paper-mcp
Search arXiv/Semantic Scholar/OpenAlex + medical evidence (PubMed/Europe PMC) + LaTeX/PDF tools
What you can do with it
Share of each task's required capabilities it coversPrefer a ready-made agent?
An MCP server is a connector for your own assistant. These finished products do the job for you: analyze financial documents.Similar tools
Listed for the same task: analyze financial documentsReviews
No review yet. Used paper-mcp? Be the first to help others choose.What it does
paper-mcp is an MCP server, a connector that lets an AI assistant use it as a tool. It is hosted: an assistant connects to it over the internet, nothing to install.
From the publisher's description, Electra Index matched it to one capability: document understanding. That makes it a candidate for tasks such as analyze financial documents or analyze patents.
Facts come from the Official MCP Registry, as declared by the publisher. Capabilities are matched automatically (low confidence). None of this is a test of the tool.
At a glance
How to connect
As declared in the Official MCP Registry · hosted endpoint tested by Electra Index 11h ago (live check)Hosted endpoint
https://latex-tools.online/mcpstreamable-http
In Claude Code: claude mcp add --transport http paper-mcp https://latex-tools.online/mcp
MCP settings (Claude Desktop, Cursor and other MCP clients)
{
"mcpServers": {
"paper-mcp": {
"url": "https://latex-tools.online/mcp"
}
}
}Live check
Electra Index connected to the hosted endpoint 11h agoONLINE paper-mcp answered an MCP connection on 17 Nov 2026 and introduced itself as paper-search 1.27.2 (MCP protocol 2025-06-18).
41 tools offered to AI assistants
search_papers· Search academic papers. Returns normalized hits with a short abstract preview; call get_paper for the full record.search_all· Aggregated search across arXiv, Semantic Scholar, OpenAlex and Yongleji at once. Fans out concurrently, de-duplicates the same work across corpora (by DOI or title) and re-ranks with Reciprocal Rank Fusion, so papers found by several sourcesearch_medical· Evidence-graded MEDICAL literature search (PubMed + Europe PMC). Unlike search_all (generic, ranks high-cited reviews/guidelines above trials), this filters by research type via PubMed Publication-Type tags and re-ranks by the evidence pyraget_paper· Fetch one paper by id, with full abstract and PDF link.search_by_author· Find papers by a specific author, newest first.list_recent· List the latest papers in a subject category, newest first.list_categories· List common subject category codes for filtering/recent.read_paper· Read a paper's full text. format='markdown' (default, body with formulas as $LaTeX$), 'html' (raw LaTeXML HTML), or 'latex' (the original LaTeX manuscript from the e-print source). arXiv only; id like 2401.01234.list_paper_sources· List available paper corpora.recognize_formula· Recognize a math formula from an image and return LaTeX. Provide image_url (downloaded server-side) OR image_base64. model: deepseek-ocr (default), paddleocr-vl, or texify. Returns {latex, model, elapsed_ms}.recognize_table· Recognize a table from an image and return LaTeX tabular code. Provide image_url OR image_base64. model: deepseek-ocr (default), paddleocr-vl, or texify. Returns {latex, model, elapsed_ms}.list_ocr_models· List the OCR models available for recognize_formula / recognize_table.
Show 29 more
lint_latex· Lint a LaTeX snippet: report errors and return an auto-fixed version. Input `code` (the LaTeX source). Returns {errors, fixed_code, summary_en, summary_zh, elapsed_ms}.extract_pdf· Extract a PDF to clean Markdown/LaTeX text via MinerU (great for papers behind no open-access full text — give the user's PDF and get readable text back). Provide pdf_url (downloaded server-side, SSRF-guarded) OR pdf_base64. formula/table textract_pdf_result· Fetch the result of an extract_pdf job by task_id. Returns {task_id, status, content, chars}: `content` is the extracted text once status='done'; while still 'running' content is null — call again shortly. Results expire server-side, so fetget_paper_citations· Semantic Scholar: papers that CITE this one (forward citation graph). id accepts S2 id / DOI: / ARXIV: / CorpusId:.get_paper_references· Semantic Scholar: papers this one REFERENCES (its bibliography). id accepts S2 id / DOI: / ARXIV: / CorpusId:.get_paper_authors· Semantic Scholar: the authors of a paper (with h-index, paper/citation counts).match_paper_title· Semantic Scholar: find the single paper whose title best matches the given text (exact-match lookup).autocomplete_papers· Semantic Scholar: autocomplete paper titles for a partial query (fast type-ahead).search_papers_bulk· Semantic Scholar: bulk paper search (up to 1000 hits, sortable e.g. 'citationCount:desc' or 'publicationDate:desc', with a continuation token). Filters: fields_of_study, year (e.g. '2020-2024'), venue, publication_types, open_access_pdf.get_papers_batch· Semantic Scholar: fetch many papers at once by id (S2/DOI:/ARXIV:/CorpusId:), up to ~500 per call.search_authors· Semantic Scholar: search for authors by name; returns profiles with h-index and paper/citation counts.get_author· Semantic Scholar: a single author's profile by id.get_author_papers· Semantic Scholar: all papers by a given author id, newest first.get_authors_batch· Semantic Scholar: fetch many authors at once by id.search_snippets· Semantic Scholar: search INSIDE paper full text and return matching text snippets (not just titles/abstracts).recommend_papers_for_paper· Semantic Scholar: recommend papers similar to one paper. pool='recent' (last open corpus) or 'all-cs' (all of CS). If the 'recent' pool yields nothing (common for older papers), it automatically retries the 'all-cs' pool.recommend_papers_from_examples· Semantic Scholar: recommend papers from positive (and optional negative) example paper ids.list_dataset_releases· Semantic Scholar Datasets: list all available release ids (dated snapshots of the full corpus).get_dataset_release· Semantic Scholar Datasets: which datasets a release contains (papers, abstracts, citations, embeddings, s2orc, tldrs…). release_id defaults to 'latest'.get_dataset_download_links· Semantic Scholar Datasets: get download links (presigned URLs) for one dataset in a release. Needs the API key.get_dataset_diffs· Semantic Scholar Datasets: incremental diff (added/updated/deleted) for a dataset between two releases. Needs the key.get_openalex_work· OpenAlex: fetch one work's full record (316M-work, all-field corpus). id accepts OpenAlex Wxxxx, a DOI, or an arXiv id.get_openalex_citations· OpenAlex: papers that CITE this work (forward citation graph), most-cited first.get_openalex_references· OpenAlex: the works this one REFERENCES (its bibliography).search_openalex_authors· OpenAlex: search authors; returns profiles with h-index, i10-index, works/citation counts and institutions.search_openalex_institutions· OpenAlex: search institutions (universities, labs) with ROR id, country, works/citation counts.search_openalex_works· OpenAlex: advanced filtered work search. Filters: from_year, to_year, is_oa (open access only), min_citations, institution_id. sort_by: relevance|newest|cited.get_openalex_trends· OpenAlex: publication-trend analytics for a query — counts grouped by year (default), or by 'institutions.id', 'authorships.author.id', 'open_access.is_oa', 'type', 'language'. Returns aggregate counts only (cheap, no rows).list_openalex_topics· OpenAlex: search the topic taxonomy (~4500 topics) to find the right subject term for filtering or recent-work queries.
What "online" means: the server answered an MCP connection at the time of the check. It is not a guarantee of security, quality or continuous uptime. How we test: we open an MCP session and ask for the tool list, as an AI assistant would. We never run a tool and never send a key. Checked every few days. Method
Is this your server? Monitoring Pro: a check every 30 minutes and an email within the hour when it stops answering. Launch offer: $39.99 once, for life.
Facts & evidence
Each fact shows where it was seen and when.| Fact | Value | Evidence | Source | Last confirmed |
|---|---|---|---|---|
| Hosted endpoint | https://latex-tools.online/mcp | DECLARED | SRC-001 Official MCP Registry | 1d ago |
| Local install (package) | no | DECLARED | SRC-001 Official MCP Registry | 1d ago |
| Remote access (hosted) | yes | DECLARED | SRC-001 Official MCP Registry | 1d ago |
| Website | https://latex-tools.online/mcp | DECLARED | SRC-001 Official MCP Registry | 1d ago |
| Repository | https://github.com/MCPServings/paper-mcp | DECLARED | SRC-001 Official MCP Registry | 1d ago |
| Registry status | active | DECLARED | SRC-001 Official MCP Registry | 1d ago |
| Version | 0.5.0 | DECLARED | SRC-001 Official MCP Registry | 1d ago |
| MCP server | yes | DECLARED | SRC-001 Official MCP Registry | 1d ago |
Change history
Is this page accurate?
Flag it and our robot re-checks the official source. Reports never change a score.Is paper-mcp still online?
Free alerts · no account▲ 0Do you run paper-mcp? Know when it stops answering
For publishers · optionalIts hosted endpoint can be monitored. Monitoring Pro connects every 30 minutes like an AI assistant, emails you within the hour when it stops answering, keeps a 90-day availability history and adds your answer rate to your badge.
Monitoring never changes a score or a rank.
Questions about paper-mcp
How do I connect paper-mcp?
Use the hosted endpoint https://latex-tools.online/mcp in your assistant's MCP settings. The exact settings are in "How to connect" above, as declared in the Official MCP Registry.
What tools does paper-mcp offer?
When Electra Index connected on 17 Nov 2026, it listed 41 tools: search_papers, search_all, search_medical, get_paper, search_by_author, list_recent, list_categories, read_paper and more. The full list is in "Live check" above.
Is paper-mcp online?
Yes. Its hosted endpoint answered an MCP connection from Electra Index 11h ago.
What can I use paper-mcp for?
Based on its description, it is most relevant to: analyze financial documents, analyze patents, answer questions from internal documents, extract data from PDFs.