papergraph-mcp
PaperGraph MCP turns math papers into evidence-grounded reading maps for AI agents: extract results, trace proof evidence, plan reading order, and review extern
What is papergraph-mcp?
PaperGraph MCP turns math papers into evidence-grounded reading maps for AI agents: extract results, trace proof evidence, plan reading order, and review external dependencies without guessing.
Overview of papergraph-mcp
What it is
PaperGraph MCP turns math papers into evidence-grounded reading maps for AI agents. It extracts results, traces proof evidence, plans reading order, and reviews external dependencies without guessing. The tool converts arXiv papers, local LaTeX projects, and born-digital PDFs into a local theorem-centered workspace where users can inspect source-backed results, proofs, citations, and dependencies, save reading progress, and export Markdown reports.
Key features
- Start with a Paper Map: inspect structure, main-result candidates, and external reading risks before choosing a theorem.
- Trace statements and proof-local references back to source slices; inspect direct and recursive dependencies, shared prerequisites, cycles, and unknowns.
- Discover public full-text candidates for DOI papers and review scholarly reference matches from Crossref, OpenAlex, and arXiv.
- Keep queues, sessions, checkpoints, notes, and open questions in local SQLite workspaces. Export Reading Reports and Cross-Paper Reading Plans.
Use cases
Researchers reading math papers who need to trace proof evidence and dependencies. AI agents requiring evidence-grounded reading maps for automated analysis. Users planning reading order across multiple papers and reviewing external reference matches. Anyone who wants to keep local, structured notes and reports on mathematical literature.
Getting started
Install uv, then run: sh uvx --from papergraph-mcp==1.2.3 papergraph-mcp --version uvx --from papergraph-mcp==1.2.3 papergraph-mcp doctor For MCP client configuration, use the stdio JSON configuration described in the repository README.
License and pricing
MIT License. Free and open source.
Based on the project's public README and repository metadata.