiku 4.5	$0.00270	$0.00270

Measured 2mo ago against content hash 524d061b2b29, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

academia_mcp CLAUDE.md scanned grade B 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

- Install TeX Live: `sudo apt install texlive-latex-base texlive-fonts-recommended texlive-latex-extra texlive-science latexmk`

CLAUDE.md · 313 lines

How it starts

The opening of the file, as written. The whole thing — 313 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

Academia MCP is an MCP (Model Context Protocol) server that provides tools for searching, fetching, analyzing, and reporting on scientific papers and datasets. It integrates with multiple academic APIs (ArXiv, ACL Anthology, Semantic Scholar, Hugging Face) and web search providers (Exa, Brave, Tavily), plus optional LLM-powered document analysis tools.

Key Features:

ArXiv and ACL Anthology search/download
Semantic Scholar citation graphs
Hugging Face datasets search
Web search and page crawling
LaTeX compilation and PDF reading
LLM-powered document QA and research proposal workflows

Tech Stack:

Python 3.12+ with type hints (strict mypy)
FastMCP framework for the MCP server
OpenAI SDK for LLM calls (via OpenRouter)
Pydantic for data models and settings
Fire for CLI argument parsing
Multiple transport options: stdio, SSE, streamable-http

Development Commands

IMPORTANT: Always prefer make commands when available. The Makefile provides consistent, tested workflows.

Setup

# Create virtual environment and install dependencies
uv venv .venv
make install

Validation (ALWAYS run before committing)

# Format code with black (line length: 100)
make black

# Run all validation: black, flake8, mypy --strict
make validate

This is the most important command - run make validate frequently during development.

Testing

# Run full test suite (via make)
make test

# Run a single test file
uv run pytest -s ./tests/test_arxiv_search.py

# Run a specific test
uv run pytest -s ./tests/test_arxiv_search.py::test_arxiv_search

Running the Server Locally

# Run with streamable-http (default, port 5056)
uv run -m academia_mcp --transport streamable-http

# Run with stdio (for Claude Desktop)
uv run -m academia_mcp --transport stdio

# Run with custom port
uv run -m academia_mcp --transport streamable-http --port 8080

Read the full file on GitHub · 313 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 · 313 lines · 2,701 tokens per session scan B 524d061b2b29

Subscribe to this mod's changes

academia_mcp CLAUDE.md is an instructions file published in the GitHub repository IlyaGusev/academia_mcp (94 stars, last pushed 7d ago), licensed Apache-2.0. It adds 2,701 tokens to every session, about $0.0108 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

LLM Python Research Scientific WebSearch mcp-server mcp-servers tools

academia_mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
academia_mcp CLAUDE.mdIlyaGusev/academia_mcp	Instructions file	94	7d ago	Apache-2.0	B	2,701	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

academia_mcp: Instructions file for Claude Code