Paper Search MCP is a Python tool and Model Context Protocol server for finding, downloading, and extracting text from academic papers across multiple sources. Researchers and AI-driven workflows use it through MCP clients or its command-line interface, with open sources prioritized and optional API keys supported. The catalogue skill provides a way to use the project from a coding-agent workflow.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add openags/paper-search-mcp --skill paper-searchgit clone --depth 1 https://github.com/openags/paper-search-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/openags/paper-search-mcp/paper-search)<a href="https://agentmods.dev/skills/openags/paper-search-mcp/paper-search"><img src="https://agentmods.dev/badge/skills/openags/paper-search-mcp/paper-search/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/openags/paper-search-mcp/paper-search"><img src="https://agentmods.dev/badge/skills/openags/paper-search-mcp/paper-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00078 | $0.00760 |
| Opus 5.5 | $0.00031 | $0.00304 |
| Sonnet 5.5 | $0.00016 | $0.00152 |
| Haiku 4.5 | $0.00008 | $0.00076 |
Grade A, and why
paper-search scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 13d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- paper-search — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paper Search
Academic paper discovery and retrieval in this harness runs through the mcp__paper-search__* tools (the paper-search-mcp MCP server). Do not run the paper-search CLI or hand-write API requests — use these tools.
Core tools
mcp__paper-search__search_papers— multi-source concurrent search with deduplication and DOI backfill. Prefer it for broad queries; one call covers many sources at once.mcp__paper-search__download_with_fallback— OA-first PDF download with a source-native → repository → Unpaywall fallback chain.mcp__paper-search__search_unpaywall— DOI-centric open-access metadata lookup.
Source-specific tools
Per source the pattern is search_<source> / download_<source> / read_<source>_paper, with availability varying by source. Sources: arxiv, pubmed, biorxiv, medrxiv, iacr, semantic, crossref, openalex, pmc, core, europepmc, dblp, openaire, citeseerx, doaj, base, zenodo, hal, ssrn, openreview, google_scholar. ACM search is available without an API key. IEEE tools require PAPER_SEARCH_MCP_IEEE_API_KEY. Discover the current tool list rather than assuming every source supports full text.
Web of Science (search_wos) and Scopus (search_scopus, read_scopus_paper)
require runtime keys and explicit source selection; default/all searches never
include them. Scopus full-text retrieval requires explicit full_text=true;
respect its full_text, abstract_only, or unavailable status. Do not describe
an abstract or metadata record as retrieved full text.
get_citing_papers and get_referenced_papers provide bounded one-hop OpenAlex
lookups from a DOI or OpenAlex ID. Search caching is disabled by default; enabling
it persists queries and public results and is an operator choice. Use
get_search_cache_status to inspect it and clear_search_cache only when the
user asks to remove cached results. Clearing does not remove downloaded PDFs.
For speed, prefer a targeted set (search_arxiv, search_semantic, search_crossref) over multi-source search when the field is clear.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 13d ago First seen · 45 lines · 78 tokens per session scan A 43187b1de970
paper-search is a skill published in the GitHub repository openags/paper-search-mcp (2,839 stars, last pushed 14d ago), licensed MIT. It adds 78 tokens to every session and 760 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-03.
Other skills, from other repositories
imaging-data-commons
Queries and downloads public cancer imaging data from NCI Imaging Data Commons. Supports IDC collection discovery, DICOM access, radiology (CT, MR, PET) and pathology AI datasets, metadata SQL, visualization, licensing, and citations. Uses public metadata and download routes without authentication; optional BigQuery…
lab-hardware-cad
Designs custom laboratory hardware as parametric build123d models and exports fabrication artifacts as STEP, STL, and DXF files - microfluidic chips and molds, optomechanical mounts and breadboard adapters, cuvette and microplate holders, tube racks, animal-behavior rigs, and 3D-printed instrument fixtures. Use when a…
neuropixels-analysis
Analyzes Neuropixels extracellular recordings end-to-end with SpikeInterface. Covers loading SpikeGLX/Open Ephys/NWB data, preprocessing, drift/motion correction, Kilosort4 (and CPU) spike sorting, quality metrics, and unit curation (threshold-based, model-based UnitRefine, and AI-assisted visual review). Use when…
onekgpd
Queries the 1000 Genomes Project dataset (3,202 whole-genome-sequenced individuals, GRCh38) at the level of individual participants. Use when a question is about individuals or variants in the 1000 Genomes Project cohort: which individuals carry variants matching specific criteria in a gene or region, which…
statistical-analysis
Guided statistical analysis for research data - test selection, assumption checking, effect sizes, power analysis, Bayesian alternatives, and APA-formatted reporting. Use whenever a user wants to compare groups, test a hypothesis, analyze experimental or survey data, check statistical assumptions, compute required…
biopython
Provides Biopython workflows for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Supports batch processing, custom molecular-biology pipelines, BLAST automation, structure analysis, and motif analysis.