What is SemanticScholarMCP CLAUDE.md?

Project instructions for a server that connects coding agents to Semantic Scholar, an academic search service and database of research papers, authors, citations, and references.

Use them when developing, testing, formatting, or configuring the Semantic Scholar MCP server, including its paper searches, citation lookups, and PDF downloads.

They give an agent the project overview, setup commands, architecture notes, testing options, and code-quality checks needed to work on the server correctly.

How fegizii/SemanticScholarMCP configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to fegizii/SemanticScholarMCP. 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/fegizii/SemanticScholarMCP/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/fegizii/SemanticScholarMCP

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/fegizii/semanticscholarmcp/claude-md/github.svg)](https://agentmods.dev/instructions/fegizii/semanticscholarmcp/claude-md)

Your own site

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

Per session 808 This file is loaded in full into every session.

When invoked 808 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.

Model	Per session	Once invoked
Fable 5.1	$0.00808	$0.00808
Opus 5.5	$0.00323	$0.00323
Sonnet 5.5	$0.00162	$0.00162
Haiku 4.5	$0.00081	$0.00081

Measured 2mo ago against content hash cc5292df9f42, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

SemanticScholarMCP 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 · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 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

Semantic Scholar MCP Server is a Model Context Protocol (MCP) server providing access to the Semantic Scholar Academic Graph API. It offers 12 tools for searching papers/authors, retrieving citations/references, and downloading PDFs through an async HTTP interface.

Development Commands

Testing:

make test                 # Run all tests
make test-unit           # Unit tests only (fast, no API calls)
make test-integration    # Integration tests (requires SEMANTIC_SCHOLAR_API_KEY)
make test-performance    # Performance/load tests

Code Quality:

make lint                # Run flake8, isort, black checks
make format              # Auto-format with black and isort

Setup:

make install-dev         # Install with dev dependencies
pip install -e ".[test,dev,metadata]"  # Alternative install

Testing Individual Components:

pytest tests/test_server.py::test_search_papers -v
pytest -m "not integration"  # Skip integration tests
pytest -k "test_format_paper"  # Run specific test patterns

Architecture Overview

Single-Module Design: All functionality in src/semantic_scholar_mcp/server.py (832 lines) using FastMCP framework.

Core Components:

API Client: make_api_request() handles HTTP requests with error handling
Formatters: format_paper(), format_author() convert API responses
12 MCP Tools: Paper search/retrieval, author search, citations, PDF downloads
PDF Handler: Downloads with metadata embedding (requires PyPDF2)

Tool Categories:

Paper tools: search_papers, get_paper, get_paper_batch, get_paper_citations, get_paper_references
Author tools: search_authors, get_author
Specialized: search_snippets, get_citation_context, get_paper_pdf_info, download_paper_pdf

Configuration

API Key (Optional): Set SEMANTIC_SCHOLAR_API_KEY environment variable for higher rate limits. Server works without key but shares public rate limits.

Read the full file on GitHub · 86 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 · 86 lines · 808 tokens per session scan A cc5292df9f42

Subscribe to this mod's changes

SemanticScholarMCP CLAUDE.md is an instructions file published in the GitHub repository fegizii/SemanticScholarMCP (3 stars, last pushed 1y ago), licensed MIT. It adds 808 tokens to every session, about $0.0032 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.

Research

SemanticScholarMCP CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
SemanticScholarMCP CLAUDE.mdfegizii/SemanticScholarMCP	Instructions file	3	1y ago	MIT	A	808	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

SemanticScholarMCP: Instructions file for Claude Code