Schema | Paper Download MCP Server

Server Configuration

Describes the environment variables required to run the server.

Name	Required	Description	Default
`PAPER_DOWNLOAD_EMAIL`	Yes	Your email address (required for Unpaywall API compliance). Used for Unpaywall API tracking and contact purposes.
`PAPER_DOWNLOAD_OUTPUT_DIR`	No	Default output directory for downloaded papers.	./downloads

Capabilities

Features and capabilities supported by this server

Capability	Details
`tools`	{ "listChanged": false }
`prompts`	{ "listChanged": false }
`resources`	{ "subscribe": false, "listChanged": false }
`experimental`	{}

Tools

Functions exposed to the LLM to take actions

Name Description

Name	Description
paper_download	Download academic paper by DOI, arXiv ID, or URL. Prioritizes open access sources (Unpaywall, arXiv, CORE) before Sci-Hub. Sources: Unpaywall (OA), arXiv (OA), CORE (OA), Sci-Hub (last resort) Args: identifier: DOI, arXiv ID, or URL output_dir: Save directory (default: './downloads') Returns: Markdown with file path, metadata, source, or error message Examples: paper_download("10.1038/nature12373") # DOI paper_download("2301.00001") # arXiv ID paper_download("https://arxiv.org/abs/2301.00001") # URL
paper_batch_download	`Download multiple papers sequentially (1-50 max, 2s delay). Prioritizes open access sources (Unpaywall, arXiv, CORE) before Sci-Hub. Args: identifiers: List of DOIs, arXiv IDs, or URLs output_dir: Save directory (default: './downloads') Returns: Markdown summary with statistics, successes, and failures Examples: paper_batch_download(["10.1038/nature12373", "2301.00001"]) paper_batch_download(dois, "/papers")`
paper_metadata	`Get paper metadata without downloading (fast, <1s). Sources: Unpaywall, Crossref, arXiv APIs Returns: title, authors, year, journal, OA status, available sources Args: identifier: DOI, arXiv ID, or URL Returns: JSON with metadata fields Examples: paper_metadata("10.1038/nature12373") # DOI paper_metadata("2301.00001") # arXiv ID`

paper_download

Download academic paper by DOI, arXiv ID, or URL.

Prioritizes open access sources (Unpaywall, arXiv, CORE) before Sci-Hub.
Sources: Unpaywall (OA), arXiv (OA), CORE (OA), Sci-Hub (last resort)

Args:
    identifier: DOI, arXiv ID, or URL
    output_dir: Save directory (default: './downloads')

Returns:
    Markdown with file path, metadata, source, or error message

Examples:
    paper_download("10.1038/nature12373")  # DOI
    paper_download("2301.00001")  # arXiv ID
    paper_download("https://arxiv.org/abs/2301.00001")  # URL

paper_batch_download

Download multiple papers sequentially (1-50 max, 2s delay).

Prioritizes open access sources (Unpaywall, arXiv, CORE) before Sci-Hub.

Args:
    identifiers: List of DOIs, arXiv IDs, or URLs
    output_dir: Save directory (default: './downloads')

Returns:
    Markdown summary with statistics, successes, and failures

Examples:
    paper_batch_download(["10.1038/nature12373", "2301.00001"])
    paper_batch_download(dois, "/papers")

paper_metadata

Get paper metadata without downloading (fast, <1s).

Sources: Unpaywall, Crossref, arXiv APIs
Returns: title, authors, year, journal, OA status, available sources

Args:
    identifier: DOI, arXiv ID, or URL

Returns:
    JSON with metadata fields

Examples:
    paper_metadata("10.1038/nature12373")  # DOI
    paper_metadata("2301.00001")  # arXiv ID

Prompts

Interactive templates invoked by user choice

Name	Description
No prompts

Resources

Contextual data attached and managed by the client

Name	Description
No resources

Paper Download MCP Server

Server Configuration

Capabilities

Tools

Prompts

Resources

Latest Blog Posts

MCP directory API