arxiv_read_paper
ActiveTool of arxiv-mcp-server
declared in 1.2.15
Fetch the full text of an arXiv paper as HTML. Tries arxiv.org/html first; falls back to ar5iv.labs.arxiv.org when the native render is unavailable. PDF-only papers (no HTML render on either source) return an html_unavailable error with the pdf_url for direct download. Page through long papers with the start and max_characters parameters.
Parameters schema
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"paper_id"
],
"properties": {
"start": {
"type": "integer",
"default": 0,
"maximum": 9007199254740991,
"minimum": 0,
"description": "Character offset into the cleaned body to begin reading from. Defaults to 0. Use with max_characters to page through long papers — e.g., start=100000 with max_characters=100000 returns chars 100,000–199,999. The total length is reported as body_characters in the response."
},
"paper_id": {
"type": "string",
"minLength": 1,
"description": "arXiv paper ID (e.g., \"2401.12345\" or \"2401.12345v2\")."
},
"max_characters": {
"type": "integer",
"default": 100000,
"maximum": 9007199254740991,
"minimum": 1,
"description": "Maximum characters of paper body content to return. Defaults to 100,000. HTML head/boilerplate is stripped before counting. When truncated, a notice and total character count are included."
}
}
}Parent server
arxiv-mcp-server
https://github.com/cyanheads/arxiv-mcp-server
2/7 registries