LABSCO SUMMARY

One query instead of twenty search boxes — and it tells you which ones actually answered.

The unified search fans the same query across every configured source, and when a PDF is not where the record says it is, the fallback works down open-access repositories and Unpaywall before giving up. The published capability matrix is the unusual part: it says which sources are metadata-only or blocked, rather than letting you find out mid-project.

What it is

One search surface over academic sources — arXiv, PubMed and PMC, bioRxiv and medRxiv, Semantic Scholar, Crossref, OpenAlex, Europe PMC, CORE, dblp, DOAJ, BASE, HAL, Zenodo, OpenAIRE, CiteSeerX, SSRN, IACR and Google Scholar — with per-source download and read calls behind it, and a published capability matrix saying which of those actually work.

What you get

One call that searches every configured source at once, and per-source search where you want that source's own filters (search_papers)
PDFs downloaded per source and read back as text, where the source allows it
A fallback download that tries the source, then open-access repositories, then Unpaywall — and Sci-Hub only when you explicitly ask for it (download_with_fallback)
A DOI looked up in Unpaywall for its open-access status (search_unpaywall)
A capability matrix per source, built from live integration tests, that says plainly which sources search reliably, which only return metadata, and which are subject to bot detection
Automatic degradation rather than silent failure: Semantic Scholar retries without the key on a 403, CORE falls back to key-less on 401 and 403, OpenAIRE retries three times with escalating request profiles, and BASE returns empty rather than erroring when your IP is not registered

Requirements

uvx, or one of six other install routes including Smithery, pip and Docker. Most sources work without credentials; the rest take their own key — PAPER_SEARCH_MCP_CORE_API_KEY, PAPER_SEARCH_MCP_SEMANTIC_SCHOLAR_API_KEY and PAPER_SEARCH_MCP_ZENODO_ACCESS_TOKEN mainly raise rate limits — and Unpaywall requires an email address in PAPER_SEARCH_MCP_UNPAYWALL_EMAIL. Read the capability matrix before planning around a source: PubMed, Crossref, OpenAlex and dblp are metadata only, PMC and Europe PMC download open-access PDFs only, Google Scholar and SSRN are under active bot detection, BASE needs institutional IP registration, and the IEEE Xplore and ACM connectors are skeletons that need their keys to activate at all.

Setup effort

One command — uvx paper-search-mcp

See installation options

USE CASES

Finding everything published on a question

Search every source in one call rather than opening each one's search box. Coverage differs enough between them that the union is meaningfully bigger than any single source.

search_papers

Getting the PDF when the publisher's link is dead

Use the fallback download: it tries the source, then open-access repositories, then Unpaywall. Sci-Hub is only in the chain if you ask for it, and that choice is yours to make.

download_with_fallbacksearch_unpaywall

Reading a preprint the week it appears

bioRxiv, medRxiv, arXiv and IACR all search, download and read reliably, so the newest work is reachable end to end rather than as a title and an abstract.

search_papers

Working from a DOI you were handed

Look the DOI up in Unpaywall for its open-access status before hunting for a PDF. It answers whether a legal free copy exists in one call — and it needs your email address configured.

search_unpaywalldownload_with_fallback

Working out whether a source is worth relying on

Read the capability matrix first. Knowing that PubMed and Crossref return metadata only, and that Google Scholar is under bot detection, saves you designing a workflow around something that will not deliver.

Building a reading pile you keep

Download and read papers per source into local storage, so the second pass over a set does not re-fetch anything and works on sources that later become unreachable.

download_with_fallbacksearch_papers

63 tools

Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.

`download_acm`

Download a PDF from ACM Digital Library. Requires PAPER_SEARCH_MCP_ACM_API_KEY (or ACM_API_KEY) and institutional access.

Args: paper_id: ACM DL paper identifier. save_path: Directory to save the PDF (default: './downloads'). Returns: str: Path to saved PDF or error message.

INSTALLATION

Connect your client

Server setup

TERMINAL

uvx paper-search-mcp

MCP Clients

Claude Desktop — Smithery

CLAUDE DESKTOP — SMITHERY · TERMINAL

npx -y @smithery/cli install @openags/paper-search-mcp --client claude

Claude Desktop — uvx

CLAUDE DESKTOP — UVX · JSON

{
  "mcpServers": {
    "paper-search-mcp": {
      "command": "uvx",
      "args": [
        "paper-search-mcp"
      ],
      "env": {
        "PAPER_SEARCH_MCP_UNPAYWALL_EMAIL": "<YOUR_PAPER_SEARCH_MCP_UNPAYWALL_EMAIL>"
      }
    }
  }
}

Claude Desktop — uv

CLAUDE DESKTOP — UV · JSON

{
  "mcpServers": {
    "paper-search-mcp": {
      "command": "uv",
      "args": [
        "tool",
        "run",
        "paper-search-mcp"
      ],
      "env": {
        "PAPER_SEARCH_MCP_UNPAYWALL_EMAIL": "<YOUR_PAPER_SEARCH_MCP_UNPAYWALL_EMAIL>"
      }
    }
  }
}

Claude Desktop — pip

CLAUDE DESKTOP — PIP · JSON

{
  "mcpServers": {
    "paper-search-mcp": {
      "command": "python",
      "args": [
        "-m",
        "paper_search_mcp.server"
      ],
      "env": {
        "PAPER_SEARCH_MCP_UNPAYWALL_EMAIL": "<YOUR_PAPER_SEARCH_MCP_UNPAYWALL_EMAIL>"
      }
    }
  }
}

Paper Search MCP

One query instead of twenty search boxes — and it tells you which ones actually answered.

What it is

What you get

Requirements

Setup effort

Finding everything published on a question

Getting the PDF when the publisher's link is dead

Reading a preprint the week it appears

Working from a DOI you were handed

Working out whether a source is worth relying on

Building a reading pile you keep

63 tools

download_acm

download_arxiv

download_base

download_biorxiv

download_citeseerx

download_crossref

download_dblp

download_doaj

download_hal

download_iacr

download_ieee

download_medrxiv

download_openaire

download_openalex

download_pubmed

download_scihub

download_semantic

download_ssrn

download_with_fallback

download_zenodo

get_crossref_paper_by_doi

read_acm_paper

read_arxiv_paper

read_base_paper

read_biorxiv_paper

read_citeseerx_paper

read_crossref_paper

read_dblp_paper

read_doaj_paper

read_hal_paper

read_iacr_paper

read_ieee_paper

read_medrxiv_paper

read_openaire_paper

read_openalex_paper

read_pubmed_paper

read_semantic_paper

read_ssrn_paper

read_zenodo_paper

search_acm

search_arxiv

search_base

search_biorxiv

search_citeseerx

search_core

search_crossref

search_dblp

search_doaj

search_europepmc

search_google_scholar

search_hal

search_iacr

search_ieee

search_medrxiv

search_openaire

search_openalex

search_papers

search_pmc

search_pubmed

search_semantic

search_ssrn

search_unpaywall

search_zenodo

What to know first

Tools you get

Requires

Moderate Standing cost

`download_acm`

`download_arxiv`

`download_base`

`download_biorxiv`

`download_citeseerx`

`download_crossref`

`download_dblp`

`download_doaj`

`download_hal`

`download_iacr`

`download_ieee`

`download_medrxiv`

`download_openaire`

`download_openalex`

`download_pubmed`

`download_scihub`

`download_semantic`

`download_ssrn`

`download_with_fallback`

`download_zenodo`

`get_crossref_paper_by_doi`

`read_acm_paper`

`read_arxiv_paper`

`read_base_paper`

`read_biorxiv_paper`

`read_citeseerx_paper`

`read_crossref_paper`

`read_dblp_paper`

`read_doaj_paper`

`read_hal_paper`

`read_iacr_paper`

`read_ieee_paper`

`read_medrxiv_paper`

`read_openaire_paper`

`read_openalex_paper`

`read_pubmed_paper`

`read_semantic_paper`

`read_ssrn_paper`

`read_zenodo_paper`

`search_acm`

`search_arxiv`

`search_base`

`search_biorxiv`

`search_citeseerx`

`search_core`

`search_crossref`

`search_dblp`

`search_doaj`

`search_europepmc`

`search_google_scholar`

`search_hal`

`search_iacr`

`search_ieee`

`search_medrxiv`

`search_openaire`

`search_openalex`

`search_papers`

`search_pmc`

`search_pubmed`

`search_semantic`

`search_ssrn`

`search_unpaywall`

`search_zenodo`