Schema | paper-search-mcp

paper-search-mcp

Describes the environment variables required to run the server.

Name	Required	Description	Default
`S2_API_KEY`	No	Semantic Scholar API key
`PAPER_MCP_CACHE_DIR`	No	Override the on-disk cache directory for downloaded PDFs
`PAPER_MCP_USER_AGENT`	No	Custom user agent string
`PAPER_MCP_HTTP_TIMEOUT`	No	HTTP timeout in seconds	30

Features and capabilities supported by this server

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

Functions exposed to the LLM to take actions

Name	Description
search_semantic_scholarB	Search Semantic Scholar for papers and return normalized metadata sorted by citation count.
get_semantic_scholar_paperB	Fetch detailed metadata for a Semantic Scholar paper by paper ID.
search_arxivC	Search arXiv and return normalized metadata for matching papers.
get_arxiv_paperA	Fetch normalized metadata for a specific arXiv paper using an arXiv ID, abs URL, or PDF URL.
export_bibtexA	Export a paper as BibTeX using either a Semantic Scholar paper ID or an arXiv identifier/URL.
align_paper_by_titleA	Find exact title matches across Semantic Scholar and arXiv and return aligned cross-source pairs.
read_arxiv_paperB	Download an arXiv PDF, extract text from the first pages, and return a reading pack for analysis.
build_literature_digestB	Search across sources, deduplicate overlapping papers, and return a compact literature review digest.
download_arxiv_pdfB	Download an arXiv PDF to a specified absolute file or directory path.
download_semantic_scholar_pdfB	Download a Semantic Scholar PDF (Open Access or arXiv linked) to a specified absolute path.

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

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

curl -X GET 'https://glama.ai/api/mcp/v1/servers/xiaoxiaoxiaotao/paper-search-mcp'

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