MCP Server

met-museum-mcp-server

io.github.cyanheads/met-museum-mcp-server
Media & Content Search & Research Public & reachable MCP 2025-11-25

What this MCP does

Searches The Metropolitan Museum of Art collection and retrieves detailed artwork metadata, provenance, measurements, and image links.

met_get_object
Get Met Objects
Fetch full records for one or more Met Museum object IDs. Accepts up to 20 IDs per call and returns partial success — a single 404 does not fail the whole batch; per-ID failures are reported separately. Object IDs come from met_search_collections (keyword search) or met_list_objects (browse by department or update date). Non-public-domain objects return empty image URLs. The constituents array is null for anonymous or unattributed works; tags and measurements are null when the Met records none. Records are returned whole and never truncated, so a batch of unusually large records may return fewer than requested — any that did not fit are listed in deferred[] with their sizes, to be re-requested in a follow-up call. Set includeImages to also receive the CC0 images of up to 3 returned records as image content a vision-capable model can look at.
Read only Idempotent
Input schema
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['objectIDs'], 'properties': {'objectIDs': {'type': 'array', 'items': {'type': 'integer', 'maximum': 9007199254740991, 'description': 'A Met object ID from met_search_collections or met_list_objects.', 'exclusiveMinimum': 0}, 'maxItems': 20, 'minItems': 1, 'description': 'One or more Met object IDs to fetch. Maximum 20 per call. IDs come from met_search_collections or met_list_objects. A repeated ID is fetched and returned once, at its first position. Partial failures are reported per ID rather than failing the whole batch.'}, 'includeImages': {'type': 'boolean', 'default': False, 'description': 'Also attach the web-display image (primaryImageSmall, about 600 px on the long edge) of the first 3 returned records that have hasCC0Image true, in request order, as image blocks in content[], each after a caption naming its objectID. images[] reports what happened for every returned record. The image bytes ride content[] only, so a client that hands the model only structuredContent will not show the images. Default false: no image is fetched.'}}, 'additionalProperties': False}
Output schema
{'type': 'object', 'anyOf': [{'not': {'required': ['error']}, 'required': ['objects', 'failed']}, {'required': ['error']}], '$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': ['all_not_found', 'all_failed', 'upstream_blocked', 'upstream_unavailable', 'retry_deadline_exceeded'], 'description': "Machine-readable failure mode. Declared by this tool: `all_not_found`: Every requested objectID returned a 404 â\x80\x94 all IDs are stale or invalid. `all_failed`: No object was fetched, no failure was a firewall block or a 500/502/503/504 outage, and the failures were neither all 404s nor all time-budget expiries â\x80\x94 network errors, other HTTP errors, or 404s beside expiries. `upstream_blocked`: No object was fetched and the Met API's firewall refused requests with HTTP 403 â\x80\x94 it blocks this server's address, not one object. `upstream_unavailable`: No object was fetched and a fetch exhausted its retries on HTTP 500, 502, 503, or 504 â\x80\x94 an outage on the Met API's side, not a problem with the IDs. `retry_deadline_exceeded`: No object was fetched and every fetch ran out of the call's time budget, retries and backoff included â\x80\x94 an ID whose fetch would have started after the budget was spent counts too. 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': {}}, 'failed': {'type': 'array', 'items': {'type': 'object', 'required': ['objectID', 'error'], 'properties': {'error': {'type': 'string', 'description': 'Error detail and suggested recovery action.'}, 'objectID': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': -9007199254740991, 'description': 'Object ID that could not be fetched.'}}, 'description': 'A per-ID fetch failure.', 'additionalProperties': False}, 'description': 'Object IDs that failed to fetch with per-ID error context.'}, 'images': {'type': 'array', 'items': {'type': 'object', 'required': ['objectID', 'status'], 'properties': {'status': {'enum': ['attached', 'no_cc0_image', 'over_cap', 'unavailable'], 'type': 'string', 'description': 'attached: the image rides content[], after a caption naming the objectID. no_cc0_image: the record has no CC0 image, so nothing was fetched. over_cap: 3 earlier CC0 records took the image slots â\x80\x94 request this ID among the first 3 CC0 records of another call to see its image. unavailable: the image host returned no image in time, or the URL was not on the Met image host.'}, 'objectID': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': -9007199254740991, 'description': 'Object ID of a returned record.'}}, 'description': "A returned record's image outcome.", 'additionalProperties': False}, 'description': 'Image outcome for each record in objects[], in request order; deferred and failed IDs get no entry. Present only when includeImages is true.'}, 'notice': {'type': 'string', 'description': 'How to retrieve the deferred records, with the budget applied. Present only when the batch byte budget deferred a record.'}, 'objects': {'type': 'array', 'items': {'type': 'object', 'required': ['objectID', 'title', 'isPublicDomain', 'hasCC0Image', 'primaryImage', 'primaryImageSmall', 'additionalImages', 'objectURL', 'department', 'departmentId', 'objectName', 'classification', 'isHighlight', 'isTimelineWork', 'artistPrefix', 'artistDisplayName', 'artistSuffix', 'artistRole', 'artistDisplayBio', 'artistNationality', 'artistBeginDate', 'artistEndDate', 'constituents', 'objectDate', 'objectBeginDate', 'objectEndDate', 'medium', 'dimensions', 'culture', 'period', 'dynasty', 'accessionNumber', 'accessionYear', 'creditLine', 'rightsAndReproduction', 'country', 'region', 'geography', 'measurements', 'tags', 'objectWikidata_URL', 'GalleryNumber', 'metadataDate'], 'properties': {'tags': {'anyOf': [{'type': 'array', 'items': {'type': 'object', 'required': ['term', 'AAT_URL', 'Wikidata_URL'], 'properties': {'term': {'type': 'string', 'description': 'Tag label (e.g., "Men", "Self-portraits", "Flowers").'}, 'AAT_URL': {'type': 'string', 'description': 'Getty Art & Architecture Thesaurus URL for the term.'}, 'Wikidata_URL': {'type': 'string', 'description': 'Wikidata entity URL for the term. Useful for enrichment.'}}, 'description': 'A controlled vocabulary tag applied to the object.', 'additionalProperties': False}}, {'type': 'null'}], 'description': 'Controlled vocabulary tags applied to the object. Null when no tags assigned.'}, 'title': {'type': 'string', 'description': 'Object title as catalogued.'}, 'medium': {'type': 'string', 'description': 'Materials and techniques (e.g., "Oil on canvas", "Bronze", "Limestone").'}, 'period': {'type': 'string', 'description': 'Historical period (e.g., "New Kingdom, Ramesside", "Meiji period"). Often empty.'}, 'region': {'type': 'string', 'description': 'Geographic region of origin. Often empty.'}, 'country': {'type': 'string', 'description': 'Country of origin. Often empty.'}, 'culture': {'type': 'string', 'description': 'Cultural origin when not attributed to an individual (e.g., "Japanese", "Roman"). Often empty for Western art with named artists.'}, 'dynasty': {'type': 'string', 'description': 'Dynasty for applicable cultures (e.g., "Dynasty 19"). Often empty.'}, 'objectID': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': -9007199254740991, 'description': 'Unique Met object identifier.'}, 'geography': {'type': 'object', 'required': ['geographyType', 'city', 'state', 'county', 'subregion', 'locale', 'locus', 'excavation', 'river'], 'properties': {'city': {'type': 'string', 'description': 'City of origin or findspot (e.g., "Damascus", "Constantinople (?)", "Springfield"). The most widely populated field of this block outside the archaeological departments; empty when the Met records no city.'}, 'locus': {'type': 'string', 'description': 'Specific findspot within the locale (e.g., "burial chamber"). Excavated objects only.'}, 'river': {'type': 'string', 'description': 'Associated river. Empty on nearly every record.'}, 'state': {'type': 'string', 'description': 'State or province of origin (e.g., "Massachusetts"). Sparse, and concentrated in departments that catalogue a manufacturing place. Empty when the Met records none.'}, 'county': {'type': 'string', 'description': 'County of origin. Empty on nearly every record.'}, 'locale': {'type': 'string', 'description': 'Named place within the site (e.g., "Late Period cemetery, Tomb of Harkhebit"). Excavated objects only.'}, 'subregion': {'type': 'string', 'description': 'Sub-region or site within the region (e.g., "Saqqara", "Deir el-Bahri"). Commonly populated for archaeological departments, empty elsewhere.'}, 'excavation': {'type': 'string', 'description': 'Excavation that recovered the object (e.g., "MMA excavations, 1928-29"). Excavated objects only.'}, 'geographyType': {'type': 'string', 'description': 'How the object relates to the place (e.g., "From", "Original", "Probably originally from"). Empty when the Met records no findspot.'}}, 'description': 'Findspot detail beyond the top-level country and region, which are not repeated here. Every field is an empty string when the Met records nothing; population concentrates in the archaeological departments.', 'additionalProperties': False}, 'objectURL': {'type': 'string', 'description': 'Canonical metmuseum.org page URL for human follow-up.'}, 'artistRole': {'type': 'string', 'description': 'The named person\'s role for this object (e.g., "Artist", "Maker", "Publisher", "Patron") â\x80\x94 a patron or publisher is not the maker. Empty when the record names no one.'}, 'creditLine': {'type': 'string', 'description': 'Provenance and gift/bequest attribution.'}, 'department': {'type': 'string', 'description': 'Curatorial department as the record names it (e.g., "European Paintings", "Egyptian Art"). Five departments carry a different name on their records than in met_list_departments â\x80\x94 "The American Wing", "The Michael C. Rockefeller Wing", "Costume Institute", "Robert Lehman Collection", "Modern and Contemporary Art" â\x80\x94 so match departments by departmentId, not by name.'}, 'dimensions': {'type': 'string', 'description': 'Dimensions as a formatted string (e.g., "16 x 12 1/2 in. (40.6 x 31.8 cm)").'}, 'objectDate': {'type': 'string', 'description': 'Human-readable date string (e.g., "1887", "ca. 1295â\x80\x931294 B.C.", "1700â\x80\x931800").'}, 'objectName': {'type': 'string', 'description': 'Object type or classification name (e.g., "Painting", "Statuette").'}, 'hasCC0Image': {'type': 'boolean', 'description': "True when a CC0 open-access image URL is available (primaryImage is non-empty). Distinct from met_search_collections's hasImages filter, which matches objects that have any image including copyrighted works."}, 'isHighlight': {'type': 'boolean', 'description': 'True when the Met designates this a collection highlight.'}, 'artistPrefix': {'type': 'string', 'description': 'Qualifier the Met places before artistDisplayName (e.g., "Style of", "Workshop of", "Attributed to", "Published by"). Read the two together: "Style of" with "Rembrandt" is a work in Rembrandt\'s style, not one by him. Empty when the attribution is unqualified.'}, 'artistSuffix': {'type': 'string', 'description': 'Text the Met places after artistDisplayName (e.g., "(r. 1876â\x80\x931909)", ", Paris", "(?)"). Empty when the Met records none.'}, 'constituents': {'anyOf': [{'type': 'array', 'items': {'type': 'object', 'required': ['constituentID', 'role', 'name', 'constituentULAN_URL', 'constituentWikidata_URL', 'gender'], 'properties': {'name': {'type': 'string', 'description': 'Constituent display name.'}, 'role': {'type': 'string', 'description': 'Role in relation to the object (e.g., "Artist", "Maker", "Designer").'}, 'gender': {'type': 'string', 'description': 'Gender of the constituent. Usually empty string â\x80\x94 sparsely populated in the Met catalogue.'}, 'constituentID': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': -9007199254740991, 'description': 'Constituent identifier for cross-referencing.'}, 'constituentULAN_URL': {'type': 'string', 'description': 'Getty ULAN (Union List of Artist Names) URL for the constituent. Empty when no ULAN record exists.'}, 'constituentWikidata_URL': {'type': 'string', 'description': 'Wikidata entity URL for the constituent. Useful for enrichment via wikidata-mcp-server. Empty when no Wikidata record exists.'}}, 'description': 'A person associated with the object.', 'additionalProperties': False}}, {'type': 'null'}], 'description': 'All persons associated with the object. Null for anonymous or unknown attribution.'}, 'departmentId': {'anyOf': [{'type': 'integer', 'maximum': 9007199254740991, 'minimum': -9007199254740991}, {'type': 'null'}], 'description': "The department's numeric ID, resolved from department, for the departmentId filter of met_list_objects and met_search_collections. Null when the record's department name was not recognized â\x80\x94 never a guess."}, 'measurements': {'anyOf': [{'type': 'array', 'items': {'type': 'object', 'required': ['elementName', 'elementDescription', 'elementMeasurements'], 'properties': {'elementName': {'type': 'string', 'description': 'Which part of the object was measured (e.g., "Overall", "Other", "Length").'}, 'elementDescription': {'type': 'string', 'description': 'Qualifier distinguishing this element from a sibling with the same name (e.g., "Print" vs "Negativ"). Empty when the Met records none.'}, 'elementMeasurements': {'type': 'object', 'description': 'Measured axes for this element. Which keys are present varies element to element, so read the keys rather than assuming a fixed set. Empty object when the Met records no values.', 'propertyNames': {'type': 'string', 'description': 'Measurement axis (e.g., "Height", "Width", "Depth", "Length").'}, 'additionalProperties': {'type': 'number', 'description': 'Measured value â\x80\x94 centimeters for spatial axes, kilograms for weight.'}}}, 'description': 'One measured element of the object.', 'additionalProperties': False}}, {'type': 'null'}], 'description': 'Structured element measurements â\x80\x94 the numeric counterpart to the formatted dimensions string. Null when the Met records none.'}, 'metadataDate': {'type': 'string', 'description': 'When the Met last created or revised this record: an ISO 8601 UTC timestamp, as sent (e.g., "2026-10-01T04:59:29.693Z"; fractional seconds run from none to three digits). Its UTC date is what met_list_objects updatedSince compares, that day included. Empty when the Met sends none.'}, 'primaryImage': {'type': 'string', 'description': 'Full-resolution image URL (CC0 objects only; empty string for non-public-domain works).'}, 'GalleryNumber': {'type': 'string', 'description': 'Gallery room number at the museum. Empty string for objects not currently on display.'}, 'accessionYear': {'type': 'string', 'description': 'Year the Met acquired the object, as sent (e.g., "1960") â\x80\x94 occasionally a full date (e.g., "2005-02-15"). Can differ from the year in creditLine. Empty when the Met records none.'}, 'artistEndDate': {'type': 'string', 'description': 'Death year of the person artistDisplayName names, or a firm\'s closing year, as a string (e.g., "1890") â\x80\x94 that person\'s even when artistPrefix qualifies the attribution. Occasionally a full date (e.g., "1928-01-10"). Empty for a living artist, a firm still active, or an anonymous work.'}, 'objectEndDate': {'anyOf': [{'type': 'integer', 'maximum': 9007199254740991, 'minimum': -9007199254740991}, {'type': 'null'}], 'description': 'Latest date as an integer year (negative = BCE). Null under the same condition as objectBeginDate â\x80\x94 the two are null together.'}, 'classification': {'type': 'string', 'description': 'Broad classification category (e.g., "Paintings", "Ceramics").'}, 'isPublicDomain': {'type': 'boolean', 'description': 'True when the object is released under CC0 open access. Only true objects return usable image URLs.'}, 'isTimelineWork': {'type': 'boolean', 'description': "True when the work appears in the Met's art timeline."}, 'accessionNumber': {'type': 'string', 'description': "The Met's accession number for the object."}, 'artistBeginDate': {'type': 'string', 'description': 'Birth year of the person artistDisplayName names, or a firm\'s founding year, as a string (e.g., "1853") â\x80\x94 that person\'s even when artistPrefix qualifies the attribution. Occasionally a full date (e.g., "1928-01-10"). Empty for anonymous works.'}, 'objectBeginDate': {'anyOf': [{'type': 'integer', 'maximum': 9007199254740991, 'minimum': -9007199254740991}, {'type': 'null'}], 'description': 'Earliest date as an integer year (negative = BCE). Null when the Met has no machine-readable date for the work â\x80\x94 read objectDate for what is known instead, and do not treat null as year zero or substitute a default.'}, 'additionalImages': {'type': 'array', 'items': {'type': 'string', 'description': 'An additional image URL (detail shot or alternate view).'}, 'description': 'Additional image URLs (detail shots, alternate views). CC0 objects only.'}, 'artistDisplayBio': {'type': 'string', 'description': 'Artist biographical summary including nationality, birth/death place and year (e.g., "Dutch, Zundert 1853â\x80\x931890 Auvers-sur-Oise"). Empty for anonymous works.'}, 'artistDisplayName': {'type': 'string', 'description': 'Name of the person or firm the attribution names (e.g., "Vincent van Gogh"), without the qualifier in artistPrefix or the text in artistSuffix â\x80\x94 read those and artistRole with it. Empty for anonymous or unknown works.'}, 'artistNationality': {'type': 'string', 'description': 'Artist\'s nationality (e.g., "Dutch", "French"). Empty for anonymous works.'}, 'primaryImageSmall': {'type': 'string', 'description': 'Web-display image URL (about 600 px on the long edge; CC0 objects only; empty string for non-public-domain works).'}, 'objectWikidata_URL': {'type': 'string', 'description': 'Wikidata entity URL for the object itself. Enables enrichment via wikidata-mcp-server.'}, 'rightsAndReproduction': {'type': 'string', 'description': 'Rights holder and reproduction notice (e.g., "© 2026 Pollock-Krasner Foundation / Artists Rights Society (ARS), New York"). Most copyrighted records carry none, so an empty value does not make a work free to reuse â\x80\x94 isPublicDomain decides that.'}}, 'description': 'A fully fetched Met Museum object record.', 'additionalProperties': False}, 'description': 'Successfully fetched objects.'}, 'deferred': {'type': 'array', 'items': {'type': 'object', 'required': ['objectID', 'bytes'], 'properties': {'bytes': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': 0, 'description': 'Serialized structuredContent size of the withheld record â\x80\x94 the same scale the budget is measured on â\x80\x94 so a follow-up batch can be sized before it is requested.'}, 'objectID': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': -9007199254740991, 'description': 'Object ID whose record was fetched but withheld from this response.'}}, 'description': 'A record fetched successfully but withheld to keep the response bounded.', 'additionalProperties': False}, 'description': 'Records that were fetched but did not fit the callâ\x80\x99s cumulative budget on serialized structuredContent bytes, in request order. Re-call met_get_object with these IDs to retrieve them. Absent when every fetched record fit.'}}, 'additionalProperties': False}
met_list_departments
List Met Departments
Return the 19 curatorial departments at The Metropolitan Museum of Art, each with its numeric departmentId and display name — the valid values for the departmentId filter on met_search_collections and met_list_objects.
Read only Idempotent
Input schema
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'properties': {}, 'additionalProperties': False}
Output schema
{'type': 'object', 'anyOf': [{'not': {'required': ['error']}, 'required': ['departments']}, {'required': ['error']}], '$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': ['upstream_blocked', 'upstream_unavailable', 'retry_deadline_exceeded'], 'description': "Machine-readable failure mode. Declared by this tool: `upstream_blocked`: The Met API's firewall refused the request with HTTP 403 â\x80\x94 it blocks this server's address, not one endpoint. `upstream_unavailable`: The Met API answered HTTP 500, 502, 503, or 504 until the retry ladder ran out â\x80\x94 an outage on its side. `retry_deadline_exceeded`: The call's time budget ran out, retries and backoff included, before the Met API returned a successful response. 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': {}}, 'departments': {'type': 'array', 'items': {'type': 'object', 'required': ['departmentId', 'displayName'], 'properties': {'displayName': {'type': 'string', 'description': 'Human-readable department name (e.g., "European Paintings", "Egyptian Art", "Arms and Armor").'}, 'departmentId': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': -9007199254740991, 'description': 'Numeric department ID for the departmentId parameter of met_search_collections and met_list_objects.'}}, 'description': 'A Met curatorial department.', 'additionalProperties': False}, 'description': 'All 19 curatorial departments at The Metropolitan Museum of Art.'}}, 'additionalProperties': False}
met_list_objects
List Met Objects
Browse the Metropolitan Museum of Art collection without a keyword: every object ID in one curatorial department, every object whose record was created or revised on or after a date, or both together. Returns the total count and one page of IDs in ascending order, which met_get_object resolves to full records. With no filter the list is the whole collection (over 500,000 IDs). departmentId takes an ID from met_list_departments; updatedSince takes a YYYY-MM-DD date and answers "what has the Met added or revised since this day". Paging has no depth limit — pass nextOffset to continue. For keyword, classification, place, or object-date filters use met_search_collections instead. A list is cached for up to an hour, so a record revised within the last hour may not appear yet.
Read only Idempotent
Input schema
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'properties': {'limit': {'type': 'integer', 'default': 20, 'maximum': 500, 'minimum': 1, 'description': 'Maximum number of object IDs to return in this page.'}, 'offset': {'type': 'integer', 'default': 0, 'maximum': 9007199254740991, 'minimum': 0, 'description': 'Zero-based index of the first ID to return (default 0); pass the nextOffset from a previous response to continue paging. IDs are in ascending order and every one is reachable; an offset at or past total returns an empty page rather than an error.'}, 'departmentId': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': 1, 'description': 'Restrict the list to one curatorial department. Valid IDs come from met_list_departments â\x80\x94 the Met exposes a sparse set (roughly 1â\x80\x9321, with gaps); an unrecognized ID is rejected with an invalid_department error rather than answered with an empty list.'}, 'updatedSince': {'type': 'string', 'pattern': '^\\d{4}-\\d{2}-\\d{2}$', 'description': 'List only objects whose record was created or revised on or after this date, the day itself included, as YYYY-MM-DD (e.g., "2026-09-01") â\x80\x94 no time part and no other date format. It compares the UTC date of each record\'s metadataDate, which met_get_object returns. A date later than the newest update returns an empty list, not an error.'}}, 'additionalProperties': False}
Output schema
{'type': 'object', 'anyOf': [{'not': {'required': ['error']}, 'required': ['total', 'objectIDs', 'returned', 'offset', 'remaining', 'truncated', 'nextOffset']}, {'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': ['invalid_department', 'invalid_date', 'upstream_blocked', 'upstream_unavailable', 'retry_deadline_exceeded'], 'description': "Machine-readable failure mode. Declared by this tool: `invalid_department`: departmentId is provided but is not one of the Met department IDs. `invalid_date`: updatedSince has the YYYY-MM-DD shape but names no calendar day, such as 2026-02-30. `upstream_blocked`: The Met API's firewall refused the request with HTTP 403 â\x80\x94 it blocks this server's address, not one endpoint. `upstream_unavailable`: The Met API answered HTTP 500, 502, 503, or 504 to the department lookup or the ID list until the retry ladder ran out â\x80\x94 an outage on its side. `retry_deadline_exceeded`: The call's time budget ran out, retries and backoff included, before the Met API returned a successful response to the department lookup or the ID list. 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': {}}, 'total': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': -9007199254740991, 'description': 'Total number of objects matching the filters. Paging reaches every one of them â\x80\x94 there is no 10,000 window here.'}, 'notice': {'type': 'string', 'description': 'Present only when total is 0: names the filters that matched nothing and how to widen the list.'}, 'offset': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': -9007199254740991, 'description': 'The resolved offset this page was read from â\x80\x94 the offset input after its default of 0. When it is at or beyond a nonzero total, the page is empty because the offset ran past the list, not because nothing matched.'}, 'returned': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': -9007199254740991, 'description': 'Count of object IDs in this page.'}, 'objectIDs': {'type': 'array', 'items': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': -9007199254740991, 'description': 'A Met object ID.'}, 'description': 'Object IDs for this page in ascending order, up to `limit` results.'}, 'remaining': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': -9007199254740991, 'description': 'Count of IDs after this page: total minus (offset + returned), floored at 0. 0 means no further page exists.'}, 'truncated': {'type': 'boolean', 'description': 'True when IDs remain after this page (offset + returned < total); false when this page ends the list.'}, 'nextOffset': {'anyOf': [{'type': 'integer', 'maximum': 9007199254740991, 'minimum': -9007199254740991}, {'type': 'null'}], 'description': 'The offset to pass on the next call to continue paging, or null when this page ends the list (truncated is false).'}, 'effectiveQuery': {'type': 'string', 'description': 'The filters as applied, as name=value pairs with JSON-encoded values â\x80\x94 an updatedSince before 1753-01-01 shows as 1753-01-01, the date sent â\x80\x94 or "no filter (whole collection)". limit and offset are left out.'}}, 'additionalProperties': False}
met_search_collections
Search Met Collection
Search the Metropolitan Museum of Art collection by keyword and optional filters. Returns the total match count and one page of matching object IDs, which met_get_object resolves to full records. Relevance is keyword-based, not semantic; department and geographic filters narrow results more than a longer query. Paging reaches only the first 10,000 matches of any search, so narrow a larger one with filters. The medium parameter takes an object classification as the Met spells it ("Paintings", "Sculpture"), not a material like "Oil on canvas". hasImages also includes copyrighted works; CC0 status is per object, from the isPublicDomain and hasCC0Image fields on met_get_object. isHighlight accepts true only. isOnView restricts results to works currently on display in a Met gallery.
Read only Idempotent
Input schema
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['q'], 'properties': {'q': {'type': 'string', 'minLength': 1, 'description': 'Keyword query, matched across title, artist name, culture, medium, tags, and other text fields; matchField narrows the match to titles or tags. Broad terms return large ID sets. "*" matches every object, for a search narrowed by filters alone; paging still reaches only the first 10,000 matches. An accession number (e.g., "29.100.5") ranks its object first, with near-numbered objects after it â\x80\x94 confirm the match from accessionNumber on met_get_object.'}, 'limit': {'type': 'integer', 'default': 20, 'maximum': 500, 'minimum': 1, 'description': 'Maximum number of object IDs to return in this page. Paging reaches only the first 10,000 matches, so a page that would cross 10,000 is cut short there.'}, 'medium': {'type': 'string', 'description': 'Filter by object classification, case-sensitive and spelled as the Met spells it (e.g., "Paintings", "Drawings", "Prints", "Ceramics", "Sculpture", "Photographs", "Textiles") â\x80\x94 "paintings" or "Painting" matches nothing. Maps to the classification field on the object, not the materials text, so a material description like "Oil on canvas" matches nothing either; met_get_object returns an objectâ\x80\x99s classification.'}, 'offset': {'type': 'integer', 'default': 0, 'maximum': 9007199254740991, 'minimum': 0, 'description': 'Zero-based index of the first match to return (default 0); pass the nextOffset from a previous response to continue paging. Only the first 10,000 matches are reachable, so an offset at or beyond 10,000, or at or beyond total, returns an empty page rather than an error. Matches with tied relevance can change order between requests, so an ID can occasionally repeat or be skipped at a page boundary.'}, 'dateEnd': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': -9007199254740991, 'description': 'Latest object date (year, inclusive). Negative integers for BCE. Requires dateBegin.'}, 'isOnView': {'type': 'boolean', 'description': 'When true, restricts results to objects currently on display in a Met gallery; false restricts them to objects not on view. The GalleryNumber field on the met_get_object record identifies the specific gallery.'}, 'dateBegin': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': -9007199254740991, 'description': 'Earliest object date (year, inclusive). Negative integers for BCE (e.g., -500 for 500 BCE). Requires dateEnd.'}, 'hasImages': {'type': 'boolean', 'description': 'When true, restricts results to objects that have at least one associated image, including copyrighted works whose images cannot be reproduced; false restricts them to objects with none. For freely reusable CC0 images, confirm per object from the isPublicDomain and hasCC0Image fields on met_get_object.'}, 'matchField': {'enum': ['title', 'tags'], 'type': 'string', 'description': 'Restrict the keyword match to one field: "title" matches object titles only, "tags" matches subject tags only. Omit it to match across all text fields. Combines with every filter. Has no effect when q is "*".'}, 'geoLocation': {'type': 'array', 'items': {'type': 'string', 'description': 'A country, region, or city (e.g., "France", "Egypt", "New York").'}, 'maxItems': 1, 'description': 'Filter by geographic origin: one country, region, or city, as a one-element array (e.g., ["France"]). The value is matched broadly against geography fields and artist nationality. Works best with the Egyptian Art, Greek and Roman Art, and similar departments that have well-populated geography fields.'}, 'isHighlight': {'type': 'boolean', 'const': True, 'description': 'Opt-in filter, true only â\x80\x94 omit it rather than passing false, which the search ignores. Selects objects the Met has designated as highlights â\x80\x94 major works central to the collection.'}, 'departmentId': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': 1, 'description': "Restrict results to one curatorial department. Valid IDs come from met_list_departments â\x80\x94 the Met exposes a sparse set (roughly 1â\x80\x9321, with gaps); an unrecognized ID is rejected with an invalid_department error rather than silently widening the search. Can be combined with other filters. The Met searches 7 (The Cloisters) and 17 (Medieval Art) as one combined result set: for either, objectIDs keeps only the requested department's matches while total and paging count both, so a page can hold fewer than limit IDs while more remain."}}, 'additionalProperties': False}
Output schema
{'type': 'object', 'anyOf': [{'not': {'required': ['error']}, 'required': ['total', 'objectIDs', 'returned', 'truncated', 'remaining', 'nextOffset', 'offset']}, {'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': ['invalid_date_range', 'invalid_filter', 'invalid_department', 'upstream_blocked', 'upstream_unavailable', 'retry_deadline_exceeded'], 'description': "Machine-readable failure mode. Declared by this tool: `invalid_date_range`: dateBegin or dateEnd is provided without the other, or dateBegin > dateEnd. `invalid_filter`: q is whitespace-only, or medium or geoLocation was supplied blank â\x80\x94 an empty array, or an entry with no non-whitespace characters. `invalid_department`: departmentId is provided but is not one of the Met department IDs. `upstream_blocked`: The Met API's firewall refused the request with HTTP 403 â\x80\x94 it blocks this server's address, not one endpoint. `upstream_unavailable`: The Met API answered HTTP 500, 502, 503, or 504 to the department lookup or the search until the retry ladder ran out â\x80\x94 an outage on its side. `retry_deadline_exceeded`: The call's time budget ran out, retries and backoff included, before the Met API returned a successful response to the department lookup or the search. 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': {}}, 'total': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': -9007199254740991, 'description': 'Total number of objects in the Met collection matching the search. Can exceed 10,000, the most that paging reaches.'}, 'notice': {'type': 'string', 'description': 'Present when total is 0, when total exceeds 10,000, or when departmentId is 7 or 17; several apply as one string. With total 0 it says whether the keyword matches nothing or the filters removed every match, naming the filters to correct or drop. Above 10,000 it states that only the first 10,000 matches are reachable by paging, and that filters or a more specific keyword bring the rest into reach. For departmentId 7 or 17 it states that total counts both departments and a page can hold fewer than limit IDs, or that the department filter could not be applied to this page.'}, 'offset': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': -9007199254740991, 'description': 'The resolved offset this page was read from â\x80\x94 the offset input after its default of 0. When it is nonzero and at or beyond the smaller of total and 10,000, the page is empty because the offset ran past what paging reaches, not because the search found nothing.'}, 'returned': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': -9007199254740991, 'description': 'Count of object IDs in this page.'}, 'objectIDs': {'type': 'array', 'items': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': -9007199254740991, 'description': 'A Met object ID.'}, 'description': "Object IDs for this page, up to `limit` results. For departmentId 7 or 17, only the requested department's matches among the positions this page read, so it can hold fewer than `limit`, or none, while more remain."}, 'remaining': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': -9007199254740991, 'description': 'Count of reachable matches after this page: the smaller of total and 10,000, minus (offset + the positions this page read), floored at 0 â\x80\x94 positions read as described under truncated. An empty page reports 0. 0 means no further page exists.'}, 'truncated': {'type': 'boolean', 'description': 'True when reachable matches remain after this page (offset + the positions this page read < the smaller of total and 10,000); false when this page is the last one paging reaches. The positions read equal returned, except for departmentId 7 or 17, where they also count the matches the department filter left out. An empty page reports false: it ends paging even inside that window.'}, 'nextOffset': {'anyOf': [{'type': 'integer', 'maximum': 9007199254740991, 'minimum': -9007199254740991}, {'type': 'null'}], 'description': 'The offset to pass on the next call to continue paging, or null when no further page is reachable (truncated is false): offset plus the positions this page read, which for departmentId 7 or 17 can exceed returned.'}, 'effectiveQuery': {'type': 'string', 'description': 'The search as applied: q and each filter set, as name=value pairs with JSON-encoded values in parameter order, without limit or offset.'}}, 'additionalProperties': False}
Changed
met_get_object
Oct. 5, 2026, 2:45 a.m.
Changed
met_list_objects
Oct. 5, 2026, 2:45 a.m.
Changed
met_search_collections
Oct. 5, 2026, 2:45 a.m.
Changed
met_list_departments
Oct. 5, 2026, 2:45 a.m.
Changed
met_get_object
Oct. 1, 2026, 2:44 a.m.
Added
met_list_objects
Oct. 1, 2026, 2:44 a.m.
Changed
met_search_collections
Oct. 1, 2026, 2:44 a.m.
Changed
met_list_departments
Oct. 1, 2026, 2:44 a.m.
Changed
met_search_collections
Sept. 27, 2026, 2:44 a.m.
Added
met_get_object
Sept. 17, 2026, 12:41 p.m.
Added
met_search_collections
Sept. 17, 2026, 12:41 p.m.
Added
met_list_departments
Sept. 17, 2026, 12:41 p.m.