MET Museum collection via MCP — 500K+ artworks, metadata, provenance, open-access images.
Glama MCP Gateway
Connect through Glama MCP Gateway for full control over tool access and complete visibility into every call.
Full call logging
Every tool call is logged with complete inputs and outputs, so you can debug issues and audit what your agents are doing.
Tool access control
Enable or disable individual tools per connector, so you decide what your agents can and cannot do.
Managed credentials
Glama handles OAuth flows, token storage, and automatic rotation, so credentials never expire on your clients.
Usage analytics
See which tools your agents call, how often, and when, so you can understand usage patterns and catch anomalies.
Average 4.7/5 across 3 of 3 tools scored.
Each tool has a distinct, non-overlapping role: listing departments, searching collections, and retrieving object details. No ambiguity in which tool to use for a given task.
All tool names follow the 'met_' prefix with a consistent verb_noun pattern (list_departments, search_collections, get_object), making them predictable and easy to remember.
Three tools is minimal but appropriate for a focused API that covers the essential workflow: discover departments, search, and retrieve object records. Could use more (e.g., image-specific tool) but not excessive.
The tool set covers the core use case of browsing and fetching collection data. Missing features like direct image retrieval or advanced filtering are minor gaps; the search tool's parameters provide reasonable completeness.
met_get_objectGet Met ObjectsAFetch 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. Non-public-domain objects return empty image URLs. The constituents array is null for anonymous or unattributed works; tags is null for untagged objects.
| Name | Required | Description | Default |
|---|---|---|---|
| objectIDs | Yes | One or more Met object IDs to fetch. Maximum 20 per call. IDs come from met_search_collections. Partial failures are reported per ID rather than failing the whole batch. |
| Name | Required | Description |
|---|---|---|
| failed | Yes | Object IDs that failed to fetch with per-ID error context. |
| objects | Yes | Successfully fetched objects. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond annotations (readOnly, idempotent), it describes partial success handling, empty image URLs for non-public-domain, and null fields for constituents/tags. Adds valuable behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Four sentences, each essential. Front-loaded with main action, no redundancy. Efficient and clear.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given output schema exists and annotations are present, description covers batch limit, error model, and data quirks thoroughly. No missing aspects for an agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema covers 100% of parameters, but description adds context: IDs come from met_search_collections and partial failures are per-ID. Enhances understanding beyond schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it fetches full records for Met Museum object IDs, distinguishing from sibling tools like met_search_collections and met_list_departments. Verb 'Fetch' and resource 'object IDs' are specific.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It specifies the source of IDs (met_search_collections), batch limit (20 IDs), and partial success behavior. It implies when to use (after searching) but does not explicitly state alternatives or when to avoid.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
met_list_departmentsList Met DepartmentsAReturn the 19 curatorial departments at The Metropolitan Museum of Art, each with its numeric departmentId and display name — the valid values for the met_search_collections departmentId filter.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| departments | Yes | All 19 curatorial departments at The Metropolitan Museum of Art. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint and idempotentHint. The description adds that exactly 19 items are returned, providing specific behavioral detail beyond annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, front-loaded with the main action and key details, no wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no parameters and an output schema, the description is fully complete, specifying the exact count and the tool's role in supplying filter values.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters exist, baseline is 4. The description adds context about the output purpose (valid filter values) beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states that the tool returns the 19 curatorial departments with numeric departmentId and display name, and explicitly connects it to the met_search_collections departmentId filter, distinguishing it from siblings.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage when needing valid departmentId values for met_search_collections, but does not explicitly state when not to use it; however, the context is clear given no parameters and a simple enumeration.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
met_search_collectionsSearch Met CollectionASearch the Metropolitan Museum of Art collection by keyword and optional filters. Returns the total match count and a 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. The medium parameter maps to the classification field (pass "Paintings", "Drawings", etc., not material descriptions like "Oil on canvas"). isPublicDomain guarantees CC0-licensed images; hasImages also includes copyrighted works. isOnView restricts results to works currently on display in a Met gallery.
| Name | Required | Description | Default |
|---|---|---|---|
| q | Yes | Keyword query, matched across title, artist name, culture, medium, tags, and other text fields. Broad terms return large ID sets. | |
| limit | No | Maximum number of object IDs to return from the full result set. The Met search returns every match (up to tens of thousands); this caps how many IDs are returned. | |
| medium | No | Filter by object classification (e.g., "Paintings", "Drawings", "Prints", "Ceramics", "Sculpture", "Photographs", "Textiles"). Maps to the classification field on the object, not the materials/medium text field — pass a classification category name, not a material description like "Oil on canvas". | |
| offset | No | Zero-based index into the full result set to start from (default 0). The nextOffset from a previous response is the value to pass here for the next page; a broad query carries the same timeout risk on every page, so narrow it with filters if paging times out. An offset at or beyond total returns an empty page, not an error. | |
| dateEnd | No | Latest object date (year, inclusive). Negative integers for BCE. Requires dateBegin. | |
| isOnView | No | When true, restricts results to objects currently on display in a Met gallery. The GalleryNumber field on the met_get_object record identifies the specific gallery. | |
| dateBegin | No | Earliest object date (year, inclusive). Negative integers for BCE (e.g., -500 for 500 BCE). Requires dateEnd. | |
| hasImages | No | When true, restricts results to objects that have at least one associated image, including copyrighted works whose images cannot be reproduced. isPublicDomain is the filter for freely reusable CC0 images. | |
| geoLocation | No | Filter by geographic origin. Each value is matched broadly against geography fields and artist nationality. Multiple values are AND-combined — ["France", "Egypt"] returns objects associated with both, not either, so more values narrow the result set. Works best with the Egyptian Art, Greek and Roman Art, and similar departments that have well-populated geography fields. | |
| isHighlight | No | When true, restricts to objects the Met has designated as highlights — major works central to the collection. | |
| departmentId | No | Restrict results to one curatorial department. Valid IDs come from met_list_departments — the Met exposes a sparse set (roughly 1–21, with gaps); an unrecognized ID is rejected with an invalid_department error rather than silently returning no matches. Can be combined with other filters; combining with isPublicDomain works but returns far fewer results than expected. | |
| isPublicDomain | No | When true, restricts results to objects released under CC0 open access — free to use without permission or attribution. These objects return direct high-resolution image URLs in met_get_object. Combining with departmentId works but returns far fewer results, since the search index covers only a subset of public-domain objects per department. |
| Name | Required | Description |
|---|---|---|
| total | Yes | Total number of matching objects in the Met collection (may far exceed the returned IDs). |
| returned | Yes | Count of object IDs in this response — may be less than `total` when the full result set was truncated by `limit`. |
| objectIDs | Yes | Object IDs for the first `limit` results. |
| remaining | Yes | Count of matching object IDs after this page: total − (offset + returned), floored at 0. 0 means this is the last page. |
| truncated | Yes | True when matching IDs remain beyond this page (offset + returned < total); false when this page is the last. |
| nextOffset | Yes | The offset to pass on the next call to continue paging, or null when the result set is exhausted (truncated is false). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond annotations (readOnlyHint, idempotentHint), description adds behavior details: returns total count and object IDs, notes timeout risks, explains offset beyond total returns empty page, and clarifies medium parameter mapping.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Single dense paragraph with no wasted words. Front-loads the core purpose, then systematically covers parameters and behaviors.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 12 parameters, siblings, and output schema, description covers return values, paging, filter interactions, and references to other tools. No gaps for effective use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema covers 100% of parameters, but description adds substantial meaning: medium maps to classification field, geoLocation is AND-combined, departmentId+isPublicDomain returns few results, and more. Adds value beyond schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool searches the Met collection by keyword and filters, and distinguishes itself from siblings met_get_object (for full records) and met_list_departments (for department IDs).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides explicit guidance: explains relevance is keyword-based not semantic, advises using filters over longer queries, describes when to use isPublicDomain vs hasImages vs isOnView, and gives paging advice with timeout warnings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Claim this connector by publishing a /.well-known/glama.json file on your server's domain with the following structure:
{
"$schema": "https://glama.ai/mcp/schemas/connector.json",
"maintainers": [{ "email": "your-email@example.com" }]
}The email address must match the email associated with your Glama account. Once published, Glama will automatically detect and verify the file within a few minutes.
Control your server's listing on Glama, including description and metadata
Access analytics and receive server usage reports
Get monitoring and health status updates for your server
Feature your server to boost visibility and reach more users
For users:
Full audit trail – every tool call is logged with inputs and outputs for compliance and debugging
Granular tool control – enable or disable individual tools per connector to limit what your AI agents can do
Centralized credential management – store and rotate API keys and OAuth tokens in one place
Change alerts – get notified when a connector changes its schema, adds or removes tools, or updates tool definitions, so nothing breaks silently
For server owners:
Proven adoption – public usage metrics on your listing show real-world traction and build trust with prospective users
Tool-level analytics – see which tools are being used most, helping you prioritize development and documentation
Direct user feedback – users can report issues and suggest improvements through the listing, giving you a channel you would not have otherwise
The connector status is unhealthy when Glama is unable to successfully connect to the server. This can happen for several reasons:
The server is experiencing an outage
The URL of the server is wrong
Credentials required to access the server are missing or invalid
If you are the owner of this MCP connector and would like to make modifications to the listing, including providing test credentials for accessing the server, please contact support@glama.ai.
No comments yet. Be the first to start the discussion!
Sign in to create a connector for this server.