ensembl-mcp-server

{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'properties': {'id': {'type': 'string', 'description': 'Ensembl stable gene ID (e.g. ENSG00000139618). Use ensembl_lookup_gene to get the stable ID from a symbol. Cannot be combined with symbol.'}, 'type': {'enum': ['orthologues', 'paralogues', 'all'], 'type': 'string', 'default': 'orthologues', 'description': 'Type of homologs to return. orthologues: genes related by speciation (cross-species equivalents). paralogues: genes related by duplication (within or across species). all: both orthologs and paralogs.'}, 'symbol': {'type': 'string', 'description': 'Gene symbol in the source species (e.g. BRCA2, TP53). Species defaults to homo_sapiens; set species for other organisms. Cannot be combined with id.'}, 'species': {'type': 'string', 'default': 'homo_sapiens', 'minLength': 1, 'description': 'Source species (the species the query gene belongs to) in Ensembl internal format. Default is homo_sapiens. Use ensembl_list_species to discover valid values.'}, 'max_results': {'type': 'integer', 'default': 25, 'maximum': 9007199254740991, 'minimum': 0, 'description': 'Maximum number of homologs to return. Broad orthology queries (e.g. BRCA2 across all species) can return 150+ homologs; the default keeps responses focused. Set to 0 to return every homolog uncapped. totalCount always reports the true number available before this cap.'}, 'target_species': {'type': 'string', 'description': 'Filter to homologs in a single target species (e.g. mus_musculus for mouse). Omit to return homologs across all available species. Use ensembl_list_species to discover valid values.'}}, 'additionalProperties': False}

{'type': 'object', 'anyOf': [{'not': {'required': ['error']}, 'required': ['homologs', 'totalCount', 'queryId', 'querySpecies', 'queryType']}, {'required': ['error']}], '$schema': 'https://json-schema.org/draft/2020-12/schema', 'properties': {'cap': {'type': 'number', 'description': 'The max_results limit applied to the homolog list.'}, 'error': {'type': 'object', 'required': ['code', 'message'], 'properties': {'code': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': -9007199254740991, 'description': 'JSON-RPC error code for this failure.'}, 'data': {'type': 'object', 'properties': {'reason': {'type': 'string', 'examples': ['not_found', 'no_input', 'conflicting_input'], 'description': 'Machine-readable failure mode. Declared by this tool: `not_found`: The gene symbol or stable ID was not found in Ensembl. `no_input`: Neither symbol nor id was provided. `conflicting_input`: Both symbol and id were provided. Other values are possible when a failure originates below the handler.'}, 'recovery': {'type': 'object', 'required': ['hint'], 'properties': {'hint': {'type': 'string'}}, 'description': 'Actionable next step for the caller.', 'additionalProperties': {}}, 'retryable': {'type': 'boolean', 'description': 'Whether retrying may succeed.'}}, 'additionalProperties': {}}, 'message': {'type': 'string', 'description': 'Human-readable description of what went wrong.'}}, 'description': 'Present when the call failed. Absent on success.', 'additionalProperties': {}}, 'shown': {'type': 'number', 'description': 'Number of homologs returned after the max_results cap.'}, 'notice': {'type': 'string', 'description': 'Guidance when no homologs are found or the list was capped.'}, 'queryId': {'type': 'string', 'description': 'The resolved Ensembl gene ID used for the homology query.'}, 'homologs': {'type': 'array', 'items': {'type': 'object', 'required': ['targetId'], 'properties': {'type': {'type': 'string', 'description': 'Homology type: ortholog_one2one, ortholog_one2many, ortholog_many2many, paralog_many2many, within_species_paralog, or similar.'}, 'percId': {'type': 'number', 'description': 'Percent identity between the query and target gene sequences (0-100). Higher values indicate more conserved sequences.'}, 'percPos': {'type': 'number', 'description': 'Percent positive (similar) positions in the alignment (0-100). Includes conservative substitutions as well as identical residues.'}, 'targetId': {'type': 'string', 'description': 'Ensembl stable ID of the homologous gene in the target species.'}, 'targetSpecies': {'type': 'string', 'description': 'Target species in Ensembl internal format (e.g. mus_musculus).'}, 'taxonomyLevel': {'type': 'string', 'description': 'Last common ancestor taxonomic level for this homology relationship (e.g. Amniota, Vertebrata, Bilateria).'}}, 'description': 'A single homologous gene with its stable ID, species, homology type, and sequence identity metrics.', 'additionalProperties': False}, 'description': 'Homologous genes found for the query gene, capped to max_results. totalCount reports the full count available before the cap.'}, 'queryType': {'type': 'string', 'description': 'The homology type queried (orthologues, paralogues, or all).'}, 'truncated': {'type': 'boolean', 'description': 'True when the homolog list was capped at max_results.'}, 'totalCount': {'type': 'number', 'description': 'Total number of homologs available before the max_results cap. Exceeds the returned homologs count when the list was capped.'}, 'querySpecies': {'type': 'string', 'description': 'The source species used for the query.'}}, 'additionalProperties': False}

{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['id'], 'properties': {'id': {'type': 'string', 'minLength': 1, 'description': 'Ensembl stable ID (ENSGâ\x80¦, ENSTâ\x80¦, ENSPâ\x80¦) or a genomic region for region mode. Region accepts species:chr:start-end (e.g. homo_sapiens:13:32315086-32400268) or a bare chr:start-end (e.g. 13:32315086-32400268) when the species field is set. A region needs start at or below end, within the sequence region, and spans at most 10,000,000 bases.'}, 'type': {'enum': ['genomic', 'cdna', 'cds', 'protein'], 'type': 'string', 'default': 'genomic', 'description': 'Sequence type to retrieve. genomic: full genomic DNA including introns (default). cdna: spliced transcript sequence (requires ENSTâ\x80¦ ID). cds: coding sequence only, no UTRs (requires ENSTâ\x80¦ ID with coding transcript). protein: amino acid sequence (requires ENSTâ\x80¦ or ENSPâ\x80¦ ID). Region ids are genomic-only â\x80\x94 request cdna, cds, or protein from a transcript or protein stable ID.'}, 'offset': {'type': 'integer', 'default': 0, 'maximum': 9007199254740991, 'minimum': 0, 'description': '0-based character offset where the returned window starts, counted in the resolved sequence (including any expand_5prime/expand_3prime flank). Default 0. Pass nextOffset from a truncated response to fetch the following window; an offset at or past the end returns an empty window.'}, 'species': {'type': 'string', 'description': 'Species in Ensembl internal format (e.g. homo_sapiens). Required for a bare chr:start-end region; optional for the species:chr:start-end form (the embedded species is used when the field is omitted). Optional for stable ID lookups â\x80\x94 Ensembl infers species from the ID prefix.'}, 'max_length': {'type': 'integer', 'default': 10000, 'maximum': 9007199254740991, 'minimum': 0, 'description': 'Maximum number of characters in the returned window. Default 10000. Set to 0 to return everything from offset to the end, uncapped.'}, 'expand_3prime': {'type': 'integer', 'default': 0, 'maximum': 9007199254740991, 'minimum': 0, 'description': "Number of base pairs to extend downstream (3' direction) of the requested feature. Default 0. Only applies to genomic sequences and region queries."}, 'expand_5prime': {'type': 'integer', 'default': 0, 'maximum': 9007199254740991, 'minimum': 0, 'description': "Number of base pairs to extend upstream (5' direction) of the requested feature. Default 0. Only applies to genomic sequences and region queries."}}, 'additionalProperties': False}

{'type': 'object', 'anyOf': [{'not': {'required': ['error']}, 'required': ['id', 'type', 'seq', 'length', 'offset', 'truncated']}, {'required': ['error']}], '$schema': 'https://json-schema.org/draft/2020-12/schema', 'properties': {'id': {'type': 'string', 'description': 'The stable ID or region used for the lookup.'}, 'seq': {'type': 'string', 'description': 'The requested window of the sequence: at most max_length characters starting at offset. DNA sequences use IUPAC nucleotide codes (ACGT + ambiguity codes); protein sequences use single-letter amino acid codes. Empty when offset is at or past the end.'}, 'type': {'type': 'string', 'description': 'Sequence type returned (genomic, cdna, cds, or protein).'}, 'error': {'type': 'object', 'required': ['code', 'message'], 'properties': {'code': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': -9007199254740991, 'description': 'JSON-RPC error code for this failure.'}, 'data': {'type': 'object', 'properties': {'reason': {'type': 'string', 'examples': ['not_found', 'type_mismatch', 'missing_species', 'invalid_region'], 'description': 'Machine-readable failure mode. Declared by this tool: `not_found`: The stable ID or region was not found in Ensembl. `type_mismatch`: A non-genomic type (cdna, cds, or protein) was requested for a region id or a gene ID. `missing_species`: A bare chr:start-end region was given without a species. `invalid_region`: A region id has its start after its end, starts past the end of its sequence region, spans more than the 10,000,000-base maximum, or names a sequence region the species lacks. Other values are possible when a failure originates below the handler.'}, 'recovery': {'type': 'object', 'required': ['hint'], 'properties': {'hint': {'type': 'string'}}, 'description': 'Actionable next step for the caller.', 'additionalProperties': {}}, 'retryable': {'type': 'boolean', 'description': 'Whether retrying may succeed.'}}, 'additionalProperties': {}}, 'message': {'type': 'string', 'description': 'Human-readable description of what went wrong.'}}, 'description': 'Present when the call failed. Absent on success.', 'additionalProperties': {}}, 'length': {'type': 'number', 'description': 'Full sequence length in characters, not the window size â\x80\x94 nucleotides for genomic/cdna/cds, amino-acid residues for protein. Includes any expand_5prime/expand_3prime flank.'}, 'notice': {'type': 'string', 'description': 'Guidance about the window: how to continue when truncated, or why it is empty when the offset is past the end.'}, 'offset': {'type': 'number', 'description': '0-based character offset where this window starts.'}, 'truncated': {'type': 'boolean', 'description': 'True when more sequence follows this window; request nextOffset to continue.'}, 'nextOffset': {'type': 'number', 'description': 'Offset of the first character after this window â\x80\x94 pass it as offset to fetch the next window. Present only when truncated.'}, 'description': {'type': 'string', 'description': 'Sequence description from Ensembl, if provided.'}}, 'additionalProperties': False}

{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['id'], 'properties': {'id': {'type': 'string', 'minLength': 1, 'description': 'Ensembl stable gene ID (ENSGâ\x80¦) or transcript ID (ENSTâ\x80¦). Use ensembl_lookup_gene to get the stable ID from a gene symbol. xrefs/id returns the full cross-reference set (56+ entries for well-annotated genes like BRCA2).'}, 'dbname': {'type': 'string', 'description': 'Filter to a specific external database by its Ensembl internal name. Examples: HGNC (HGNC gene ID), Uniprot_gn (UniProt gene name), EntrezGene (NCBI Gene ID), MIM_GENE (OMIM disease gene), RefSeq_mRNA (NCBI RefSeq transcript), Reactome (pathway IDs), GO (Gene Ontology terms). Omit to return all available xrefs.'}}, 'additionalProperties': False}

{'type': 'object', 'anyOf': [{'not': {'required': ['error']}, 'required': ['xrefs', 'totalCount', 'queriedId']}, {'required': ['error']}], '$schema': 'https://json-schema.org/draft/2020-12/schema', 'properties': {'error': {'type': 'object', 'required': ['code', 'message'], 'properties': {'code': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': -9007199254740991, 'description': 'JSON-RPC error code for this failure.'}, 'data': {'type': 'object', 'properties': {'reason': {'type': 'string', 'examples': ['not_found'], 'description': 'Machine-readable failure mode. Declared by this tool: `not_found`: The Ensembl stable ID was not found or has no cross-references. Other values are possible when a failure originates below the handler.'}, 'recovery': {'type': 'object', 'required': ['hint'], 'properties': {'hint': {'type': 'string'}}, 'description': 'Actionable next step for the caller.', 'additionalProperties': {}}, 'retryable': {'type': 'boolean', 'description': 'Whether retrying may succeed.'}}, 'additionalProperties': {}}, 'message': {'type': 'string', 'description': 'Human-readable description of what went wrong.'}}, 'description': 'Present when the call failed. Absent on success.', 'additionalProperties': {}}, 'xrefs': {'type': 'array', 'items': {'type': 'object', 'properties': {'dbname': {'type': 'string', 'description': 'Database name in Ensembl internal format (e.g. HGNC, Uniprot_gn, EntrezGene, MIM_GENE, RefSeq_mRNA).'}, 'displayId': {'type': 'string', 'description': 'Display identifier â\x80\x94 often the same as primaryId but may be a formatted accession.'}, 'primaryId': {'type': 'string', 'description': 'Primary identifier in the external database (e.g. HGNC:1101 for BRCA2 in HGNC, P51587 for BRCA2 in UniProt).'}, 'description': {'type': 'string', 'description': 'Description of the cross-reference entry.'}, 'dbDisplayName': {'type': 'string', 'description': 'Human-readable database display name.'}}, 'description': 'A single cross-database reference entry with database name, primary ID, and description.', 'additionalProperties': False}, 'description': 'Cross-database references for the queried Ensembl ID.'}, 'notice': {'type': 'string', 'description': 'Guidance when no cross-references are found.'}, 'queriedId': {'type': 'string', 'description': 'The Ensembl stable ID that was queried.'}, 'totalCount': {'type': 'number', 'description': 'Total number of cross-references returned.'}}, 'additionalProperties': False}

{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'properties': {'division': {'enum': ['EnsemblVertebrates', 'EnsemblPlants', 'EnsemblFungi', 'EnsemblMetazoa', 'EnsemblProtists'], 'type': 'string', 'description': 'Filter to a specific Ensembl division. EnsemblVertebrates includes human, mouse, zebrafish, and other vertebrates. EnsemblPlants covers crop and model plant genomes. EnsemblFungi, EnsemblMetazoa, EnsemblProtists cover non-vertebrate model organisms. Omit to return the endpoint default division (vertebrates).'}, 'nameContains': {'type': 'string', 'description': 'Case-insensitive substring filter applied locally after fetching. Matches against species name, display name, and common name. Example: "sapiens" matches homo_sapiens; "mouse" matches mus_musculus.'}}, 'additionalProperties': False}

{'type': 'object', 'anyOf': [{'not': {'required': ['error']}, 'required': ['species', 'totalCount']}, {'required': ['error']}], '$schema': 'https://json-schema.org/draft/2020-12/schema', 'properties': {'error': {'type': 'object', 'required': ['code', 'message'], 'properties': {'code': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': -9007199254740991, 'description': 'JSON-RPC error code for this failure.'}, 'data': {'type': 'object', 'properties': {'reason': {'type': 'string', 'description': 'Machine-readable failure mode.'}, 'recovery': {'type': 'object', 'required': ['hint'], 'properties': {'hint': {'type': 'string'}}, 'description': 'Actionable next step for the caller.', 'additionalProperties': {}}, 'retryable': {'type': 'boolean', 'description': 'Whether retrying may succeed.'}}, 'additionalProperties': {}}, 'message': {'type': 'string', 'description': 'Human-readable description of what went wrong.'}}, 'description': 'Present when the call failed. Absent on success.', 'additionalProperties': {}}, 'notice': {'type': 'string', 'description': 'Guidance when the filter matches no species.'}, 'species': {'type': 'array', 'items': {'type': 'object', 'required': ['name'], 'properties': {'name': {'type': 'string', 'description': 'Ensembl internal species name in lowercase_underscore format (e.g. homo_sapiens, mus_musculus). This is the value to pass as the species parameter in all other Ensembl tools.'}, 'taxonId': {'type': 'string', 'description': 'NCBI taxonomy ID for this species.'}, 'assembly': {'type': 'string', 'description': 'Current genome assembly name (e.g. GRCh38).'}, 'division': {'type': 'string', 'description': 'Ensembl division this species belongs to (e.g. EnsemblVertebrates, EnsemblPlants).'}, 'commonName': {'type': 'string', 'description': 'Common name (e.g. Human, Mouse).'}, 'displayName': {'type': 'string', 'description': 'Human-readable scientific name (e.g. Homo sapiens).'}}, 'description': 'A single Ensembl species entry.', 'additionalProperties': False}, 'description': 'Species matching the filter criteria, sorted by internal name.'}, 'totalCount': {'type': 'number', 'description': 'Total number of matching species after local filtering.'}}, 'additionalProperties': False}

{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'properties': {'id': {'type': 'string', 'description': 'Ensembl stable gene ID (e.g. ENSG00000139618 or ENSG00000139618.7 with version). Species is not required for ID lookup.'}, 'ids': {'type': 'array', 'items': {'type': 'string', 'minLength': 1, 'description': 'An Ensembl stable gene or transcript ID to resolve in this batch.'}, 'maxItems': 20, 'description': 'Batch lookup: up to 20 Ensembl stable IDs (ENSGâ\x80¦, ENSTâ\x80¦). Returns a succeeded/failed split. Provide exactly one of symbol, id, ids, or symbols.'}, 'symbol': {'type': 'string', 'description': 'Gene symbol to look up (e.g. BRCA2, TP53, EGFR). Species defaults to homo_sapiens; set species for other organisms. Case-insensitive in most species.'}, 'species': {'type': 'string', 'description': 'Species in Ensembl internal format: lowercase scientific name with underscores (e.g. homo_sapiens, mus_musculus, danio_rerio). Optional for symbol lookups â\x80\x94 defaults to homo_sapiens; set it for other organisms. Use ensembl_list_species to discover valid values.'}, 'symbols': {'type': 'array', 'items': {'type': 'string', 'minLength': 1, 'description': 'A gene symbol to resolve in this batch (e.g. BRCA2, TP53).'}, 'maxItems': 20, 'description': 'Batch lookup: up to 20 gene symbols. Species defaults to homo_sapiens; set species for other organisms. Returns a succeeded/failed split. Provide exactly one of symbol, id, ids, or symbols.'}, 'expand_transcripts': {'type': 'boolean', 'default': False, 'description': 'When true, include the full transcript list in the response. Each transcript has its ID, biotype, canonical flag, and coordinates. Default is false to keep responses compact.'}}, 'additionalProperties': False}

{'type': 'object', 'anyOf': [{'not': {'required': ['error']}}, {'required': ['error']}], '$schema': 'https://json-schema.org/draft/2020-12/schema', 'properties': {'gene': {'type': 'object', 'required': ['id'], 'properties': {'id': {'type': 'string', 'description': 'Ensembl gene stable ID (ENSGâ\x80¦). Use this as input to other Ensembl tools.'}, 'end': {'type': 'number', 'description': 'Gene end position on the chromosome (1-based).'}, 'start': {'type': 'number', 'description': 'Gene start position on the chromosome (1-based).'}, 'strand': {'type': 'number', 'description': 'Strand: 1 for forward, -1 for reverse.'}, 'biotype': {'type': 'string', 'description': 'Gene biotype (e.g. protein_coding, lncRNA, pseudogene).'}, 'species': {'type': 'string', 'description': 'Species in Ensembl internal format (e.g. homo_sapiens). Echoed from lookup.'}, 'chromosome': {'type': 'string', 'description': 'Chromosome or sequence region name.'}, 'description': {'type': 'string', 'description': 'Brief gene description from Ensembl.'}, 'displayName': {'type': 'string', 'description': 'Gene symbol or display name (e.g. BRCA2, TP53).'}, 'transcripts': {'type': 'array', 'items': {'type': 'object', 'required': ['id', 'isCanonical'], 'properties': {'id': {'type': 'string', 'description': 'Ensembl transcript stable ID (ENSTâ\x80¦).'}, 'end': {'type': 'number', 'description': 'Transcript end position on the chromosome (1-based).'}, 'start': {'type': 'number', 'description': 'Transcript start position on the chromosome (1-based).'}, 'strand': {'type': 'number', 'description': 'Strand: 1 for forward, -1 for reverse.'}, 'biotype': {'type': 'string', 'description': 'Transcript biotype (e.g. protein_coding, lncRNA, retained_intron).'}, 'lengthInBp': {'type': 'number', 'description': 'Transcript length in base pairs.'}, 'displayName': {'type': 'string', 'description': 'Transcript display name.'}, 'isCanonical': {'type': 'boolean', 'description': 'True when this is the canonical transcript for the gene.'}}, 'description': 'A single transcript summary entry.', 'additionalProperties': False}, 'description': 'Transcript list. Present only when expand_transcripts is true.'}, 'assemblyName': {'type': 'string', 'description': 'Genome assembly name (e.g. GRCh38). All coordinates are relative to this assembly.'}}, 'description': 'Single gene record. Present for symbol or id lookups.', 'additionalProperties': False}, 'batch': {'type': 'object', 'required': ['succeeded', 'failed'], 'properties': {'failed': {'type': 'array', 'items': {'type': 'object', 'properties': {}, 'description': 'A failed lookup entry with query (the submitted ID or symbol) and error (reason string) fields.', 'additionalProperties': {}}, 'description': 'IDs/symbols that could not be resolved, with per-item query and error fields.'}, 'succeeded': {'type': 'array', 'items': {'type': 'object', 'properties': {}, 'description': 'A resolved gene record with the same shape as the gene output field.', 'additionalProperties': {}}, 'description': 'Gene records for IDs/symbols that resolved successfully. Same shape as gene.'}}, 'description': 'Batch results. Present for ids or symbols lookups.', 'additionalProperties': False}, 'error': {'type': 'object', 'required': ['code', 'message'], 'properties': {'code': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': -9007199254740991, 'description': 'JSON-RPC error code for this failure.'}, 'data': {'type': 'object', 'properties': {'reason': {'type': 'string', 'examples': ['not_found', 'invalid_species', 'no_input', 'conflicting_input'], 'description': 'Machine-readable failure mode. Declared by this tool: `not_found`: The gene symbol or stable ID was not found in Ensembl. `invalid_species`: The species string was not recognized by Ensembl. `no_input`: Neither symbol, id, ids, nor symbols was provided. `conflicting_input`: More than one of symbol, id, ids, or symbols was provided. Other values are possible when a failure originates below the handler.'}, 'recovery': {'type': 'object', 'required': ['hint'], 'properties': {'hint': {'type': 'string'}}, 'description': 'Actionable next step for the caller.', 'additionalProperties': {}}, 'retryable': {'type': 'boolean', 'description': 'Whether retrying may succeed.'}}, 'additionalProperties': {}}, 'message': {'type': 'string', 'description': 'Human-readable description of what went wrong.'}}, 'description': 'Present when the call failed. Absent on success.', 'additionalProperties': {}}}, 'additionalProperties': False}

{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['variant'], 'properties': {'species': {'type': 'string', 'default': 'homo_sapiens', 'minLength': 1, 'description': 'Species in Ensembl internal format. Default is homo_sapiens. For non-human variants, set the appropriate species (e.g. mus_musculus for mouse). Use ensembl_list_species to discover valid values.'}, 'variant': {'type': 'string', 'minLength': 1, 'description': 'Variant in one of three formats: (1) HGVS notation â\x80\x94 transcript-relative: ENST00000380152.8:c.2T>A; genomic: 13:g.32316462T>A; (2) Region+allele: chr:start:end:strand/allele â\x80\x94 e.g. 1:65568:65568:1/T (strand is 1 for forward or -1 for reverse); (3) dbSNP rsID â\x80\x94 e.g. rs334. Ensembl normalizes chromosome names; canonical vertebrate output omits the "chr" prefix, though a chr-prefixed name is also accepted.'}, 'max_pubmed_ids_per_variant': {'type': 'integer', 'default': 10, 'maximum': 9007199254740991, 'minimum': 0, 'description': 'Maximum PubMed IDs to return per colocated known variant. Well-studied variants (e.g. rs334) cite 100+ papers; the default trims each list. Set to 0 to return every PubMed ID uncapped. pubmedTotal on each colocated variant reports the true pre-cap count. Ignored when include_all_colocated_pubmed is true.'}, 'max_transcript_consequences': {'type': 'integer', 'default': 10, 'maximum': 9007199254740991, 'minimum': 0, 'description': 'Maximum transcript consequences to return per VEP record. High-impact variants can affect 60+ transcripts; the default keeps the response focused on the top consequences. Set to 0 to return every transcript consequence uncapped. transcriptConsequencesTotal on each record always reports the true pre-cap count.'}, 'include_all_colocated_pubmed': {'type': 'boolean', 'default': False, 'description': 'When true, return every PubMed ID for each colocated variant, overriding max_pubmed_ids_per_variant. Default false to keep responses compact.'}}, 'additionalProperties': False}

{'type': 'object', 'anyOf': [{'not': {'required': ['error']}, 'required': ['results', 'totalCount']}, {'required': ['error']}], '$schema': 'https://json-schema.org/draft/2020-12/schema', 'properties': {'cap': {'type': 'number', 'description': 'The max_transcript_consequences limit applied.'}, 'error': {'type': 'object', 'required': ['code', 'message'], 'properties': {'code': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': -9007199254740991, 'description': 'JSON-RPC error code for this failure.'}, 'data': {'type': 'object', 'properties': {'reason': {'type': 'string', 'examples': ['invalid_notation', 'not_found'], 'description': 'Machine-readable failure mode. Declared by this tool: `invalid_notation`: The variant notation is malformed or cannot be parsed by VEP. `not_found`: The variant location falls outside any known transcript or assembly region. Other values are possible when a failure originates below the handler.'}, 'recovery': {'type': 'object', 'required': ['hint'], 'properties': {'hint': {'type': 'string'}}, 'description': 'Actionable next step for the caller.', 'additionalProperties': {}}, 'retryable': {'type': 'boolean', 'description': 'Whether retrying may succeed.'}}, 'additionalProperties': {}}, 'message': {'type': 'string', 'description': 'Human-readable description of what went wrong.'}}, 'description': 'Present when the call failed. Absent on success.', 'additionalProperties': {}}, 'shown': {'type': 'number', 'description': 'Total transcript consequences returned across all records after the cap.'}, 'notice': {'type': 'string', 'description': 'Guidance when no results are returned or when caps omitted detail.'}, 'results': {'type': 'array', 'items': {'type': 'object', 'required': ['transcriptConsequences', 'colocatedVariants'], 'properties': {'end': {'type': 'number', 'description': 'Variant end position (1-based).'}, 'input': {'type': 'string', 'description': 'The input variant notation as submitted to VEP.'}, 'start': {'type': 'number', 'description': 'Variant start position (1-based).'}, 'chromosome': {'type': 'string', 'description': 'Chromosome the variant is on.'}, 'assemblyName': {'type': 'string', 'description': 'Genome assembly name (e.g. GRCh38).'}, 'colocatedVariants': {'type': 'array', 'items': {'type': 'object', 'properties': {'id': {'type': 'string', 'description': 'Known variant ID (e.g. rs1234567 for dbSNP entries).'}, 'pubmed': {'type': 'array', 'items': {'type': 'number', 'description': 'A PubMed ID for literature citing this variant.'}, 'description': 'PubMed IDs for literature associated with this variant, capped to max_pubmed_ids_per_variant. pubmedTotal reports the full count when the list was capped.'}, 'pubmedTotal': {'type': 'number', 'description': 'Total PubMed IDs available for this variant before the max_pubmed_ids_per_variant cap. Equals the returned pubmed length when the list was not capped.'}, 'alleleString': {'type': 'string', 'description': 'Allele string showing reference/alternate (e.g. A/T).'}, 'clinicalSignificance': {'type': 'array', 'items': {'type': 'string', 'description': 'A clinical significance term for this colocated known variant.'}, 'description': 'Clinical significance terms from ClinVar (e.g. pathogenic, benign).'}}, 'description': 'A known variant at the same genomic position from public databases (dbSNP, ClinVar).', 'additionalProperties': False}, 'description': 'Known variants at the same position from public databases (dbSNP, ClinVar). Empty when the variant is novel.'}, 'mostSevereConsequence': {'type': 'string', 'description': 'Most severe Sequence Ontology consequence term across all transcripts (e.g. stop_gained, missense_variant, synonymous_variant).'}, 'transcriptConsequences': {'type': 'array', 'items': {'type': 'object', 'required': ['consequenceTerms'], 'properties': {'sift': {'type': 'object', 'required': ['prediction', 'score'], 'properties': {'score': {'type': 'number', 'description': 'SIFT score (0-1). Lower scores indicate more deleterious variants.'}, 'prediction': {'type': 'string', 'description': 'SIFT prediction: deleterious or tolerated.'}}, 'description': 'SIFT pathogenicity prediction for missense variants. Omitted when not applicable.', 'additionalProperties': False}, 'hgvsc': {'type': 'string', 'description': 'HGVS notation at the cDNA level (e.g. c.2T>A).'}, 'hgvsp': {'type': 'string', 'description': 'HGVS notation at the protein level (e.g. p.Met1Thr).'}, 'geneId': {'type': 'string', 'description': 'Ensembl gene ID (ENSGâ\x80¦) harboring the affected transcript.'}, 'impact': {'type': 'string', 'description': 'Impact level: HIGH (frameshift, stop_gained), MODERATE (missense), LOW (synonymous), or MODIFIER.'}, 'biotype': {'type': 'string', 'description': 'Transcript biotype (e.g. protein_coding).'}, 'polyphen': {'type': 'object', 'required': ['prediction', 'score'], 'properties': {'score': {'type': 'number', 'description': 'PolyPhen score (0-1). Higher scores indicate more damaging variants.'}, 'prediction': {'type': 'string', 'description': 'PolyPhen prediction: probably_damaging, possibly_damaging, or benign.'}}, 'description': 'PolyPhen pathogenicity prediction for missense variants. Omitted when not applicable.', 'additionalProperties': False}, 'aminoAcids': {'type': 'string', 'description': 'Reference/alternate amino acids separated by "/" (e.g. M/T).'}, 'geneSymbol': {'type': 'string', 'description': 'Gene symbol (e.g. BRCA2, TP53).'}, 'transcriptId': {'type': 'string', 'description': 'Ensembl transcript ID (ENSTâ\x80¦) affected by this variant.'}, 'consequenceTerms': {'type': 'array', 'items': {'type': 'string', 'description': 'A Sequence Ontology consequence term (e.g. missense_variant, stop_gained).'}, 'description': 'Sequence Ontology consequence terms for this transcript.'}}, 'description': 'Consequence details for one affected transcript, including impact, HGVS notation, and pathogenicity scores.', 'additionalProperties': False}, 'description': 'Per-transcript consequence details, capped to max_transcript_consequences. High-impact variants may affect many transcripts; focus on canonical transcripts (isCanonical from ensembl_lookup_gene) for primary effect. transcriptConsequencesTotal reports the full count.'}, 'transcriptConsequencesTotal': {'type': 'number', 'description': 'Total transcript consequences available before the max_transcript_consequences cap. Equals the returned transcriptConsequences length when not capped.'}}, 'description': 'VEP consequence record for one genomic position, with transcript consequences and colocated known variants.', 'additionalProperties': False}, 'description': 'VEP consequence records â\x80\x94 typically one per input variant. Multiple records appear when a single notation matches multiple genomic positions.'}, 'truncated': {'type': 'boolean', 'description': 'True when transcript consequences were capped at max_transcript_consequences.'}, 'totalCount': {'type': 'number', 'description': 'Number of VEP consequence records returned.'}}, 'additionalProperties': False}

{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['species', 'region'], 'properties': {'region': {'type': 'string', 'minLength': 1, 'description': 'Genomic region in chr:start-end format (e.g. 13:32315086-32400268). Ensembl serves at most 5,000,000 bases per region; split a larger area into smaller windows. Ensembl normalizes chromosome names and canonical vertebrate output omits the chr prefix (13, not chr13); a chr-prefixed name like chr13 is also accepted. For large regions (>100 kb), limit to gene feature type to avoid overwhelming results.'}, 'biotype': {'type': 'string', 'description': 'Optional biotype filter (e.g. protein_coding, lncRNA, SNV). Applied server-side by Ensembl. Not all feature types support biotype filtering.'}, 'feature': {'type': 'array', 'items': {'enum': ['gene', 'transcript', 'variation', 'regulatory', 'exon'], 'type': 'string', 'description': 'A feature type to retrieve: gene, transcript, variation, regulatory, or exon.'}, 'default': ['gene'], 'minItems': 1, 'description': 'Feature types to retrieve â\x80\x94 at least one. Default is gene only. Requesting variation in a large region can match tens of thousands of features. Include variation only for targeted small regions (single gene loci or smaller).'}, 'species': {'type': 'string', 'minLength': 1, 'description': 'Species in Ensembl internal format (e.g. homo_sapiens, mus_musculus). Use ensembl_list_species to discover valid values.'}, 'max_results': {'type': 'integer', 'default': 100, 'maximum': 9007199254740991, 'minimum': 0, 'description': 'Maximum number of features to return. A gene-length region can hold tens of thousands of variation features; the default keeps the response compact. Set to 0 to return every feature uncapped. totalCount always reports the true number found before this cap.'}}, 'additionalProperties': False}

{'type': 'object', 'anyOf': [{'not': {'required': ['error']}, 'required': ['features', 'totalCount', 'region', 'species']}, {'required': ['error']}], '$schema': 'https://json-schema.org/draft/2020-12/schema', 'properties': {'cap': {'type': 'number', 'description': 'The max_results limit applied to the feature list.'}, 'error': {'type': 'object', 'required': ['code', 'message'], 'properties': {'code': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': -9007199254740991, 'description': 'JSON-RPC error code for this failure.'}, 'data': {'type': 'object', 'properties': {'reason': {'type': 'string', 'examples': ['invalid_region', 'invalid_species'], 'description': 'Machine-readable failure mode. Declared by this tool: `invalid_region`: The region string could not be parsed, contains invalid coordinates, or spans more than the 5,000,000-base maximum. `invalid_species`: The species string was not recognized by Ensembl. Other values are possible when a failure originates below the handler.'}, 'recovery': {'type': 'object', 'required': ['hint'], 'properties': {'hint': {'type': 'string'}}, 'description': 'Actionable next step for the caller.', 'additionalProperties': {}}, 'retryable': {'type': 'boolean', 'description': 'Whether retrying may succeed.'}}, 'additionalProperties': {}}, 'message': {'type': 'string', 'description': 'Human-readable description of what went wrong.'}}, 'description': 'Present when the call failed. Absent on success.', 'additionalProperties': {}}, 'shown': {'type': 'number', 'description': 'Number of features returned after the max_results cap.'}, 'notice': {'type': 'string', 'description': 'Guidance about the result set: empty, large, capped, or missing assembly.'}, 'region': {'type': 'string', 'description': 'The region queried, as provided.'}, 'species': {'type': 'string', 'description': 'The species queried.'}, 'features': {'type': 'array', 'items': {'type': 'object', 'required': ['featureType', 'chromosome', 'start', 'end'], 'properties': {'id': {'type': 'string', 'description': 'Ensembl stable ID for this feature (e.g. ENSGâ\x80¦, rsâ\x80¦).'}, 'end': {'type': 'number', 'description': 'End position on the chromosome (1-based).'}, 'name': {'type': 'string', 'description': 'External name or symbol for this feature.'}, 'rank': {'type': 'number', 'description': 'Position (1-based) of an exon within its parent transcript.'}, 'start': {'type': 'number', 'description': 'Start position on the chromosome (1-based).'}, 'strand': {'type': 'number', 'description': 'Strand: 1 for forward, -1 for reverse.'}, 'biotype': {'type': 'string', 'description': 'Biotype of the feature (e.g. protein_coding, lncRNA, SNV).'}, 'parentId': {'type': 'string', 'description': 'Parent transcript ID (ENSTâ\x80¦) for exon features. An exon is reported once per parent transcript it belongs to, so the same exon ID can appear on multiple rows that differ only by this field â\x80\x94 not duplicates.'}, 'chromosome': {'type': 'string', 'description': 'Chromosome or sequence region name.'}, 'description': {'type': 'string', 'description': 'Feature description when provided.'}, 'featureType': {'type': 'string', 'description': 'Feature type: gene, transcript, variation, regulatory, or exon.'}, 'consequenceType': {'type': 'string', 'description': 'Most severe consequence type for variation features.'}, 'clinicalSignificance': {'type': 'array', 'items': {'type': 'string', 'description': 'A clinical significance term for this variant.'}, 'description': 'Clinical significance terms for variation features (e.g. pathogenic, benign).'}}, 'description': 'A single genomic feature overlapping the queried region.', 'additionalProperties': False}, 'description': 'Genomic features found in the requested region, capped to max_results. totalCount reports the full count found before the cap.'}, 'truncated': {'type': 'boolean', 'description': 'True when the feature list was capped at max_results.'}, 'totalCount': {'type': 'number', 'description': 'Total number of features found in the region before the max_results cap. Exceeds the returned features count when the list was capped.'}, 'assemblyName': {'type': 'string', 'description': 'Genome assembly the coordinates are on (e.g. GRCh38). Omitted only when it could not be resolved, in which case the notice says so.'}}, 'additionalProperties': False}