Papergraph MCP

by lotchuazzz-crypto• 279•• Scanned•Claim this listing•Request removal
Research & Analysisai agentsarxivknowledge graphlatexmathematics

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.

Papergraph MCP is an open-source mcp server by lotchuazzz-crypto, written mainly in Python, with 279 GitHub stars and the MIT license. Its code was last updated Oct 18, 2026. The latest PyPI release is papergraph-mcp 1.2.3, published Oct 18, 2026, with 39 downloads last week.

Scan summary: scanned Nov 5, 2026 at commit af7f302. Seen able to read environment and secrets. Scan policy

aboutREADMEsecurityreviews

How to install Papergraph MCP

Built from the start command in the project's README: uvx --from papergraph-mcp==1.2.3 papergraph-mcp. Check the README for required keys or settings.

Claude Code · Terminal
claude mcp add papergraph-mcp -- uvx --from papergraph-mcp==1.2.3 papergraph-mcp
Claude Desktop · claude_desktop_config.json
{
  "mcpServers": {
    "papergraph-mcp": {
      "command": "uvx",
      "args": [
        "--from",
        "papergraph-mcp==1.2.3",
        "papergraph-mcp"
      ]
    }
  }
}
Cursor · .cursor/mcp.json
{
  "mcpServers": {
    "papergraph-mcp": {
      "command": "uvx",
      "args": [
        "--from",
        "papergraph-mcp==1.2.3",
        "papergraph-mcp"
      ]
    }
  }
}
VS Code · Terminal
code --add-mcp '{"name":"papergraph-mcp","command":"uvx","args":["--from","papergraph-mcp==1.2.3","papergraph-mcp"]}'

What Papergraph MCP can touch

  • Run shell commandsNot seen in this scan
  • Run dynamic codeNot seen in this scan
  • Read or write filesNot seen in this scan
  • Read environment and secretsListed as a tool: get_environment_diagnostics
  • Control a web browserNot seen in this scan
  • Connect to databasesNot seen in this scan
  • Read or send messagesNot seen in this scan
  • Touch money or tradingNot seen in this scan
  • Connect to the internetNo connections seen while running

"Not seen" means our checks did not find it, and the tool may still do it. Covers commit af7f302, Nov 5, 2026. See the scan policy.

Before you install Papergraph MCP

AgenticMart scanned Papergraph MCP on Nov 5, 2026 with automated checks for hidden code, known-malicious packages, leaked secrets and vulnerable dependencies. The result covers one commit under our scan policy, so review what access you give it and check any advisories shown here.

What it can access

  • An MCP server is a program your AI app starts and talks to. A local one runs with your user's permissions: it can see the files, environment variables and network your account can.

Before you install

  1. Pin the version you reviewed instead of always installing the latest release.
  2. Read the tool list or scripts before the first run, and keep approval prompts on for actions that write, send or delete.
  • Maintained by lotchuazzz-crypto on GitHub, 279 stars and 4 forks. Popularity is not proof of safety.
  • Last code change: Oct 18, 2026.
  • Open-source license: MIT.
Read the scan reportWhat our scan checks

Tools Papergraph MCP exposes (68)

Listed by the server itself during our scan of commit af7f302.

  • get_environment_diagnostics

    Return PaperGraph version and reproducible launch diagnostics.

  • validate_arxiv_input

    Normalize arXiv ID and URL inputs and return the safe next action.

  • validate_arxiv_request

    Validate a raw user arXiv request and return the safe next action.

  • open_workspace

    Open or initialize a persistent multi-paper workspace.

  • workspace_add_local_paper

    Add or replace a local LaTeX project in the active workspace.

  • workspace_add_arxiv_paper

    Add or replace an arXiv LaTeX project in the active workspace.

  • workspace_add_pdf_paper

    Add or replace a born-digital PDF paper in the active workspace.

  • discover_doi_paper

    Find exact DOI metadata and public body candidates; never download links.

  • workspace_import_doi_candidate

    Import a selected root DOI PDF only after explicit review/confirmation. This is not permission to download newly discovered external references. Candidate provider identity is evidence, not a verification of PDF contents.

  • workspace_add_doi_paper

    Load a user-requested root DOI when one public PDF candidate is eligible. Multiple candidates require user selection. Do not use for newly discovered external references: those require an import plan and review first.

  • workspace_list_papers

    List all papers stored in the active workspace.

  • workspace_get_paper

    Return metadata and counts for one stored paper.

  • workspace_search_theorems

    Search theorem titles and bodies across the active workspace.

  • workspace_get_dependencies

    Return dependencies of a globally identified stored theorem.

  • workspace_get_dependency_diagnostics

    Explain how workspace dependencies were extracted for one theorem.

  • workspace_get_citations

    Return incoming or outgoing citation evidence for a stored paper.

  • workspace_list_results

    List a stable result page (limit 1..100). Advance offset by returned count. A full page may be truncated; continue until a page has fewer than limit results. This is not an unbounded complete list.

  • workspace_get_result

    Return one stored evidence result with source spans.

  • workspace_get_result_proof

    Return proof evidence for one stored evidence result.

  • workspace_get_proof_dependencies

    Return proof dependency evidence for one stored evidence result.

  • workspace_get_external_result_mentions

    Return external result mentions from a result's proof evidence.

  • workspace_get_evidence

    Return metadata and source spans for one evidence node or edge.

  • workspace_export_reading_bundle

    Export a paper-level evidence bundle for paper-reading consumers.

  • workspace_export_result_reading_context

    Export focused evidence context for reading one result's proof.

  • workspace_get_source_slice

    Return bounded source text around one span, result, or proof.

  • workspace_read_source_blocks

    Read raw source blocks from a slice locator; follow next until null. Blocks are source text, with no inferred proof ownership. Works for legacy imports without changing reading data. A changed extraction needs new locators.

  • workspace_get_result_reading_path

    Return deterministic local reading paths for one result.

  • workspace_get_dependency_reading

    List main-result candidates or read a user-selected target with evidence. Statement references and proof-local dependencies remain separate. External references produce reviewable plans only; empty evidence is not independence.

  • workspace_create_reading_session

    Create a persistent reading session in the active workspace.

  • workspace_list_reading_sessions

    List persistent reading sessions in the active workspace.

  • workspace_get_reading_session

    Return one persistent reading session with checkpoints and notes.

  • workspace_record_reading_checkpoint

    Create or update a reading checkpoint in the active workspace.

  • workspace_add_reading_note

    Add a note or question to a reading session.

  • workspace_export_reading_session_summary

    Export a deterministic recovery summary for a reading session.

  • workspace_create_reading_queue

    Create a persistent reading queue for one stored result.

  • workspace_list_reading_queues

    List persistent reading queues in the active workspace.

  • workspace_get_reading_queue

    Return one persistent reading queue with ordered items.

  • workspace_apply_reading_queue_to_session

    Apply reading queue items as checkpoints in a reading session.

  • workspace_plan_external_imports_for_result

    Plan external arXiv imports for one result's reading path.

  • workspace_plan_external_imports_for_queue

    Plan external arXiv imports referenced by one reading queue.

Papergraph MCP is an open-source mcp server by lotchuazzz-crypto, written mainly in Python. 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.

At a glance

Stars
279
Forks
4
Language
Python
License
MIT
Created
Sep 2026
Last update
Oct 18, 2026
Type
MCP Server
Price
Free

Topics

ai-agentsarxivknowledge-graphlatexmathematicsmcpmodel-context-protocolpythonresearch-toolsskills

Questions about Papergraph MCP

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.

Who maintains Papergraph MCP?

Papergraph MCP is maintained by lotchuazzz-crypto on GitHub (lotchuazzz-crypto/papergraph-mcp). AgenticMart lists it from public repository data.

Is Papergraph MCP safe to use?

AgenticMart scanned Papergraph MCP on Nov 5, 2026 with automated checks for hidden code, known-malicious packages, leaked secrets and vulnerable dependencies. The result covers one commit under our scan policy, so review what access you give it and check any advisories shown here.

What license does Papergraph MCP use?

It is published under the MIT license.

Papergraph MCP alternatives

View more →

Similar mcp servers in Research & Analysis, ranked by GitHub stars. Compare licence, recent activity and scan status before you choose.

NameStarsLicenceLast updatedScan
Papergraph MCP (this page)
lotchuazzz-crypto
279MITOct 18, 2026Scanned, no flagged issues
Worldmonitor
koala73
90kAGPL-3.0Nov 1, 2026Scanned, no flagged issues
GPT Researcher
assafelovic
30kApache-2.0Oct 10, 2026Scanned, no flagged issues
Auto Claude Code Research In Sleep
wanshuiyin
18kMITNov 1, 2026Scanned, no flagged issues
Deep Research
u14app
4.7kMITJun 18, 2026Scanned, no flagged issues
MCP Server Chart
antvis
4.4kMITAug 27, 2026Scanned, no flagged issues