io.github.cyanheads/chembl-mcp-server

Est-ce que io.github.cyanheads/chembl-mcp-server est sûr ?

Au dernier audit MCP Hub, le serveur MCP « io.github.cyanheads/chembl-mcp-server » 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 7 outils

• chembl_dataframe_describe≈ 778 tokens

  List the tables and columns staged on a canvas by chembl_get_bioactivities — inspect before calling chembl_dataframe_query to write correct SQL. Returns each table with its row count, kind (table | view), and column names + types. Requires CANVAS_PROVIDER_TYPE=duckdb.

  Paramètres, retour & exemple (1)

  Paramètres

  • canvas_id · string · requis
    Canvas ID returned by chembl_get_bioactivities — non-null whenever that call staged a table.

  Exemple d'appel

  {"name": "chembl_dataframe_describe", "arguments": {"canvas_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"error": {}, "tables": []}}

• chembl_dataframe_query≈ 999 tokens

  Run a read-only SQL SELECT over the bioactivity rows chembl_get_bioactivities staged on a canvas — rank, group, dedupe, and aggregate across the FULL set, not the inline preview. Reference each staged table by the name chembl_get_bioactivities returned — bioactivities for its potency_ranked view, bioactivities_null_potency for null_potency; discover the staged tables and their columns with chembl_dataframe_describe. Compute honest aggregates here (e.g. SELECT molecule_chembl_id, MEDIAN(pchembl_value) AS med FROM bioactivities WHERE standard_type = 'IC50' GROUP BY 1 ORDER BY 2 DESC). Two independent bounds apply, each reported on its own field: truncated is true when the SQL result exceeded the canvas row cap, and rendered_rows says how many of the returned rows the markdown table holds once its character budget is reached (below row_count on a wide or long result). Page past either bound with SQL LIMIT/OFFSET — append e.g. LIMIT 500 OFFSET 500 and re-call; offsets reach rows beyond the canvas row cap. Requires CANVAS_PROVIDER_TYPE=duckdb.

  Paramètres, retour & exemple (2)

  Paramètres

  • sql · string · requis
    A read-only SELECT against the staged tables. Reference tables by the names chembl_get_bioactivities returned.
  • canvas_id · string · requis
    Canvas ID returned by chembl_get_bioactivities — non-null whenever that call staged a table.

  Exemple d'appel

  {"name": "chembl_dataframe_query", "arguments": {"sql": "texte", "canvas_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"rows": [], "error": {}, "row_count": 1, "truncated": true, "rendered_rows": 1}}

• chembl_get_assay≈ 878 tokens

  Assay provenance behind a bioactivity row: description, type (binding / functional / ADMET / toxicity), the target it measures, organism, and ChEMBL's 1–9 confidence score (9 = direct assay on the protein target, lower = homologous or indirect). Supply assay_chembl_id from a chembl_get_bioactivities row. Call this to judge whether two measurements are comparable before ranking them together.

  Paramètres, retour & exemple (1)

  Paramètres

  • assay_chembl_id · string · requis
    ChEMBL assay ID from a bioactivity row's assay_chembl_id, e.g. "CHEMBL674637".

  Exemple d'appel

  {"name": "chembl_get_assay", "arguments": {"assay_chembl_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"error": {}, "organism": "texte", "assay_type": "texte", "description": "texte", "assay_chembl_id": "texte", "confidence_score": 1, "target_chembl_id": "texte", "assay_type_description": "texte", "confidence_description": "texte"}}

• chembl_get_bioactivities≈ 3732 tokens

  The flagship compound↔target bioactivity bridge: measurements for a molecule (target deconvolution / selectivity), a target (lead finding), or both together (how potently one compound hits one target). Supply at least one of molecule_chembl_id (from chembl_search_molecules) or target_chembl_id (from chembl_search_targets) — supplying both narrows to that compound–target pair, supplying neither is an error. Filter by standard_type (IC50/Ki/EC50/…), minimum potency pchembl_value_min, assay_type, and organism. Not every measurement has a derivable pchembl_value, so potency_view picks which side of that split you get: the default "potency_ranked" returns the measurements that have one, most potent first (ChEMBL sorts the rest first otherwise, which is why they are not merged), and "null_potency" returns exactly the measurements that have none. totalCount is the honest full match count across both views either way. Mixing measurement types (IC50 vs Ki) is a scientific error — set standard_type to compare like with like. A popular target carries tens of thousands of rows: results spill to a DataCanvas table (call chembl_dataframe_describe for its columns, then chembl_dataframe_query for honest aggregates across the staged set), while an inline preview answers the immediate question. Each view stages its own table (bioactivities / bioactivities_null_potency), so running both against one canvas_id lets a UNION ALL rebuild the full set. A canvas is minted only when a view spills; pass its canvas_id back and every later non-cursor call re-stages the table of its view with its own rows, even when they fit inline or none match, so a successful call never leaves rows from an earlier query in it, and a spill that fails or is cancelled leaves the earlier table in place. The spill is bounded by a row cap (CHEMBL_MAX_SPILL_ROWS) and a time budget (CHEMBL_SPILL_DEADLINE_MS); when either stops it short of the view, truncated is true, truncated_by names the bound, and the table is a bounded slice, not the complete view. The inline rows are always capped at limit, so compare that against totalCount before treating them as the whole answer. Spilling requires CANVAS_PROVIDER_TYPE=duckdb. Whenever a call stages nothing and rows remain past this page — the canvas is off, or the view fit inline with no canvas_id — nextCursor continues the view: pass it back as cursor, with the same filters and potency_view, for the next page. A cursor page is always returned inline and never staged, canvas or not.

  Paramètres, retour & exemple (10)

  Paramètres

  • limit · integer · optionnel
    Maximum rows in the inline preview or cursor page. Defaults to the server default (25). With the canvas enabled, a call without cursor still spills the full set to the canvas; when a call stages nothing, nextCursor reaches the rows past limit.
  • cursor · string · optionnel
    Opaque continuation token from a previous call's nextCursor — resumes the view where that page ended. Omit for the first page. Re-send the same molecule_chembl_id/target_chembl_id, filters, and potency_view that minted it (only limit may change; it sets this page's size); redeeming it against different filters walks a different result set. A cursor page is returned inline and never staged, even with the canvas enabled.
  • organism · string · optionnel
    Restrict to a target organism, e.g. "Homo sapiens" (case-insensitive exact match).
  • canvas_id · string · optionnel
    Optional canvas ID from a prior call to reuse the same canvas. With it, the call re-stages the selected potency_view's table with this call's rows whether they spill, fit inline, or are empty, so a second query of the SAME view REPLACES (overwrites) its prior rows once it succeeds — it does not append, and a spill that fails or is cancelled leaves them — while the other view's table is left intact, which is what lets both coexist on one canvas. Omit it and a fresh canvas is minted only if the view spills. Left untouched on a cursor page, which never stages.
  • assay_type · string · optionnel
    Restrict to an assay type code: "B" (binding), "F" (functional), "A" (ADMET), "T" (toxicity).
  • potency_view · string · optionnel · potency_ranked | null_potency
    Which side of the pchembl_value presence split to retrieve. "potency_ranked" (default) returns the measurements that have a derivable pchembl_value, most potent first. "null_potency" returns exactly the measurements that have none — the rows the ranked view excludes, otherwise unreachable. The two partition the match set and stage to separate canvas tables.
  • standard_type · string · optionnel
    Restrict to one measurement type, e.g. "IC50", "Ki", "EC50". Set this to compare potencies validly.
  • target_chembl_id · string · optionnel
    ChEMBL target ID (from chembl_search_targets), e.g. "CHEMBL203". Supply this, molecule_chembl_id, or both — both narrows to that compound–target pair.
  • pchembl_value_min · number · optionnel
    Minimum pchembl_value (−log10 molar potency), e.g. 7 keeps sub-100 nM activities. Only valid on the potency_ranked view — the null_potency rows have no pchembl_value to compare against.
  • molecule_chembl_id · string · optionnel
    ChEMBL molecule ID (from chembl_search_molecules), e.g. "CHEMBL941". Supply this, target_chembl_id, or both — both narrows to that compound–target pair.

  Exemple d'appel

  {"name": "chembl_get_bioactivities", "arguments": {"limit": 1, "cursor": "texte", "organism": "texte", "canvas_id": "texte", "assay_type": "texte", "potency_view": "potency_ranked"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"error": {}, "notice": "texte", "spilled": true, "canvas_id": "texte", "truncated": true, "activities": [], "nextCursor": "texte", "table_name": "texte", "totalCount": 1, "potency_view": "potency_ranked", "truncated_by": "texte", "appliedFilters": {}}}

• chembl_get_drug_info≈ 1745 tokens

  Pharmacology for a drug (molecule): mechanism(s) of action, the molecular target(s) it acts on, action type (inhibitor / agonist / …), first-approval year, and clinical indications with the max phase reached for each. Supply molecule_chembl_id (from chembl_search_molecules). Distinct from the openfda server's label/adverse-event view — this is the curated mechanism-and-indication record. A mechanism's target_chembl_id chains into chembl_get_bioactivities for compounds hitting the same target. Each list carries its own retrieval state: an empty mechanisms or indications array means the molecule has none recorded only when the matching mechanisms_status / indications_status is "complete" — "failed" means the upstream request was rejected and the array says nothing about the molecule, and "truncated" means the page cap bounded the list at fewer rows than the matching *_total_count.

  Paramètres, retour & exemple (1)

  Paramètres

  • molecule_chembl_id · string · requis
    ChEMBL molecule ID (from chembl_search_molecules), e.g. "CHEMBL939" for gefitinib.

  Exemple d'appel

  {"name": "chembl_get_drug_info", "arguments": {"molecule_chembl_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"error": {}, "notice": "texte", "max_phase": 1, "pref_name": "texte", "mechanisms": [], "indications": [], "first_approval": 1, "mechanisms_status": "complete", "indications_status": "complete", "molecule_chembl_id": "texte", "mechanisms_total_count": 1, "indications_total_count": 1}}

• chembl_search_molecules≈ 1731 tokens

  Discovery entry point for compounds. Find by name / ChEMBL ID / InChIKey with the default search_type=name (supply query), or run a structure search with search_type exact | similarity | substructure (supply structure as a SMILES). At least one of query or structure is required, and structure is required for the three structure modes. Returns ChEMBL ID, preferred name, canonical SMILES, formula, MW, AlogP, Lipinski violations, QED, and max clinical phase on every row; only search_type=similarity adds a Tanimoto similarity percent. Chain molecule_chembl_id into chembl_get_bioactivities or chembl_get_drug_info. A capped result carries nextCursor — pass it back as cursor with the same filters to read the next page.

  Paramètres, retour & exemple (7)

  Paramètres

  • limit · integer · optionnel
    Maximum molecules to return. Defaults to the server default (25) when omitted.
  • query · string · optionnel
    Search text for search_type=name — a drug name, ChEMBL ID, or InChIKey, e.g. "imatinib" or "CHEMBL25".
  • cursor · string · optionnel
    Opaque continuation token from a previous call's nextCursor — resumes where that page ended. Omit for the first page. Re-send the same query/structure/filters that minted it (only limit may change; it sets this page's size); redeeming it against different filters walks a different result set.
  • structure · string · optionnel
    SMILES string for structure search, e.g. "CC(=O)Oc1ccccc1C(=O)O". Required when search_type is exact/similarity/substructure.
  • search_type · string · optionnel · name | exact | similarity | substructure
    name = text lookup (query); exact = exact structure match; similarity = Tanimoto ≥ threshold; substructure = contains the structure. All structure modes need `structure`.
  • max_phase_min · integer · optionnel
    For search_type=name, restrict to compounds at or above this max clinical phase (e.g. 4 for marketed drugs only).
  • similarity_threshold · integer · optionnel
    Minimum Tanimoto similarity percent for search_type=similarity (40–100; ChEMBL rejects below 40). Ignored for other modes.

  Exemple d'appel

  {"name": "chembl_search_molecules", "arguments": {"limit": 1, "query": "texte", "cursor": "texte", "structure": "texte", "search_type": "name", "max_phase_min": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"cap": 1, "error": {}, "shown": 1, "notice": "texte", "molecules": [], "truncated": true, "nextCursor": "texte", "totalCount": 1}}

• chembl_search_targets≈ 1460 tokens

  Resolve a protein/gene/UniProt accession to the ChEMBL target ID that chembl_get_bioactivities needs for the target→leads workflow. Supply at least one of accession (UniProt, e.g. P00533), gene_symbol (e.g. EGFR), or query (free-text name); filter further by organism and target_type. Returns each target with its type, organism, and component UniProt accessions + gene symbols. A UniProt accession from the uniprot/protein server is the most precise input. A capped result carries nextCursor — pass it back as cursor with the same filters to read the next page.

  Paramètres, retour & exemple (7)

  Paramètres

  • limit · integer · optionnel
    Maximum targets to return. Defaults to the server default (25) when omitted.
  • query · string · optionnel
    Free-text name match against the target preferred name, e.g. "kinase" or "growth factor receptor".
  • cursor · string · optionnel
    Opaque continuation token from a previous call's nextCursor — resumes where that page ended. Omit for the first page. Re-send the same accession/gene_symbol/query/filters that minted it (only limit may change; it sets this page's size); redeeming it against different filters walks a different result set.
  • organism · string · optionnel
    Restrict to a source organism, e.g. "Homo sapiens" (case-insensitive exact match).
  • accession · string · optionnel
    UniProt accession of a target component, e.g. "P00533". The most precise resolver — from the uniprot/protein server.
  • gene_symbol · string · optionnel
    Gene symbol of a target component, e.g. "EGFR" (case-insensitive exact match).
  • target_type · string · optionnel
    Restrict to a target class, e.g. "SINGLE PROTEIN" or "PROTEIN COMPLEX".

  Exemple d'appel

  {"name": "chembl_search_targets", "arguments": {"limit": 1, "query": "texte", "cursor": "texte", "organism": "texte", "accession": "texte", "gene_symbol": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"cap": 1, "error": {}, "shown": 1, "notice": "texte", "targets": [], "truncated": true, "nextCursor": "texte", "totalCount": 1}}

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://chembl.caseyjhand.com/mcp