Skip to main content
Glama

Unpaywall MCP Server

unpaywall_fetch_pdf_text

Extract text content from open access research papers using DOI or PDF URL to enable analysis of academic literature.

Instructions

Download and extract text from best OA PDF for a DOI, or from a provided PDF URL.

Input Schema

NameRequiredDescriptionDefault
doiNoDOI string or DOI URL. Used if pdf_url is not provided.
emailNoEmail to identify requests to Unpaywall (required when resolving via DOI).
pdf_urlNoDirect PDF URL to download and parse (takes precedence over DOI).
truncate_charsNoMax characters of extracted text to return (default 20000).

Input Schema (JSON Schema)

{ "additionalProperties": false, "properties": { "doi": { "description": "DOI string or DOI URL. Used if pdf_url is not provided.", "type": "string" }, "email": { "description": "Email to identify requests to Unpaywall (required when resolving via DOI).", "type": "string" }, "pdf_url": { "description": "Direct PDF URL to download and parse (takes precedence over DOI).", "type": "string" }, "truncate_chars": { "description": "Max characters of extracted text to return (default 20000).", "minimum": 1000, "type": "integer" } }, "required": [], "type": "object" }

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/ElliotPadfield/unpaywall-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server