What is scholar-mcp AGENTS.md?

Repository instructions for scholar-mcp, a server that provides access to scholarly papers, patents, books, and standards and can convert PDFs for processing.

It helps maintain the server, add research-related tools and resources, work with scholarly documents and PDFs, and follow its Python development and release conventions.

It gives coding agents the project's structure, conventions, tools, and domain context before they change the code.

How pvliesdonk/scholar-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to pvliesdonk/scholar-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/pvliesdonk/scholar-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/pvliesdonk/scholar-mcp

Made for: Codex, OpenCode.

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/pvliesdonk/scholar-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/pvliesdonk/scholar-mcp/agents-md)

Your own site

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

Per session 6,586 This file is loaded in full into every session.

When invoked 6,586 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 91% copy Near-identical to another mod 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	$0.06586	$0.06586
Opus 5.5	$0.02634	$0.02634
Sonnet 5.5	$0.01317	$0.01317
Haiku 4.5	$0.00659	$0.00659

Measured 23d ago against content hash 09e3c019b47f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

scholar-mcp AGENTS.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 23d 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.

Origin

This is a copy

91% identical to markdown-vault-mcp AGENTS.md — 267 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

AGENTS.md · 275 lines

How it starts

The opening of the file, as written. The whole thing — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scholar MCP

Scholarly papers, patents, books, standards and PDF conversion

Design

Project Structure

src/scholar_mcp/
  server.py            -- FastMCP server factory (make_server) + auth wiring
  config.py            -- env var loading; add domain config fields here
  cli.py               -- CLI entry point (serve command)
  _server_deps.py      -- template lifespan + get_service() DI (template-owned)
  domain.py            -- Service: every upstream client, the cache, enrichment
  tools.py             -- MCP tools; dispatches to the _tools_* category modules
  resources.py         -- MCP resources; add domain resources here
  prompts.py           -- MCP prompts; add domain prompts here
  _rate_limiter.py     -- Rate limiter, retry, try-once + RateLimitedError

Conventions

Python 3.11+
uv for package management, ruff for linting/formatting (line length 88)
hatchling build backend
Conventional commits, one type from build, chore, ci, docs, feat, fix, perf, refactor, revert, style, test — optionally scoped (feat(search): ...) and with ! for a breaking change. Only feat, fix, and the ! marker drive releases: feat cuts a minor, fix a patch, ! a major. Every other type — perf included — cuts nothing and never reaches CHANGELOG.md; a performance change that must ship on its own is either honestly a fix: (it fixes a performance defect) or released with Release Prepare's explicit override_version input.
Google-style docstrings on all public functions
logging.getLogger(__name__) throughout, no print(); messages are event_name key=%s (see the logging-standard skill), and tests/test_logging_standard.py fails on any first-party call that is not
Type hints everywhere
Tests: pytest with fixtures in tests/fixtures/

Read the full file on GitHub · 275 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.

23d ago Changed · +5 lines · +598 tokens per session 09e3c019b47f
1mo ago Changed · +1 lines · +85 tokens per session 6f552fde13e2
1mo ago Changed · +2 lines · +70 tokens per session a194c9202e4d
1mo ago Changed · +7 lines · +105 tokens per session f815c49f3039
1mo ago Changed · +2 lines · +141 tokens per session 37e621668f3c
1mo ago First seen · 258 lines · 5,587 tokens per session scan A 91df2e0e299d

Subscribe to this mod's changes

scholar-mcp AGENTS.md is an instructions file published in the GitHub repository pvliesdonk/scholar-mcp (2 stars, last pushed yesterday), licensed MIT. It adds 6,586 tokens to every session, about $0.0263 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 91% identical to markdown-vault-mcp AGENTS.md, differing in 267 lines, and is treated as a copy.

Research Scientific books citations fastmcp mcp mcp-server model-context-protocol

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 9,649 tokens

scholar-mcp: Instructions file for Codex

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

This is a copy

How it starts

Scholar MCP

Design

Project Structure

Conventions

What this file has done since we first saw it

Other instructions, from other repositories

vscode buildNext.instructions.md

next.js AGENTS.md

vscode oss-third-party-notices.instructions.md

langchain AGENTS.md

vscode copilot-instructions.md

deno copilot-instructions.md