Skip to main content
Glama
paper-download-mcp

paper-download-mcp

by TIGERwu0118

paper-download-mcp

General-purpose paper downloader MCP: probes providers by DOI/UT identifier, downloads to a short-lived staging area, verifies the PDF, and cleans up. It does not connect to PostgreSQL, does not accept project/output_dir/year/publisher/filename, and does not manage final storage—those are the responsibility of the calling project (e.g., the HC integration side).

Architecture (converged 2026-07-22)

MCP (通用获取器)                    调用项目集成侧
  health                              任务规划与项目筛选
  list_providers                      最终存储与资产登记
  probe(identifier, hint?)            批量编排与限速
  fetch(identifier, hint?) → artifact 下载审计
  verify_artifact(id)                 项目级状态管理
  discard_artifact(id)

Related MCP server: acatome-quest-mcp

Tools (6)

Tool

Description

paper_download_health

Version/staging directory/provider availability (does not echo keys)

paper_download_list_providers

Lists providers and their status

paper_download_probe

Probes whether a provider can fetch a given identifier

paper_download_fetch

Downloads to staging, returns artifact_id (does not accept project/output_dir, etc.)

paper_download_verify_artifact

Verifies the staged PDF (existence/page count/hash/size)

paper_download_discard_artifact

Cleans up the staged artifact

fetch returns: artifact_id / temp_path / source / byte count / SHA-256 / page count / status / failure classification.

Providers

Provider

Status

Description

fake

✅

For testing, synthesizes PDFs, no network

elsevier

✅ controlled enablement

Article Retrieval API; requires authorization, campus IP, and a 0600 key file

mdpi

✅

cloakbrowser extracts the PDF link and captures the browser download

springer

✅

cloakbrowser obtains cookies, requests downloads; limited subscription scope

frontiers

✅

Redirected article URL goes from /full to /pdf

plos

✅

DOI journal prefix maps to the PLOS PDF address

copernicus

✅

Article page and DOI suffix construct the PDF address

bmc

✅

Springer-like page structure and cookie download

The Elsevier key only enters through the mode 0600 file pointed to by PAPER_DOWNLOAD_ELSEVIER_API_KEY_FILE, never into tool arguments, logs, or messages.

These providers' page rules come from practical records in existing English-literature paper download work; specific limitations and evidence are in docs/provider-acceptance.md. "Implemented" in code does not mean every paper is downloadable in the current network environment; subscriptions, page changes, rate limiting, and article takedowns still cause explainable failures.

This project does not integrate scansci-pdf. It is an independent third-party MCP and is not part of this project's provider chain.

Installation and Running

cd paper-download-mcp
python -m pip install -e ".[dev,browser]"

# 测试(无网络无 DB 无 secret)
python -m pytest tests -v

# 启动 MCP (stdio)
paper-download-mcp   # 或 python -m paper_download_mcp

Browser providers require cloakbrowser; Elsevier's page-count verification requires the system to provide pdfinfo (usually from poppler-utils).

Calling Project Integration Side

The project side is responsible for candidate SQL, canonical storage policy, orchestration loop, asset table, and download audit. This MCP only delivers staged artifacts and their verification metadata.

Available Tools

6 tools
paper_download_discard_artifactC

Remove a staged artifact from the staging area.

Inputs: artifact_id (required). Returns: result

paper_download_fetchA

Fetch a paper into the staging area; return artifact metadata.

Does NOT accept project, output_dir, year, publisher, or final filename. The caller moves the verified artifact to final storage.

Args: identifier: DOI or UT. provider_hint: Preferred provider name (hard constraint if given).

Inputs: identifier (required), provider_hint. Returns: result

paper_download_healthA

Report version, staging dir, provider availability.

Never prints API keys or credentials.

Inputs: no named parameters. Returns: result

paper_download_list_providersA

List available download providers and their status.

Inputs: no named parameters. Returns: result

paper_download_probeB

Probe whether a provider can likely fetch the given identifier.

Args: identifier: DOI (e.g. 10.1016/j.x) or UT. provider_hint: If given, only this provider is considered.

Inputs: identifier (required), provider_hint. Returns: result

paper_download_verify_artifactA

Verify a staged artifact: existence, PDF validity, page count, hash.

Inputs: artifact_id (required). Returns: result

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.7/5.0

    Scored across 6 tools

    Disambiguation5/5

    Each tool has a clear, distinct role in the fetch→verify→discard workflow, plus provider/system introspection. Fetch and probe are differentiated by actual download vs. likelihood check, and health versus list_providers is similarly distinct.

    Naming Consistency4/5

    All tools share the paper_download_ prefix and use snake_case, but most follow a verb_noun pattern while paper_download_health uses a noun. The overall convention is still predictable and readable.

    Tool Count5/5

    With six tools covering fetch, discard, probe, health, provider listing, and verification, the count is well-scoped for a focused paper-download staging service. Each tool earns its place and there is no bloat.

    Completeness4/5

    The core lifecycle of fetching, verifying, discarding, and probing is covered, and provider/health introspection is present. A minor gap is the lack of a tool to list currently staged artifacts, though the workflow is still usable without it.

    Maintenance

    ActivityInactive
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      D
      maintenance
      An MCP server for downloading academic papers from multiple sources using intelligent routing and year-aware priority selection. It enables users to retrieve metadata and download single or batch PDFs by DOI or URL.
      3
      21 PyPI
      3
      MIT
    • A
      license
      A
      quality
      D
      maintenance
      An MCP server that resolves paper requests (DOI, arXiv, etc.), checks a local store, fetches open-access PDFs, and returns request IDs. It integrates with acatome-extract for ingestion and provides tools for submission, status, update, and file upload.
      4
      43 PyPI
      GPL 3.0
    • A
      license
      A
      quality
      C
      maintenance
      MCP server for downloading academic papers from DOI or title, resolving references, and generating citations. Supports batch downloads, multiple mirrors, and optional Unpaywall integration.
      11
      2
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      A provider-neutral Web Search MCP server and CLI that combines live search, scholarly discovery, verified PDF downloads, URL normalization, multi-provider ranking, secure page fetching, caching, and citation-ready research evidence.
      MIT