ScrapeMole Arxiv

dev.pages.scrapemolePublished by scrapemole.pages.devv1.0.0Updated Oct 24, 2026

Pay-per-call x402 arXiv paper search, metadata, abstracts, and category listings.

The publisher's own server: Scrape.ly

VerifiedStreamable HTTPWeb executableWeb Search & ScrapingKnowledge & Memory

Overview

AI-generated overview

Remote MCP server for searching arXiv e-prints and fetching paper metadata, abstracts and category listings, paid per call via x402 USDC on Base.

What you can do
  • Search arXiv e-prints by keyword, title, author or field query, returning up to 25 papers with ids, titles, summaries and authors
  • Fetch a full metadata card for an arXiv id, including abstract, authors with affiliations, categories and timestamps
  • Get a compact abstract card for an arXiv id with author names, category, dates and abs/pdf links
  • List the latest or relevance-ranked papers in one arXiv subject class, with total results for paging
When to use it
Useful when an assistant needs to look up arXiv preprints, check a paper's metadata or abstract, or browse recent papers in a subject category, and you are willing to pay a small per-call fee in USDC.
Requirements
A remote streamable HTTP endpoint; no local package, account or API key is declared. Some tools are paid per successful call via x402 USDC on Base, so a wallet able to make x402 payments is needed for those. Network access to the endpoint is required.
Before you install
Several tools are paid: x402 USDC on Base at $0.002 per successful call, so usage spends real funds from a wallet. Payment credentials are handled through the x402 flow. Queries and paper ids are sent to a third-party service.

Installation

In SourceWeft

  1. Open ScrapeMole Arxiv in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/dev.pages.scrapemole%2Farxiv/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "scrapemole-arxiv": {
      "type": "http",
      "url": "https://arxiv.scrapemole.workers.dev/mcp"
    }
  }
}

Tools

4

arxiv_paper

ScrapeMole Arxiv: arXiv paper search and metadata for AI agents: arXiv paper metadata

Use when you have an arXiv id (new-style like 1706.03762 or with version 1706.03762v7, or old-style like hep-ex/0307015) and need its public metadata card: title, abstract/summary, authors with affiliations (emails removed), primary category, all categories, published and updated timestamps, author comment, journal reference, DOI, and abs/PDF URLs. Without a version suffix, arXiv returns the latest version. Paid tool: x402 USDC on Base, $0.002 per successful call; call without payment to receive the PaymentRequired object.

Parametersidrequired

arxiv_abs

ScrapeMole Arxiv: arXiv paper search and metadata for AI agents: arXiv abstract card

Use when you need a compact abstract card for an arXiv id without full affiliation/journal/comment fields: returns id, title, summary, author names only, primary category, published/updated, absUrl and pdfUrl. Same id rules as /v1/arxiv/paper. Paid tool: x402 USDC on Base, $0.002 per successful call; call without payment to receive the PaymentRequired object.

Parametersidrequired

arxiv_category

ScrapeMole Arxiv: arXiv paper search and metadata for AI agents: arXiv papers by category

Use when you want the latest or relevance-ranked papers in one arXiv subject class: pass cat (e.g. cs.AI, quant-ph, stat.ML). Returns up to 25 papers with the same fields as search, plus totalResults for paging. Default sort is submittedDate descending (newest first). Paid tool: x402 USDC on Base, $0.003 per successful call; call without payment to receive the PaymentRequired object.

ParameterscatrequiredstartsortBysortOrdermax_results

Version history

1
  1. v1.0.0LatestOct 12, 2026

Score

72% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts

    Publish an icon in the registry entry.

  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • LicenseNot applicable

    A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.

Other Scrape integrations