paper-mcp

A local, Claude-native MCP server for searching and reading arXiv papers. Successor to the Streamlit app in paper-distill/, rebuilt as a plain stdio MCP server with first-class Claude Code support.

No API keys, no secrets, no server-side LLM. The server only searches arXiv and converts papers to markdown — Claude (the MCP client) does all summarization and Q&A. Cheap-model summarization is handled client-side by a bundled Claude Code subagent running on Haiku.

Requirements

• Python 3.12+

• uv

Related MCP server: arXiv Research Assistant MCP Server

Setup

uv sync

That's it. Claude Code picks up the server automatically from the checked-in .mcp.json when you start claude in this directory (approve the project-scoped server on first launch).

To register it elsewhere:

claude mcp add paper-mcp -- uv run --directory C:\path\to\paper-mcp python -m paper_mcp

The server is started as python -m paper_mcp rather than via the paper-mcp console script: on locked-down Windows machines (AppLocker/WDAC), the generated .venv\Scripts\*.exe shims may be blocked from executing, while python.exe is allowed.

Tools

Prompts (slash commands in Claude Code)

• /mcp__paper-mcp__summarize-paper <id> [paragraphs] [audience] — audience: High School, Undergraduate, Graduate, PhD

• /mcp__paper-mcp__ask-paper <id> "<question>"

Haiku summarization (Claude Code)

• /summarize-paper <arxiv-id> [paragraphs] [audience] runs the bundled paper-summarizer subagent on Haiku, so the full paper text never enters your main conversation context — only the summary comes back.

Configuration (optional)

Downloads are capped at 50 MB with a 60 s timeout. Cached paper versions are immutable, so there is no TTL — the cache is size-bounded instead.

Development

uv run python -m pytest -q    # tests (no network needed)
uv run ruff check .           # lint
uv run ruff format .          # format

Manual smoke test against the live server:

npx @modelcontextprotocol/inspector uv run python -m paper_mcp