"Affinity Designer" matching MCP tools:

• sti_searchA

  Stimulsoft Documentation MCP ServerA

  Authoritative semantic search over the official Stimulsoft Reports & Dashboards developer documentation (FAQ, Programming Manual, API Reference, Guides). Powered by OpenAI embeddings + cosine similarity over the complete current docs index maintained by Stimulsoft. Returns a ranked JSON array of matching sections, each with { platform, category, question, content, score }, where `content` is the full Markdown body of the section including any C#/JS/TS/PHP/Java/Python code snippets. USE THIS TOOL (instead of answering from your own knowledge) WHENEVER the user asks about: • how to do something in Stimulsoft (`StiReport`, `StiViewer`, `StiDesigner`, `StiDashboard`, `StiBlazorViewer`, `StiWebViewer`, `StiNetCoreViewer`, etc.); • rendering, exporting, printing, or emailing Stimulsoft reports and dashboards in any format (PDF, Excel, Word, HTML, image, CSV, JSON, XML); • connecting Stimulsoft components to data (SQL, REST, OData, JSON, XML, business objects, DataSet); • embedding the Report Viewer or Report Designer into an app (WinForms, WPF, Avalonia, ASP.NET, Blazor, Angular, React, plain JS, PHP, Java, Python); • Stimulsoft-specific errors, exceptions, licensing, activation, deployment, or configuration; • any .mrt / .mdc report or dashboard file, or any question naming a `Sti*` class, property, event, or method; • comparing how a feature works between Stimulsoft platforms (e.g. "WinForms vs Blazor viewer options"). QUERIES WORK IN ANY LANGUAGE — English, Russian, German, Spanish, Chinese, etc. Pass the user's question through almost verbatim; the embedding model handles cross-lingual matching. Do NOT translate queries yourself. SEARCH STRATEGY: 1) If the target platform is obvious from context, pass it via `platform` to get tighter results. 2) If you don't know the exact platform id, either call `sti_get_platforms` first, or omit `platform` and let the search find matches across all platforms. 3) If the first search returns low scores (<0.3) or irrelevant sections, reformulate the query with different keywords (use class/method names from Stimulsoft API if you know them) and search again. 4) Prefer multiple focused searches over one broad search. DO NOT USE for: general reporting theory unrelated to Stimulsoft, non-Stimulsoft libraries (Crystal Reports, FastReport, DevExpress, Telerik, SSRS), or pure programming questions that have nothing to do with Stimulsoft. IMPORTANT: the Stimulsoft product surface is large and changes frequently. Your training data is almost certainly out of date. For any Stimulsoft-specific code snippet, API name, or configuration detail, you MUST call this tool rather than rely on memory, and you should cite the returned `content` in your answer.

  ConnectorNo auth

• quizbase_randomA

  QuizBaseA

  Fetch N random trivia questions matching filters. Quality-first: by default excludes questions flagged for review (use quality='all' to include for audit/research). USE WHEN: building a quiz, sampling content for warmup, generating practice sets. NOT WHEN: you need a specific question ID (use quizbase_question_by_id) or want to explore a topic deeply with facets (use quizbase_topic_by_slug). KEY FILTERS: - amount: 1-50, default 10. - lang: ISO 639-1. Default "en". Supported: en, pl. Strict — unknown language returns 400. - category (slug): e.g. geography, history, science-and-nature. Full list via quizbase_categories. - difficulty: trivial | easy | medium | hard | expert. LLM-calibrated. Records not yet LLM-rated hold the importer placeholder (mostly "medium" for factoid sources). - type: multiple | boolean (default both; no text_input in random). - regions (cultural affinity, AND): empty in data = no cultural advantage assumed. Lowercase ISO 3166-1 alpha-2 ('us', 'pl', 'gb') + cultural codes ('jewish', 'christian-catholic', 'islam'). Filter for content statistically more likely known by residents/members. Discover via quizbase_regions. - source (array): include only these source databases (one or more of 12: opentdb, opentriviaqa, kqa-pro, entityq, mintaka, mkqa, nq-open, creak, qasc, arc, webq, quizbase). - exclude_source (array): drop these sources, e.g. ["entityq"] for human-curated only. Applied after source. - license (SPDX): CC-BY-SA-4.0 | CC-BY-SA-3.0 | MIT | etc. Restrict to redistribution-friendly content. - topic (curated slug): higher precision than tags. Alias resolver matches subcategories+tags. List via quizbase_topics. - topics_any: OR over curated topics, max 10. - tags (AND), tags_any (OR), subcategory: raw taxonomy. Use topic if available. - quality: 'high' (default, recommended) = cleanest, most broadly-useful. 'standard' = broader pool incl. niche/too-specific (more volume). 'all' = audit/research, includes flagged — when 'all', each question gains a "quality" field ('high' or 'needs_review'). - exclude (UUIDs, max 250): de-dupe within a quiz session. OUTPUT: { questions: [...], meta: { count, language } }. Each question carries full per-record attribution (source, author, license, licenseVersion, licenseUrl, sourceId, url, modifications, lastModified) — identical shape to REST /api/v1/questions/random. ATTRIBUTION REQUIRED if you redistribute. CC-BY-SA modifications must be credited per § 3(a)(1)(B) using each question's own attribution object. COMMON MISTAKES: forcing lang='pl' for a global audience (use 'en' default); skipping quality (default already excludes flagged content — only pass quality='all' for audit); using tags when a curated topic exists (worse precision).

  ConnectorNo auth

• sti_searchA

  docsA

  Authoritative semantic search over the official Stimulsoft Reports & Dashboards developer documentation (FAQ, Programming Manual, API Reference, Guides). Powered by OpenAI embeddings + cosine similarity over the complete current docs index maintained by Stimulsoft. Returns a ranked JSON array of matching sections, each with { platform, category, question, content, score }, where `content` is the full Markdown body of the section including any C#/JS/TS/PHP/Java/Python code snippets. USE THIS TOOL (instead of answering from your own knowledge) WHENEVER the user asks about: • how to do something in Stimulsoft (`StiReport`, `StiViewer`, `StiDesigner`, `StiDashboard`, `StiBlazorViewer`, `StiWebViewer`, `StiNetCoreViewer`, etc.); • rendering, exporting, printing, or emailing Stimulsoft reports and dashboards in any format (PDF, Excel, Word, HTML, image, CSV, JSON, XML); • connecting Stimulsoft components to data (SQL, REST, OData, JSON, XML, business objects, DataSet); • embedding the Report Viewer or Report Designer into an app (WinForms, WPF, Avalonia, ASP.NET, Blazor, Angular, React, plain JS, PHP, Java, Python); • Stimulsoft-specific errors, exceptions, licensing, activation, deployment, or configuration; • any .mrt / .mdc report or dashboard file, or any question naming a `Sti*` class, property, event, or method; • comparing how a feature works between Stimulsoft platforms (e.g. "WinForms vs Blazor viewer options"). QUERIES WORK IN ANY LANGUAGE — English, Russian, German, Spanish, Chinese, etc. Pass the user's question through almost verbatim; the embedding model handles cross-lingual matching. Do NOT translate queries yourself. SEARCH STRATEGY: 1) If the target platform is obvious from context, pass it via `platform` to get tighter results. 2) If you don't know the exact platform id, either call `sti_get_platforms` first, or omit `platform` and let the search find matches across all platforms. 3) If the first search returns low scores (<0.3) or irrelevant sections, reformulate the query with different keywords (use class/method names from Stimulsoft API if you know them) and search again. 4) Prefer multiple focused searches over one broad search. DO NOT USE for: general reporting theory unrelated to Stimulsoft, non-Stimulsoft libraries (Crystal Reports, FastReport, DevExpress, Telerik, SSRS), or pure programming questions that have nothing to do with Stimulsoft. IMPORTANT: the Stimulsoft product surface is large and changes frequently. Your training data is almost certainly out of date. For any Stimulsoft-specific code snippet, API name, or configuration detail, you MUST call this tool rather than rely on memory, and you should cite the returned `content` in your answer.

  ConnectorNo auth

• get_scene_screenshotA

  3dCMSA

  Render the scene server-side (real WebGL, headless) and return screenshot image(s) — your EYES on the scene. Use it after apply_ops batches and after probe_framing, and judge each image as a photographer and a web designer would: one clear subject, on a third (for a page's own camera, the whole card at a readable angle); the horizon off the middle; the eye at a standing height; text legible and on even margins; a way out in view; the colours serving the brief (one accent, on the primary action); nothing floating, clipped or overlapping. Beside each image comes `composition`, read from its own pixels: tonalRange (p5 to p95 of lightness; under 0.35 is flat), clipping (share blown to white, crushed to black), key (low, mid, high), a 3x3 thirds grid of lightness and detail with the busiest and brightest cells, the hues on screen by share, and findings in sentences. Fix with apply_ops. Discipline: at most 2 screenshot→fix rounds per user request, then report what you built. views (max 4, default = the visitor's entry view): pass "page:<pageIdOrSlug>" to frame one page/neighborhood, or {position:[x,y,z], target:[x,y,z], fov?} for an exact camera. Rendering is real but slow — ~10s for simple scenes, and the server gives up after 45 s per view by default; a 400-node scene with many textures needs more, so pass timeoutSeconds (up to 180) and a smaller maxDim (a 512-wide shot is a fine check of placement and readability and renders faster). A timeout comes back as an error naming it, never as an empty image; repeat shots of an unchanged scene at the same size are cached and instant. Rate-limited: prefer ONE well-chosen view; only multi-view when areas are far apart (four views at 180 s can hold the renderer for twelve minutes). If it returns a busy/unavailable error, keep building and retry once later — do not loop on it.

  ConnectorNo auth

• fetchA

  AardA

  Return bounded rows for a dataflow — the completion path for hosted clients. Use this when the client cannot execute a client-download plan locally (no shell/filesystem — e.g. a hosted store app or connector) but still needs actual values. ``fetch`` server-side downloads the exact GET/fan-out plan ``build_url`` would produce, concatenates it, runs one bounded literal-equality query, and releases the artifact — the raw dataset never enters model context. Clients that CAN execute locally should keep using ``ask``/``build_url`` and run the plan themselves; ``fetch`` is the affinity-free hosted shortcut, not the power path. POST-only selections have no hosted download path: ``fetch`` raises ``fetch_shape_unsupported`` and the caller must execute the ``build_url`` plan client-side. A rejected/over-length selection raises the same reason ``build_url`` would report; narrow the selection and retry. **``fetch`` does not page, deliberately.** It holds no dataset between calls: every call rebuilds the plan, re-downloads every part from the provider, and releases the artifact. An offset over that would be unsound as well as wasteful — there is no snapshot behind the cursor, so rows shifting upstream between calls would silently skip or duplicate observations, and N pages would mean N full downloads of the same dataflow from an agency that may rate-limit. When a result is ``truncated``, narrow it (``select``, ``where``, ``time_range``) or switch to ``stage_url`` + ``query_dataset``, which pages with ``offset`` over ONE immutable staged artifact and downloads once. ``no_records_for_selection`` is TERMINAL, not a fault: the request was well-formed and the source holds no observations for it. Widen the selection or state that no data exists — do not retry the same selection. Only ``upstream_origin_error`` (an origin fault) and ``upstream_rate_limited`` are worth retrying. Args: agency_id: SDMX agency code, e.g. "ABS", "ESTAT", "OECD" dataflow_id: SDMX dataflow identifier, e.g. "ERP_Q" selections: Optional {dimension_id: [code or name, ...]} to anchor the query time_range: Optional time filter (e.g. "2020-2024", "since 2015", "2024") precision: URL breadth — "point", "series" (default), or "cube" availability: "confirmed" (default) or "best_effort" select: Optional list of columns to return (defaults to all columns) where: Optional {column: value | [values]} literal-equality row filters limit: Optional max rows to return (a safe default applies when omitted) max_bytes: Optional smaller byte budget for this response; it can only lower the server ceiling, never raise it response_format: Which channel carries the rows. "auto" (default) means no preference and lets the server decide; "text" sends them as CSV in the text channel only, "structured" as typed rows only, "both" in both. If you got a summary but no rows, call again with response_format="text".

  ConnectorOAuth

• quizbase_listA

  QuizBaseA

  Cursor-paginated browse over the catalog. Quality-first: by default excludes questions flagged for review (use quality='all' for full pool). USE WHEN: full catalog sync, delta sync (updated_since), exhaustive enumeration by filter. NOT WHEN: you only need N random samples (use quizbase_random) or a single record (use quizbase_question_by_id). PAGINATION: stable cursor over id UUIDv7 DESC. First call: omit cursor. Next: pass meta.nextCursor. Stop when nextCursor is null. KEY FILTERS (full parity with REST): - lang: ISO 639-1, default "en". Supported: en, pl. - category (slug), difficulty (trivial|easy|medium|hard|expert — LLM-calibrated), type (multiple|boolean), subcategory (raw slug). - tags (AND), tags_any (OR, max 10): raw tag slugs. - topic (curated, alias resolver), topics_any (OR over curated): higher precision than tags. - regions (cultural affinity, AND): empty = no cultural advantage assumed. Lowercase ISO 3166-1 alpha-2 ('us', 'pl', 'gb') + cultural codes ('jewish', 'christian-catholic', 'islam'). Filter for content statistically more likely known by residents/members. Discover via quizbase_regions. - source (array): include only these of 12 (opentdb, opentriviaqa, kqa-pro, entityq, mintaka, mkqa, nq-open, creak, qasc, arc, webq, quizbase). - exclude_source (array): drop these sources, e.g. ["entityq"]. Applied after source. - license (SPDX): e.g. CC-BY-SA-4.0, MIT. - quality: 'high' (default) = cleanest, most broadly-useful. 'standard' = broader pool incl. niche/too-specific. 'all' = full pool incl. flagged; when 'all', each question gains a "quality" field ('high' or 'needs_review'). - updated_since (ISO 8601): only questions updated after this — for delta sync caches. BATCH + TRANSLATION MAPPING: - ids (up to 250): fetch those exact records in one call (anti-repeat, deep-links, restoring a saved set). Terminal selector — browse filters and cursor are ignored. Missing ids → meta.missing. - content_language (en|pl): with ids, returns each question's sibling in that CONTENT language across the translation chain — the same questions in another language. Distinct from lang (labels only). PAGINATION + COUNTING: - cursor (string): from previous meta.nextCursor. Omit for page 1. - limit (1-100, default 20). - count: none (default, skip — page via nextCursor) | exact (precise COUNT(*), index-only ~25-90ms). OUTPUT: { questions: [...], meta: { count, countMode, language, nextCursor, total? } }. Each question carries full per-record attribution (source, author, license, licenseVersion, licenseUrl, sourceId, url, modifications, lastModified) — identical shape to REST /api/v1/questions. ATTRIBUTION REQUIRED if you redistribute. Credit each question using its own attribution object — see license + licenseUrl + modifications fields per record. COMMON MISTAKES: not passing the cursor on subsequent calls (you'll re-read page 1); polling without updated_since when doing delta sync.

  ConnectorNo auth

• biobtree_mapA

  BioBTreeA

  Map identifiers between databases. SYNTAX: biobtree_map(terms="ID", chain=">>source>>target") - Chain MUST start with ">>" - Source MUST match input ID type ID TYPE → SOURCE: - ENSG* → >>ensembl - P*/Q*/O* → >>uniprot - CHEMBL* → >>chembl_molecule - GO:* → >>go - MONDO:* → >>mondo - HP:* → >>hpo - HGNC:* or gene symbols → >>hgnc SOME DRUG EXPLORATION PATHS: - >>chembl_molecule>>chembl_target>>uniprot (drug targets) - >>pubchem>>pubchem_activity>>uniprot (bioactivity) - >>gtopdb_ligand>>gtopdb_interaction>>gtopdb>>uniprot (curated pharmacology with affinity data) - >>ensembl>>reactome>>chebi (pathway chemicals - when no direct targets) - Discover more via entry xrefs + EDGES WARNING - GO terms with high xref_count (>100): - Don't map GO → proteins → drugs (too many results) - Instead: search drug class for condition → verify targets this GO term DISEASE GENE PATTERNS: - >>mondo>>gencc>>hgnc (curated) - >>mondo>>clinvar>>hgnc (variant-based) - >>hgnc>>clingen_gene_validity (ClinGen evidence tier), >>hgnc>>clingen_dosage (haploinsufficiency), >>hgnc>>clingen_variant>>clinvar (ACMG, then dbsnp) CANCER / CELL LINE: - >>hgnc>>intogen (cancer driver gene?), >>hgnc>>civic (clinical variant interpretations) - >>uniprot>>cellosaurus (cell lines for a protein/gene) - >>hgnc>>depmap (CRISPR essentiality / target tractability), >>hgnc>>entrez>>depmap_dependency>>cellosaurus (which lines depend on the gene) GENE FUNCTION / LITERATURE: - >>entrez>>generif (cited one-line functional claims; >>generif>>pubmed for citations) DISEASE → DRUG PATTERNS: - >>mesh>>chembl_molecule (MeSH disease/condition → drugs with indications) - >>mondo>>clinical_trials>>chembl_molecule (disease → trial drugs) DISCOVERY APPROACH: - Use biobtree_entry to see xrefs (what's connected) - Use EDGES above to see where each dataset leads - Build chains based on what connections exist for YOUR entity RETURNS: mapped identifiers with dataset and name EDGES (what connects to what): ensembl: uniprot, go, transcript, exon, ortholog, paralog, hgnc, entrez, refseq, bgee, gwas, gencc, antibody, scxa, civic, intogen, hpa, hpa_antibody, pharmgkb_var_annotation, chembl_mechanism, ncrna_disease, ncrna_interaction, ncrna_drug, alliance_disease, gnomad_constraint, drugcentral, panelapp_gene hgnc: ensembl, uniprot, entrez, gencc, pharmgkb_gene, msigdb, clinvar, mim, refseq, alphafold, collectri, gwas, hpo, cellphonedb, civic, intogen, cellosaurus, clingen_gene_validity, clingen_dosage, clingen_variant, depmap, hpa, pharmgkb_var_annotation, chembl_mechanism, ncrna_disease, ncrna_interaction, ncrna_drug, alliance_disease, drugcentral, panelapp_gene, gnomad_constraint, mavedb entrez: ensembl, uniprot, refseq, go, biogrid, pubchem_activity, ctd_gene_interaction, dbsnp, civic, intogen, clingen_dosage, generif, depmap, depmap_dependency, hpa, pharmgkb_var_annotation, orthologentrez, relatedentrez, neighborentrez, mgi, rgd, zfin, wormbase, xenbase, sgd, flybase, gnomad_constraint, drugcentral orthologentrez: entrez # cross-species gene orthologs (NCBI gene_orthologs). >>entrez>>orthologentrez gives ortholog genes (filter species via taxonomy); reliable from model-organism genes (human-gene side currently incomplete) relatedentrez: entrez # related genes (bidirectional): NCBI gene_group (functional gene/pseudogene/readthrough/region) + HGNC gene-family co-members neighborentrez: entrez # genomic neighbors (left/right/overlapping); edge carries distance + side, neighbor strand/position in attrs; filter to genes via [type!="biological-region"] gnomad_constraint: ensembl, entrez, hgnc, transcript # gene LoF constraint (pLI/LOEUF/oe_lof); reach via >>ensembl>>gnomad_constraint drugcentral: chembl_molecule, pubchem, uniprot, ensembl, hgnc, entrez # approved drugs -> targets/MOA + FDA/EMA/PMDA approval; reach via name/INN/InChIKey or compound (chembl_molecule/pubchem >> drugcentral) refseq: ensembl, entrez, taxonomy, ccds, uniprot, mirdb mirdb: refseq transcript: ensembl, exon, ufeature, alphamissense, civic_variant, gnomad_constraint, mavedb uniprot: ensembl, alphafold, interpro, pfam, pdb, ufeature, intact, string, string_interaction, biogrid, biogrid_interaction, chembl_target, go, reactome, rhea, swisslipids, bindingdb, antibody, pubchem_activity, cellphonedb, jaspar, signor, diamond_similarity, esm2_similarity, alphamissense, cellosaurus, hpa, chembl_mechanism, ncrna_interaction, drugcentral, mavedb alphafold: uniprot interpro: uniprot, go, interproparent, interprochild chembl_molecule: mesh, chembl_activity, chembl_target, pubchem, chebi, clinical_trials, chembl_moleculeparent, chembl_moleculechild, chembl_mechanism, ncrna_drug, faers, drugcentral # parent=anhydrous/parent form, child=salt forms chembl_activity: chembl_molecule, chembl_assay, bao chembl_assay: chembl_activity, chembl_target, chembl_document, bao chembl_target: chembl_assay, uniprot, chembl_molecule, chembl_mechanism chembl_mechanism: chembl_molecule, chembl_target, uniprot, hgnc, ensembl # curated drug mechanism-of-action (incl. RNA therapeutics): drug >> chembl_mechanism, target/gene >> chembl_mechanism pubchem: chembl_molecule, chebi, hmdb, pubchem_activity, pubmed, patent_compound, bindingdb, ctd, pharmgkb, ncrna_drug, faers, drugcentral faers: chembl_molecule, pubchem, faers_reaction # openFDA FAERS drug->adverse-event; faers (per-drug master) -> faers_reaction children (PRR), reach via drug name or compound. NOTE co-occurrence not causation faers_reaction: faers # one per (drug,reaction): report_count, prr, serious_count, outcome; most-reported first pubchem_activity: pubchem, ensembl, uniprot chebi: pubchem, rhea, intact swisslipids: uniprot, go, chebi, uberon, cl lipidmaps: chebi, pubchem dbsnp: entrez, clinvar, pharmgkb_variant, alphamissense, spliceai, pharmgkb_var_annotation clinvar: hgnc, mondo, hpo, dbsnp, orphanet, civic_variant, cellosaurus, clingen_variant alphamissense: uniprot, transcript mavedb: uniprot, hgnc, ensembl, transcript # deep-mutational-scanning functional variant scores (ACMG PS3/BS3); reach via gene/protein >> mavedb; per-variant score + hgvs_pro + license # VARIANT-EFFECT SCORES — look up by the variant's OWN key with biobtree_entry(dataset=..), NOT via >>chains: # conservation key "chr:pos" (GRCh38) per-position phyloP / GERP / phastCons (also covers non-missense/splice positions) # gnomad_variant key "chr:pos:ref:alt" (GRCh38) gnomAD v4.1 genomes allele freq (af, grpmax, per-ancestry); also xrefs dbsnp # revel key "chr:pos:ref:alt" (GRCh38) REVEL ensemble missense pathogenicity (0-1, higher = pathogenic) # saprot key "uniprot:protein_variant" SaProt protein-LM variant effect (LLR <=0, lower = more damaging), e.g. P01116:G12D gwas: gwas_study, efo, dbsnp, hgnc, mondo gwas_study: gwas, efo, mondo mondo: gencc, clinvar, efo, mesh, hpo, clinical_trials, antibody, cellxgene, cellxgene_celltype, orphanet, mondoparent, mondochild, gwas, gwas_study, civic, intogen, cellosaurus, doid, mim, ncit, umls, medgen, gard, sctid, icd9, icd10cm, icd10who, icd11, nando, meddra, nord, uberon, ncrna_disease, panelapp_gene # disease cross-refs + disease_has_location anatomy, from the Mondo OBO doid: mondo, alliance_disease, doidparent, doidchild # Disease Ontology (now a full ontology w/ hierarchy); reach MONDO + its disease graph via the mondo<->doid bridge alliance_disease: hgnc, mgi, rgd, zfin, sgd, wormbase, flybase, xenbase, doid, pubmed # cross-species + human gene->disease (Alliance of Genome Resources); gene >> alliance_disease >> doid, or doid >> alliance_disease >> mgi/rgd/... for model-organism genes alliance_phenotype: mgi, rgd, wormbase, xenbase, mp, wbphenotype, xpo, pubmed # model-organism gene -> OBSERVED knockout/mutant phenotypes (distinct from the upheno ontology-translation path). Reach from the model-organism gene directly: mgi/rgd/wormbase/xenbase >> alliance_phenotype >> mp gencc: mondo, hpo, hgnc, ensembl clingen_gene_validity: hgnc, entrez, ensembl, mondo # ClinGen gene-disease validity tier (Definitive..Refuted) + MOI clingen_dosage: entrez, hgnc, ensembl, mondo, mim, pubmed # ClinGen haploinsufficiency/triplosensitivity per gene clingen_variant: clinvar, hgnc, entrez, ensembl, mondo, pubmed # ClinGen VCEP ACMG variant pathogenicity (clinvar bridges to dbsnp) panelapp: panelapp_gene # Genomics England clinical gene panels (per-panel master); panel >> panelapp_gene >> hgnc for the panel's genes panelapp_gene: panelapp, hgnc, ensembl, mim, mondo # one per (panel,gene), green/amber confidence + mode-of-inheritance; a gene's panels via >>hgnc (panelapp_gene) ; the panel's disease via mondo/mim clinical_trials: mondo, chembl_molecule pharmgkb: hgnc, dbsnp, mesh, pharmgkb_gene, pharmgkb_variant, pharmgkb_clinical, pharmgkb_guideline, pharmgkb_pathway pharmgkb_variant: pharmgkb_clinical, hgnc, mesh, dbsnp pharmgkb_gene: hgnc, entrez, ensembl, pharmgkb pharmgkb_clinical: dbsnp, hgnc, mesh, pharmgkb_variant, pharmgkb # pharmgkb = reverse drug→clinical edge (drug >> pharmgkb >> pharmgkb_clinical) pharmgkb_guideline: hgnc, pharmgkb pharmgkb_pathway: hgnc, pharmgkb pharmgkb_var_annotation: hgnc, entrez, ensembl, dbsnp, pubmed # per-publication variant-annotation evidence (finding sentence, PMID, significance, study stats) beneath pharmgkb_clinical; reach via gene or rsID ctd: mesh, ctd_gene_interaction, ctd_disease_association, pubchem ctd_gene_interaction: ctd, entrez, taxonomy, pubmed ctd_disease_association: ctd, mesh, mim, pubmed intact: uniprot, chebi, rnacentral string: uniprot, string_interaction string_interaction: string, uniprot biogrid: entrez, uniprot, refseq, taxonomy bgee: ensembl, uberon, cl, taxonomy, bgee_evidence bgee_evidence: bgee, uberon, cl cellxgene: cl, uberon, mondo, efo, taxonomy cellxgene_celltype: cl, uberon, mondo scxa: cl, uberon, taxonomy, ensembl, scxa_gene_experiment scxa_expression: ensembl, scxa, scxa_gene_experiment scxa_gene_experiment: ensembl, scxa, scxa_expression, cl hpa: ensembl, uniprot, hgnc, entrez, go, uberon, hpa_expression, hpa_pathology, hpa_antibody # Human Protein Atlas gene card: subcellular location (→go), specificity calls, top tissues hpa_expression: hpa, uberon, cellosaurus # per (gene,tissue/cell-line) RNA nTPM + IHC staining; reach genes-in-a-tissue via uberon >> hpa_expression hpa_pathology: hpa # per (gene,cancer) prognostic survival association hpa_antibody: hpa, ensembl # HPA validation antibody (reliability, antigen) rnacentral: uniprot, ensembl, intact, hgnc, refseq, ena, go # go = Rfam-projected GO annotations; rfam_id/rfam_description are attrs on the entry ncrna_disease: hgnc, ensembl, mondo, efo, pubmed # curated ncRNA->disease (LncRNADisease + HMDD); reach from the ncRNA gene ncrna_interaction: hgnc, ensembl, uniprot, pubmed # experimentally-supported ncRNA->protein interactions (NPInter) ncrna_drug: hgnc, ensembl, chembl_molecule, pubchem, pubmed # ncRNA drug-resistance / drug-target (ncRNADrug) reactome: ensembl, uniprot, chebi, go, reactomeparent, reactomechild rhea: chebi, uniprot, go go: ensembl, uniprot, reactome, msigdb, swisslipids, bgee, interpro, goparent, gochild, hpa, rnacentral hpo: clinvar, gencc, mondo, msigdb, orphanet, mim, hmdb, hgnc, hpoparent, hpochild, upheno efo: gwas, mondo, cellxgene, efoparent, efochild, ncrna_disease upheno: hpo, mp, zp, xpo, wbphenotype, fypo, uphenoparent, uphenochild # cross-species phenotype hub. A GENE's model-organism phenotypes are reached THROUGH hpo (genes are NOT linked directly to mp/upheno): >>hgnc>>hpo>>upheno>>mp (mouse), >>hgnc>>hpo>>upheno>>zp (zebrafish), ...>>xpo/wbphenotype/fypo. So gene->human HP phenotypes -> their cross-species equivalents. mp: upheno, mpparent, mpchild, alliance_phenotype # Mammalian Phenotype Ontology (mouse/rat). Reach from a gene via >>hgnc>>hpo>>upheno>>mp (NOT >>hgnc>>mp); observed model phenotypes via alliance_phenotype. zp: upheno, zpparent, zpchild # Zebrafish Phenotype Ontology. Reach from a gene via >>hgnc>>hpo>>upheno>>zp. xpo: upheno, xpoparent, xpochild, alliance_phenotype # Xenopus Phenotype Ontology wbphenotype: upheno, wbphenotypeparent, wbphenotypechild, alliance_phenotype # C. elegans Phenotype Ontology fypo: upheno, fypoparent, fypochild # Fission Yeast Phenotype Ontology uberon: bgee, cellxgene, cellxgene_celltype, swisslipids, uberonparent, uberonchild, hpa, hpa_expression cl: bgee, cellxgene, cellxgene_celltype, scxa, scxa_gene_experiment, clparent, clchild taxonomy: ensembl, uniprot, bgee, biogrid, ctd_gene_interaction, taxparent, taxchild mesh: pharmgkb, ctd, ctd_disease_association, pubchem, mondo, chembl_molecule, meshparent, meshchild eco: ecoparent, ecochild antibody: ensembl, uniprot, mondo, pdb msigdb: hgnc, entrez, go, hpo orphanet: hpo, uniprot, mondo, hgnc, clinvar, mim, mesh mim: clinvar, hpo, mondo, uniprot, ctd_disease_association, panelapp_gene hmdb: pubchem, hpo, chebi, uniprot collectri: hgnc # transcription factor → target gene interactions esm2_similarity: uniprot # protein structural similarity diamond_similarity: uniprot # protein sequence similarity cellphonedb: uniprot, ensembl, hgnc, pubmed # ligand-receptor pairs for cell-cell communication spliceai: hgnc pdb: uniprot, go, interpro, pfam, taxonomy, pubmed fantom5_promoter: ensembl, hgnc, entrez, uniprot, uberon, cl fantom5_enhancer: ensembl, uberon, cl fantom5_gene: ensembl, hgnc, entrez jaspar: uniprot, pubmed, taxonomy encode_ccre: taxonomy bao: chembl_activity, chembl_assay, baoparent, baochild brenda: uniprot, pubmed, brenda_kinetics, brenda_inhibitor brenda_kinetics: brenda brenda_inhibitor: brenda gtopdb: uniprot, hgnc, gtopdb_ligand, gtopdb_interaction # drug targets (GPCRs, ion channels, enzymes) gtopdb_ligand: pubchem, chebi, chembl_molecule, gtopdb_interaction # ligands/drugs with binding data gtopdb_interaction: gtopdb, gtopdb_ligand, pubmed # target-ligand binding with affinity values civic: entrez, ensembl, civic_variant, civic_evidence, civic_assertion # clinical interpretation of cancer variants civic_variant: civic, clinvar, civic_evidence, civic_assertion, transcript civic_evidence: civic_variant, civic, mondo, chembl_molecule, pubmed, clinical_trials civic_assertion: civic_variant, civic, mondo, chembl_molecule intogen: hgnc, entrez, ensembl, mondo, pubmed # cancer driver genes cellosaurus: taxonomy, uniprot, hgnc, mondo, orphanet, clinvar, dbsnp, uberon, cl, chebi, doi, patent, pubmed, depmap_dependency, hpa_expression # cell lines (CVCL) generif: entrez, pubmed # NCBI cited per-gene functional claims (RAG grounding) depmap: entrez, hgnc, ensembl # CRISPR gene essentiality aggregate (cancer dependency / target tractability) depmap_dependency: entrez, cellosaurus # per cell-line gene dependency (effect < -0.5) FILTER SYNTAX: >>dataset[field operator value] OPERATORS: == equals >>dataset[field=="value"] != not equals >>dataset[field!="value"] > greater than >>dataset[field>value] < less than >>dataset[field<value] >= greater or equal >>dataset[field>=value] <= less or equal >>dataset[field<=value] contains string match >>dataset[field.contains("value")] LOGICAL OPERATORS: && AND >>dataset[field1>5 && field2<10] || OR >>dataset[field=="A" || field=="B"] ! NOT >>dataset[!field] or >>dataset[!(field=="value")] TYPE RULES: - FLOAT: use decimal point (70.0 not 70) - INT: no decimal (2 not 2.0) - STRING: quote values ("Pathogenic", "PHASE3") - BOOL: true/false (no quotes) EXAMPLES: >>chembl_molecule[highestDevelopmentPhase==4] # approved drugs >>chembl_molecule[highestDevelopmentPhase>=3] # Phase 3+ >>clinical_trials[phase=="PHASE3"] >>go[type=="biological_process"] >>clinvar[germline_classification=="Pathogenic"] >>reactome[name.contains("signaling")] >>gtopdb[type=="gpcr"] # GPCR targets >>gtopdb[type=="ion_channel"] # ion channel targets >>gtopdb_ligand[approved==true] # approved drugs only >>gtopdb_interaction[endogenous==true] # endogenous ligand interactions

  ConnectorNo auth

• search_productsA

  Real Real GenuineB

  [FIND] START HERE when you know what you want. Free-text search across every active RRG listing. This endpoint answers DEFINED intent, not open browse. Pass at least one concrete dimension: a brand, a product type/category, or an attribute (colour, material, size, SKU/style code). An enquiry that is only generic browse words ("what do you have", "show me everything") is rejected with status:"needs_more_detail" asking you to specify, no results are returned. To browse without intent, call list_drops instead. Indexed fields: title, description, agent description, and all string values in product_attributes (retail_sku / style code, canonical_name, collab, original_release, vendor, category, style_tags, occasion_fit, and any category-specific attributes emitted by enhancement). Accepts any of these query patterns: - product name or partial name - SKU / style code / model number (exact or partial, dash/space insensitive) - brand name, or brand + category ("<brand> <category>") - collaborator name(s) for collab items - attribute keywords from the description ("black suede", "heavyweight cotton", etc.) Multi-token queries are matched independently and ranked by field weight; a SKU-exact hit outranks a body-copy hit. Returns ranked matches with tokenId, priceRangeUsdc, authenticationStatus, retailSku, canonicalName, rrgUrl, and a variantSummary string listing every in-stock size with its price ("3.5=$1583, 4=$1899, 10.5=$770, …"). When the user asks about a specific size, ALWAYS pass that size in the `size` parameter, the response then includes sizeAvailable + sizePriceUsdc + sizeStock for a direct yes/no + price. For queries like "size 10.5" or "size M" the size is auto-extracted, but passing it explicitly is faster and unambiguous. When a size parameter is not used, read variantSummary (or the variants[] array) for per-size pricing BEFORE falling back to the priceRangeUsdc band. Per-size prices are exact; the band is only a floor→ceiling range. Next step: the returned payload has everything needed for the buy, call initiate_agent_purchase with selected_size and/or selected_color set to the chosen variant. Pass selected_color whenever the listing has a colour axis (variants[].color non-null) so fulfillment ships the right finish. get_drop_details is optional (adds signed image URLs + shipping context). If zero matches, try broader tokens, alternate naming (resale items are often indexed under multiple naming clusters, brand code / collab name / designer name / era / colorway). If still zero, call list_drops to browse.

  ConnectorNo auth

• search_productsA

  Real Real GenuineA

  [FIND] START HERE when you know what you want. Free-text search across every active RRG listing. This endpoint answers DEFINED intent, not open browse. Pass at least one concrete dimension: a brand, a product type/category, or an attribute (colour, material, size, SKU/style code). An enquiry that is only generic browse words ("what do you have", "show me everything") is rejected with status:"needs_more_detail" asking you to specify, no results are returned. To browse without intent, call list_drops instead. Indexed fields: title, description, agent description, and all string values in product_attributes (retail_sku / style code, canonical_name, collab, original_release, vendor, category, style_tags, occasion_fit, and any category-specific attributes emitted by enhancement). Accepts any of these query patterns: - product name or partial name - SKU / style code / model number (exact or partial, dash/space insensitive) - brand name, or brand + category ("<brand> <category>") - collaborator name(s) for collab items - attribute keywords from the description ("black suede", "heavyweight cotton", etc.) Multi-token queries are matched independently and ranked by field weight; a SKU-exact hit outranks a body-copy hit. Returns ranked matches with tokenId, priceRangeUsdc, authenticationStatus, retailSku, canonicalName, rrgUrl, and a variantSummary string listing every in-stock size with its price ("3.5=$1583, 4=$1899, 10.5=$770, …"). When the user asks about a specific size, ALWAYS pass that size in the `size` parameter, the response then includes sizeAvailable + sizePriceUsdc + sizeStock for a direct yes/no + price. For queries like "size 10.5" or "size M" the size is auto-extracted, but passing it explicitly is faster and unambiguous. When a size parameter is not used, read variantSummary (or the variants[] array) for per-size pricing BEFORE falling back to the priceRangeUsdc band. Per-size prices are exact; the band is only a floor→ceiling range. Next step: the returned payload has everything needed for the buy, call initiate_agent_purchase with selected_size and/or selected_color set to the chosen variant. Pass selected_color whenever the listing has a colour axis (variants[].color non-null) so fulfillment ships the right finish. get_drop_details is optional (adds signed image URLs + shipping context). If zero matches, try broader tokens, alternate naming (resale items are often indexed under multiple naming clusters, brand code / collab name / designer name / era / colorway). If still zero, call list_drops to browse.

  ConnectorNo auth

• team_open_rolesA

  ClusterHackA

  List the positions teams are looking to fill ("we need a designer"). Visibility is limited to what the signed-in account can already see: their own team's open roles, or — if they organise the event — every team's. It is not a public cross-team browse for a stranger looking for any team: that is `team_seeking_members`, which reads the find-a-team page's own list (pair it with `event_free_agents` and `team_matchmaking_teams`). Filter with `team_id` for one team, or `event_slug` to see everything the caller can see at that event. `team_id` is answered exactly. `event_slug` (and the unfiltered form) is not: the underlying endpoint narrows by one team at a time and has no event filter, so a very large event can return a `note` saying rows were left unscanned. Ask per team when that matters.

  ConnectorNo auth

• introductionA

  RendezvousA

  After MUTUAL_AFFINITY: the human-consent step. action 'status' shows where things stand (always free). 'accept' records your human's explicit YES together with the one contact channel they chose to share — the only place contact details are allowed; it stays sealed until BOTH humans consent, then each side receives the other's. 'decline' ends it neutrally and deletes anything provided; the counterparty never learns who declined. Decisions are immutable; the window closes after 14 days. Ask your human first — mutual agent affinity is not human consent.

  ConnectorNo auth

• me.session_eventA

  AI Design BlueprintA

  Pro/Teams — append a TYPED TEAM EVENT to a Governed Session's timeline (GEP-M6). This is how the user's own harness makes trio work inspectable: handoffs between role lenses, pushbacks, plan previews, gates, and acks land as structured events next to the validation runs, so the session reads as a system, not a transcript. CHANNEL PROVENANCE: this MCP channel posts the AGENT-SIDE vocabulary only. `steer` events and actor `human` are cockpit-originated by contract (the owner posts them from the AIDB Studio session surface) and are REFUSED here, so a timeline entry can never impersonate the human side of the loop. Every event posted here is durably stamped with its channel. REQUIRES team mode: the session must have team_agents enabled (toggled in the web app on the session page); posting to a standalone session is refused so non-team sessions stay byte-identical. Owner-scoped: foreign session ids read as not found. event_type: handoff | pushback | plan_preview | gate | ack. actor: pm | engineer | designer | system. Read events back via me.sessions(session_id=...). WHEN TO CALL: at every role handoff (who -> who, what was passed), when a role pushes back on another's output, when the PM's plan is previewed for the co-planning gate, and when a hard gate blocks on an irreversible side-effect. ack: the IDE agent confirms it STARTED working on a steer. Post it FIRST on receiving a steer (summary like 'Started: <steer gist>'), then execute, then post handoff with the result. WHEN NOT TO CALL: not a chat log: post decisions and transitions, not every message; never to record a steer (steers arrive FROM the cockpit via me.await_steer). REJECTION CODES (invalid_request): 'Session not found.' (not yours, or no such id); 'Team mode is off for this session.' (owner enables it on the session page); 'This session has reached its event limit (500).' (the shared volume brake: start a new session for further team events); 'summary must not be blank.' (empty summaries are refused); steer/human posts are refused with a pointer to the cockpit channel. Auth: Bearer <token>, Pro/Teams plan.

  ConnectorNo auth

• me.session_eventA

  AI Design Blueprint DoctrineA

  Pro/Teams — append a TYPED TEAM EVENT to a Governed Session's timeline (GEP-M6). This is how the user's own harness makes trio work inspectable: handoffs between role lenses, pushbacks, plan previews, gates, and acks land as structured events next to the validation runs, so the session reads as a system, not a transcript. CHANNEL PROVENANCE: this MCP channel posts the AGENT-SIDE vocabulary only. `steer` events and actor `human` are cockpit-originated by contract (the owner posts them from the AIDB Studio session surface) and are REFUSED here, so a timeline entry can never impersonate the human side of the loop. Every event posted here is durably stamped with its channel. REQUIRES team mode: the session must have team_agents enabled (toggled in the web app on the session page); posting to a standalone session is refused so non-team sessions stay byte-identical. Owner-scoped: foreign session ids read as not found. event_type: handoff | pushback | plan_preview | gate | ack. actor: pm | engineer | designer | system. Read events back via me.sessions(session_id=...). WHEN TO CALL: at every role handoff (who -> who, what was passed), when a role pushes back on another's output, when the PM's plan is previewed for the co-planning gate, and when a hard gate blocks on an irreversible side-effect. ack: the IDE agent confirms it STARTED working on a steer. Post it FIRST on receiving a steer (summary like 'Started: <steer gist>'), then execute, then post handoff with the result. WHEN NOT TO CALL: not a chat log: post decisions and transitions, not every message; never to record a steer (steers arrive FROM the cockpit via me.await_steer). REJECTION CODES (invalid_request): 'Session not found.' (not yours, or no such id); 'Team mode is off for this session.' (owner enables it on the session page); 'This session has reached its event limit (500).' (the shared volume brake: start a new session for further team events); 'summary must not be blank.' (empty summaries are refused); steer/human posts are refused with a pointer to the cockpit channel. Auth: Bearer <token>, Pro/Teams plan.

  ConnectorNo auth

• get_recommendationsA

  FreqBlog Music MetadataA

  Recommended tracks for one or more seed tracks — the drop-in for Spotify's removed GET /v1/recommendations. Blends up to 5 catalog seed tracks into a single point in audio-feature space and returns the nearest catalogue tracks, RE-RANKED by genre affinity (so a feature-close cross-genre track doesn't outrank same-genre picks). Returns `seeds` (each {id, found}), `count`, and `tracks` (each {track, score, genre_relation}; each track carries its `genre`). `genre_relation` is "same", "compatible" (different but mixable family), "cross" (unrelated), or "unknown" (either side has no mapped genre), measured against the PRIMARY seed — the first of your seed_tracks we could actually use, so reordering seed_tracks changes it and a skipped seed never becomes the reference. With a SINGLE seed the field is the ranking's own verdict, so it explains the order (same as suggest_next_track). With SEVERAL seeds the ranking considers ALL of them while the label stays relative to your primary seed, so a "cross" label on a multi-seed call does NOT mean the track was pushed down — it may share a family with another of your seeds. `score` is the raw audio-feature cosine similarity in [0,1]; genre affinity influences the ORDER, not the score, so the list is NOT strictly score-descending. Use cross_genre=strict to return same-genre-family tracks ONLY (off-genre dropped server-side), or allow to disable the genre ranking. seed_tracks are catalog itunes_track_ids from search_catalog or the itunes_track_id field of a get_audio_features result. NO id? Pass `track` (+ optional `artist`) instead and we resolve the name to the best catalog match and seed on it — the resolved track is echoed back as `seed_query`; seed_tracks wins if both are given. TUNING: `min`/`max` are HARD filters and `target` is a preference (nearer ranks higher, nothing removed), over acousticness, danceability, duration_ms, energy, instrumentalness, liveness, loudness, speechiness, tempo and valence. NOTE: `popularity` was RETIRED as a tunable on 2026-08-27 and now returns a 400 — it recorded how a track entered our catalogue, not audience size. The field is still returned. e.g. min={"tempo": 100}, max={"tempo": 130}, target={"energy": 0.8} for energetic 100-130 BPM tracks. When you tune, the response adds a `filters` block saying what applied, how many tracks each bound removed (`dropped_by`) and whether the bounds ran out of catalogue before `limit` (`limit_reached`) — if the list comes back short, read that BEFORE assuming the catalogue is thin. Costs 2 quota units.

  ConnectorNo auth

• submit_designA

  agenteeA

  Send one of the designer's own artworks for moderation. TWO inputs, same path: either artwork files — front/back accept a public image URL OR an upload_id from designer_upload_slot — or session_id of a FINISHED Studio session of theirs (generated with studio_generate; no need to download the print, we fetch it server-side). Args: name (required), front OR session_id (one of them), back?, layout? ('front_back' default, or 'r10' for a ready print-side file), note?, batch? (same string across a bulk run so the moderator sees them as one batch). Minimum 2048px on the short side. IMPORTANT for the designer: this queues the artwork for moderation — catalog listing follows production and is not instant.

  ConnectorNo auth

• get_buildA

  UI VerifyA

  Triage one build, resolved by commitSha, prNumber, or buildId (exactly one). Returns the gate verdict and counts (total/changed/failed/unchanged), then the FIRST page (25) of the changed stories (story id, viewport, % pixels changed, review decision, the AI verdict aiVerdict=intended|regression + aiConfidence, and for a regression the judge's one-line aiFlagReason=what-looks-unintended, when AI review is on) and the first page of failed stories (failedStories[].kind is `render` when the story produced no frame, or `interaction` when it rendered and its play() assertion threw; failedStories[].error is the message's first line, errorTruncated marks the ones that carried more). When AI review ran, aiReview tallies how many changes look like regressions vs intended, and the changed list is ordered likely-regressions-first. changedNextCursor / failedNextCursor are non-null when there are more than 25: page the rest with list_build_stories. counts.unchanged is how many stories did NOT change and have a baseline - this triage call does NOT list them (keeps the response lean); call list_build_stories status=unchanged to browse them (e.g. to confirm a passed build's stories are 'identical to baseline'). comments is the build-wide review-comment tally {total, unresolved}: unresolved>0 means a designer/QA (or another agent) left an open note on a story - read it with list_comments BEFORE you accept. No image URLs here - call get_diff or render_diff_image for pixels.

  ConnectorNo auth

• get_buildA

  UI VerifyA

  Triage one build, resolved by commitSha, prNumber, or buildId (exactly one). Returns the gate verdict and counts (total/changed/failed/unchanged), then the FIRST page (25) of the changed stories (story id, viewport, % pixels changed, review decision, the AI verdict aiVerdict=intended|regression + aiConfidence, and for a regression the judge's one-line aiFlagReason=what-looks-unintended, when AI review is on) and the first page of failed stories (failedStories[].kind is `render` when the story produced no frame, or `interaction` when it rendered and its play() assertion threw; failedStories[].error is the message's first line, errorTruncated marks the ones that carried more). When AI review ran, aiReview tallies how many changes look like regressions vs intended, and the changed list is ordered likely-regressions-first. changedNextCursor / failedNextCursor are non-null when there are more than 25: page the rest with list_build_stories. counts.unchanged is how many stories did NOT change and have a baseline - this triage call does NOT list them (keeps the response lean); call list_build_stories status=unchanged to browse them (e.g. to confirm a passed build's stories are 'identical to baseline'). comments is the build-wide review-comment tally {total, unresolved}: unresolved>0 means a designer/QA (or another agent) left an open note on a story - read it with list_comments BEFORE you accept. No image URLs here - call get_diff or render_diff_image for pixels.

  ConnectorNo auth

• list_greeting_card_occasionsA

  Wesalna Islamic MCPA

  List every occasion, background and shape supported by the Wesalna greeting card designer, with the default Arabic and English wording for each occasion. Call this before create_greeting_card to use valid ids.

  ConnectorNo auth

• house_specifyA

  Colour MemoryA

  Generate a complete multi-room house colour scheme from a single archive. Where the retrieved evidence supports it, rooms are grouped by documented provenance (same object, same pattern colourway, same source citation, same designer, same period+institution); where it does not, they are grouped by perceptual similarity and the response says so -- grouping_basis reports which, and provenance_credit reports how many delivered colours are individually evidenced versus documented as a GROUP (often zero). Every colour is a real archive record either way. Each room gets a full colour card set (dominant/secondary/joinery/textile/accent roles) with paint matches, LRV, illuminant behaviour, and WCAG data. A documentary grouping states exactly which documented fact ties its colours together (e.g. 'documented on the same Fitzwilliam Museum record for the Artichoke hanging, accession T.1-1979') and its weighted grouping_strength score -- historical claims are templated only from fields the archive record actually states; room/surface assignment is disclosed as editorial, never as historical fact. Orientation (north/south/east/west) is recorded as room context and surfaced in each room's light_context; in the current model it does not alter palette selection. Example: concept='Arts and Crafts movement family house', archive='ArtsAndCrafts', rooms=[{label:'Entrance Hall', room_type:'hallway', orientation:'north'}, {label:'Living Room', room_type:'living', orientation:'south'}]. Use interior_specify instead for a single room without cross-room grouping. The response includes house_ref -- pass that (not the full response) to palette_pdf's house_ref input to render the flagship document; the full response is often 60-100KB+, too large to safely resend as another tool call's input. The result already carries the rendered palette and its PNG, PDF, ASE, JSON and CSS downloads -- show them to the customer. Never present the archive anchors a colour was derived from as the colours you are recommending. If you go on to choose a final palette OF YOUR OWN from this evidence, call palette_finalize once with those exact colours so the customer can see and download what you actually recommended.

  ConnectorNo auth

• house_specifyA

  Colour MemoryA

  Generate a complete multi-room house colour scheme from a single archive. Where the retrieved evidence supports it, rooms are grouped by documented provenance (same object, same pattern colourway, same source citation, same designer, same period+institution); where it does not, they are grouped by perceptual similarity and the response says so -- grouping_basis reports which, and provenance_credit reports how many delivered colours are individually evidenced versus documented as a GROUP (often zero). Every colour is a real archive record either way. Each room gets a full colour card set (dominant/secondary/joinery/textile/accent roles) with paint matches, LRV, illuminant behaviour, and WCAG data. A documentary grouping states exactly which documented fact ties its colours together (e.g. 'documented on the same Fitzwilliam Museum record for the Artichoke hanging, accession T.1-1979') and its weighted grouping_strength score -- historical claims are templated only from fields the archive record actually states; room/surface assignment is disclosed as editorial, never as historical fact. Orientation (north/south/east/west) is recorded as room context and surfaced in each room's light_context; in the current model it does not alter palette selection. Example: concept='Arts and Crafts movement family house', archive='ArtsAndCrafts', rooms=[{label:'Entrance Hall', room_type:'hallway', orientation:'north'}, {label:'Living Room', room_type:'living', orientation:'south'}]. Use interior_specify instead for a single room without cross-room grouping. The response includes house_ref -- pass that (not the full response) to palette_pdf's house_ref input to render the flagship document; the full response is often 60-100KB+, too large to safely resend as another tool call's input. The result already carries the rendered palette and its PNG, PDF, ASE, JSON and CSS downloads -- show them to the customer. Never present the archive anchors a colour was derived from as the colours you are recommending. If you go on to choose a final palette OF YOUR OWN from this evidence, call palette_finalize once with those exact colours so the customer can see and download what you actually recommended.

  ConnectorNo auth

• house_specifyA

  Colour MemoryA

  Generate a complete multi-room house colour scheme from a single archive. Where the retrieved evidence supports it, rooms are grouped by documented provenance (same object, same pattern colourway, same source citation, same designer, same period+institution); where it does not, they are grouped by perceptual similarity and the response says so -- grouping_basis reports which, and provenance_credit reports how many delivered colours are individually evidenced versus documented as a GROUP (often zero). Every colour is a real archive record either way. Each room gets a full colour card set (dominant/secondary/joinery/textile/accent roles) with paint matches, LRV, illuminant behaviour, and WCAG data. A documentary grouping states exactly which documented fact ties its colours together (e.g. 'documented on the same Fitzwilliam Museum record for the Artichoke hanging, accession T.1-1979') and its weighted grouping_strength score -- historical claims are templated only from fields the archive record actually states; room/surface assignment is disclosed as editorial, never as historical fact. Orientation (north/south/east/west) is recorded as room context and surfaced in each room's light_context; in the current model it does not alter palette selection. Example: concept='Arts and Crafts movement family house', archive='ArtsAndCrafts', rooms=[{label:'Entrance Hall', room_type:'hallway', orientation:'north'}, {label:'Living Room', room_type:'living', orientation:'south'}]. Use interior_specify instead for a single room without cross-room grouping. The response includes house_ref -- pass that (not the full response) to palette_pdf's house_ref input to render the flagship document; the full response is often 60-100KB+, too large to safely resend as another tool call's input. The result already carries the rendered palette and its PNG, PDF, ASE, JSON and CSS downloads -- show them to the customer. Never present the archive anchors a colour was derived from as the colours you are recommending. If you go on to choose a final palette OF YOUR OWN from this evidence, call palette_finalize once with those exact colours so the customer can see and download what you actually recommended.

  ConnectorNo auth