io.github.thaohienhomes/pho-research-tools

Est-ce que io.github.thaohienhomes/pho-research-tools est sûr ?

Au dernier audit MCP Hub, le serveur MCP « io.github.thaohienhomes/pho-research-tools » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Les 9 outils

• check_retractions≈ 600 tokens

  Check DOIs for retractions, expressions of concern and corrections, using Crossref (which includes Retraction Watch data). Status per DOI: retracted, concern, corrected, other_notice, no_notice (nothing on record), not_in_crossref, invalid_doi, rate_limited or lookup_failed (the DOI could not be checked, which is not a clean result). Works for a single paper or a whole reference list. verify_references already includes this check, so use this tool for DOIs that have not just been through verify_references. A DOI the same caller checked in the last hour is answered again at no cost to the allowance.

  Paramètres, retour & exemple (1)

  Paramètres

  • dois · array · requis
    DOIs, bare (10.1000/xyz) or as https://doi.org/ links.

  Exemple d'appel

  {"name": "check_retractions", "arguments": {"dois": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"quota": {}, "counts": {}, "results": []}}

• find_datasets≈ 1514 tokens

  Find open scientific datasets (and optionally models) that fit a research question, check their licences, verify the source papers (DOI, retractions, corrections), and return a citable Research Data Brief with a public share link. Searches DataCite (Zenodo, Figshare, Dryad and other data repositories), the Hugging Face Hub boosted by the Hugging Science curated index, and, for life-science questions, NCBI GEO, CZ CELLxGENE Discover (curated single-cell data) and the CZ CryoET Data Portal (cryo-electron tomography). Each result has a match level, a plain-language licence verdict, the source paper and whether it checks out, a citation for the data, and a line of code to load it. Every identifier comes from the repositories' own metadata; nothing is generated. The `why` field lists the facts behind the match: explain the fit to the user in your own words from those facts, and say plainly when the brief is empty. Pass `keywords` with English search words when the question is long or not in English. Licence verdicts come from repository metadata and are not legal advice.

  Paramètres, retour & exemple (7)

  Paramètres

  • domain · string · optionnel · genomics | biology | medicine | chemistry | physics | earth_science | materials | engineering
    Field of the question. Life-science domains also search NCBI GEO.
  • keywords · string · optionnel
    English search keywords (e.g. "triple negative breast cancer RNA-seq"). Recommended.
  • question · string · requis
    The research question in natural language (e.g. "gene expression in triple-negative breast cancer").
  • max_results · integer · optionnel
    Number of results, 1–5.
  • intended_use · string · optionnel · thesis | publication | commercial | teaching
    What the data is for. `commercial` demotes anything its licence does not clear for commercial use.
  • citation_style · string · optionnel · apa | mla | chicago | harvard | vancouver | ieee | ama
    Style for the ready-made citations.
  • include_models · boolean · optionnel
    Also look for pretrained models on Hugging Face.

  Exemple d'appel

  {"name": "find_datasets", "arguments": {"question": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"quota": {}, "stats": {}, "title": "texte", "results": [], "question": "texte", "warnings": [], "share_url": "texte", "takeaways": [], "suggestions": [], "intended_use": "thesis", "search_terms": []}}

• find_evidence≈ 1006 tokens

  Find the strongest published evidence for and against a scientific or medical claim. Searches PubMed (including a pass limited to guidelines, meta-analyses, systematic reviews and randomized trials) and OpenAlex, and returns real papers, each with a PMID or DOI, ordered by level of evidence: guideline, meta-analysis, systematic review, RCT, other trial, observational study, narrative review, case report, then study protocols that have not reported results yet. Each paper comes with the conclusion copied verbatim from its abstract, so you can judge for yourself whether it supports the claim, contradicts it, or does not address it, and quote the sentence you rely on. The tool does not judge stance and does not summarise: count a paper as support or contradiction only when its conclusion says so. Pass `query` with English search keywords when the claim is long or not in English. Retracted papers and correction notices are left out. Preprints are included and marked (not peer reviewed).

  Paramètres, retour & exemple (6)

  Paramètres

  • claim · string · requis
    The claim to check, as a sentence (e.g. "Drinking coffee reduces the risk of type 2 diabetes").
  • query · string · optionnel
    English search keywords for the claim (e.g. "coffee consumption type 2 diabetes risk"). Recommended.
  • year_to · integer · optionnel
    Latest publication year, inclusive.
  • year_from · integer · optionnel
    Earliest publication year, inclusive.
  • max_results · integer · optionnel
    Number of papers, 1–25.
  • include_preprints · boolean · optionnel
    Keep preprints (marked as not peer reviewed).

  Exemple d'appel

  {"name": "find_evidence", "arguments": {"claim": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"claim": "texte", "query": "texte", "papers": [], "status": "ok", "by_level": {}, "excluded": {}, "warnings": [], "without_abstract": 1}}

• find_tools≈ 1542 tokens

  Find research software for a task from the bio.tools registry (ELIXIR), check each tool's licence, verify the paper behind it (DOI, retractions, corrections), label whether it is still maintained, and give the install line. Describe the task (e.g. "cluster single-cell RNA-seq data") and optionally the file format the data is in (e.g. H5AD, FASTQ, VCF); tools that list that format as an input are favoured. Each result has a match level, a plain-language licence verdict, the paper and whether it checks out, a maintenance label (active, idle, stale, archived) read from the linked GitHub repository, and an install line built from a PyPI, Bioconda, Bioconductor, CRAN or GitHub link the registry lists. Every identifier and command comes from the registry's own records; nothing is generated. The `why` field lists the facts behind the match: explain the fit in your own words from those facts, and say plainly when no tool matched. Pass `keywords` with English words when the task is long or not in English. Licence verdicts come from registry and repository metadata and are not legal advice.

  Paramètres, retour & exemple (6)

  Paramètres

  • keywords · string · optionnel
    English search keywords (e.g. "single-cell clustering"). Recommended.
  • question · string · requis
    The task in natural language (e.g. "cluster single-cell RNA-seq data").
  • max_results · integer · optionnel
    Number of results, 1–5.
  • input_format · string · optionnel
    The file format the data is in (e.g. "H5AD", "FASTQ", "VCF"). Tools that read it are favoured.
  • intended_use · string · optionnel · thesis | publication | commercial | teaching
    What the software is for. `commercial` demotes anything its licence does not clear.
  • citation_style · string · optionnel · apa | mla | chicago | harvard | vancouver | ieee | ama
    Style for the ready-made paper citations.

  Exemple d'appel

  {"name": "find_tools", "arguments": {"question": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"quota": {}, "stats": {}, "results": [], "question": "texte", "warnings": [], "data_note": "texte", "takeaways": [], "suggestions": [], "input_format": "texte", "intended_use": "thesis", "search_terms": []}}

• format_citations≈ 781 tokens

  Format references in a citation style (APA 7, MLA 9, Chicago author-date, Harvard, Vancouver, IEEE, AMA) or export them as BibTeX, RIS or CSL-JSON. By default every reference is first verified against Crossref, PubMed and OpenAlex, and verified references are formatted from the database record, so wrong years, pages or author names in the input are corrected. References that could not be verified are formatted exactly as written and flagged in `entries[].warnings`. Returns the bibliography and, for text and html output, the matching in-text citation for each reference.

  Paramètres, retour & exemple (4)

  Paramètres

  • style · string · optionnel · apa | mla | chicago | harvard | vancouver | ieee | ama
    Citation style: apa (APA 7), mla (MLA 9), chicago (Chicago author-date), harvard (Harvard), vancouver (Vancouver), ieee (IEEE), ama (AMA). Ignored for bibtex/ris/csl-json output.
  • output · string · optionnel · text | html | bibtex | ris | csl-json
    text (plain bibliography), html, bibtex, ris or csl-json.
  • verify · boolean · optionnel
    Verify each reference before formatting (recommended). When false, references are formatted exactly as given, without corrections.
  • references · string · requis
    References in any form: a pasted list in any style, BibTeX, RIS, CSL-JSON, or DOIs one per line.

  Exemple d'appel

  {"name": "format_citations", "arguments": {"references": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"quota": {}, "style": "texte", "output": "texte", "content": "texte", "entries": [], "warnings": [], "style_title": "texte"}}

• prisma_flow_diagram≈ 1578 tokens

  Draw a PRISMA 2020 flow diagram for a new systematic review from the record counts, as a PNG image plus an SVG and download links. Give the counts you have; screened, sought, assessed and reports-included boxes that follow from others are filled in and marked as derived. Studies included is never derived. The tool checks that the numbers add up (records identified minus removed equals screened, and so on) and returns a warning naming each box that does not, with the value it should have. The diagram always shows the numbers exactly as given. Add `otherMethods` counts to draw the second column (websites, organisations, citation searching).

  Paramètres, retour & exemple (3)

  Paramètres

  • counts · object · requis
  • footnotes · boolean · optionnel
    Print the template footnotes and source attribution.
  • other_methods_column · boolean · optionnel
    Force the other-methods column on or off. Default: drawn when otherMethods counts are given.

  Exemple d'appel

  {"name": "prisma_flow_diagram", "arguments": {"counts": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"svg": "texte", "width": 1, "counts": {}, "height": 1, "svg_url": "texte", "warnings": [], "image_url": "texte"}}

• screening_log≈ 1276 tokens

  Turn the screening decisions of a systematic review into its PRISMA 2020 counts, flow diagram and screening log. Give one row per record: its title/abstract decision (include or exclude), its full-text decision for records that passed (include, exclude or not_retrieved), and the reason for each exclusion. Every box from "records screened" down is counted from the rows, so the diagram always matches the decisions; full-text exclusions are grouped by reason. Returns the diagram (PNG, SVG, links), the counts, a CSV of every decision for the review appendix, and the problems a reviewer would catch: full-text exclusions without a reason, records still waiting for a full-text decision, and duplicate ids. Add the identification counts (records from databases, duplicates removed) to complete the top of the diagram. At most 5000 records per call.

  Paramètres, retour & exemple (3)

  Paramètres

  • records · array · requis
  • footnotes · boolean · optionnel
    Print the template footnotes and source attribution.
  • identification · object · optionnel
    Counts before screening, for the top of the diagram.

  Exemple d'appel

  {"name": "screening_log", "arguments": {"records": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"svg": "texte", "width": 1, "counts": {}, "height": 1, "svg_url": "texte", "warnings": [], "image_url": "texte", "screening": {}}}

• search_papers≈ 872 tokens

  Search PubMed and OpenAlex for real papers. Every result carries a DOI or PubMed ID that resolves, so nothing returned can be fabricated. Finds sources for a claim or a topic. Filters: publication year range, open-access only, study types, and the number of results. Retracted papers are left out by default. Preprints are included and marked `preprint: true` (not peer reviewed). Results are ranked by the databases' relevance, alternating between the two sources.

  Paramètres, retour & exemple (7)

  Paramètres

  • query · string · requis
    What to look for, in English keywords (e.g. "sepsis early antibiotics mortality").
  • year_to · integer · optionnel
    Latest publication year, inclusive.
  • year_from · integer · optionnel
    Earliest publication year, inclusive.
  • max_results · integer · optionnel
    Number of results, 1–50.
  • study_types · array · optionnel
    Study designs. Known ids use database filters: rct, clinical-trial, systematic-review, meta-analysis, review, guideline, cohort, case-control, case-report, observational. Any other text is added as keywords.
  • open_access_only · boolean · optionnel
    Only papers with a free, legal full text.
  • include_retracted · boolean · optionnel
    Keep retracted papers (flagged) instead of leaving them out.

  Exemple d'appel

  {"name": "search_papers", "arguments": {"query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"query": "texte", "status": "ok", "results": [], "excluded": {}, "warnings": []}}

• verify_references≈ 1100 tokens

  Check every reference in a list against Crossref, PubMed and OpenAlex and report, for each one, whether the paper really exists and whether the details are right. Works on lists written by a person or generated by an AI model. Input: a pasted reference list in any common style (APA, Vancouver, numbered, mixed), BibTeX, RIS, CSL-JSON, or one DOI per line. Each reference gets exactly one status: verified, verified_with_corrections (real paper, some details wrong; corrected metadata included), likely_fabricated (no such paper exists), not_found (could not be confirmed either way), retracted, or ambiguous (several papers fit). likely_fabricated, not_found and ambiguous mean the reference could not be confirmed as a real paper; retracted means the paper exists but has been withdrawn. Retractions, expressions of concern and corrections are already checked here, so there is no need to call check_retractions on the same references afterwards. At most 50 references per call.

  Paramètres, retour & exemple (1)

  Paramètres

  • references · string · requis
    The reference list exactly as written: any citation style, BibTeX, RIS, CSL-JSON, or DOIs one per line.

  Exemple d'appel

  {"name": "verify_references", "arguments": {"references": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"quota": {}, "summary": {}, "references": []}}

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

https://mcp.pho.chat/mcp