met-museum-mcp-server
Server Details
MET Museum collection via MCP — 500K+ artworks, metadata, provenance, open-access images.
- Status
- Healthy
- Last Tested
- Transport
- Streamable HTTP
- URL
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.
Tool Definition Quality
Average 4.7/5 across 3 of 3 tools scored.
Each tool serves a distinct function: listing departments, searching the collection, and fetching full object records. There is no overlap in their purposes.
All tools follow a consistent `met_verb_noun` pattern (met_list_departments, met_search, met_get_object), making it easy to predict tool names.
Three tools cover the essential operations for a read-only museum API—discover, search, and retrieve. The scope is well-defined and neither too sparse nor excessive.
The tool set provides full coverage for accessing Met Museum data: discover departments, search with filters, and retrieve full object records. No obvious gaps are present for the intended use case.
Available Tools
3 toolsmet_get_objectGet Met ObjectsARead-onlyIdempotentInspect
Fetch full records for one or more Met Museum object IDs. Accepts up to 20 IDs per call, fetches in parallel (concurrency-limited), and returns partial-success — a single 404 does not fail the whole batch. Object IDs come from met_search. 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. Fetches run in parallel (concurrency-limited); partial failures are reported per ID rather than failing the whole batch. |
Output Schema
| Name | Required | Description |
|---|---|---|
| failed | Yes | Object IDs that failed to fetch with per-ID error context. |
| objects | Yes | Successfully fetched objects. |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds significant behavioral details beyond the readOnly and idempotent annotations: parallel fetching with concurrency limits, partial-success handling (404 doesn't fail batch), null image URLs for non-public-domain, null constituents for anonymous works, and null tags for untagged objects. No contradictions.
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?
The description is a single paragraph that efficiently conveys the main purpose and key behaviors. It is not verbose, though it could be slightly more concise by combining some details. Front-loads the core function.
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 that an output schema exists, the description does not need to explain return values. It covers constraints, edge cases (null fields, partial success), and dependencies on met_search. All relevant aspects are addressed.
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 coverage is 100%, so baseline is 3. The description adds value by explaining that fetching is parallel and concurrency-limited, and that partial failure is handled per ID. This provides context 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 it fetches full records for Met Museum object IDs. It specifies the source of IDs (met_search), constraints (up to 20 IDs), and distinguishes from sibling tools by focusing on retrieval rather than search or listing.
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 indicates when to use this tool (after obtaining IDs from met_search) and describes constraints (max 20 IDs, parallel fetching, partial success). It does not explicitly state when not to use, but context from sibling tools implies appropriate usage.
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 DepartmentsARead-onlyIdempotentInspect
Return the 19 curatorial departments at The Metropolitan Museum of Art with their numeric IDs and display names. Use before calling met_search to discover valid departmentId values. The department list is fetched live on each call to remain accurate if the Met reorganizes.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Output Schema
| Name | Required | Description |
|---|---|---|
| departments | Yes | All 19 curatorial departments at The Metropolitan Museum of Art. |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate readOnly and idempotent. Description adds context that the department list is fetched live each call, ensuring accuracy if the Met reorganizes, which goes 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?
Three concise sentences, front-loaded with purpose, 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?
Given no parameters and presence of an output schema, the description fully covers what the tool returns (departments with IDs and display names) and its purpose, making it complete.
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, so baseline 4 is appropriate. Description adds no param info because none needed.
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?
Description clearly states it returns the 19 curatorial departments with numeric IDs and display names, and distinguishes from siblings by positioning it as a prerequisite for met_search to discover valid departmentId values.
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?
Explicitly says to use before calling met_search to get valid departmentId values, and notes the live fetch for accuracy. Does not explicitly state when not to use, but context is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
met_searchSearch Met CollectionARead-onlyIdempotentInspect
Search the Metropolitan Museum of Art collection by keyword and optional filters; returns total match count and a page of object IDs. Always chain the returned IDs to met_get_object (up to 20 at a time) to retrieve full records. Search relevance is keyword-based, not semantic — use concise terms and apply departmentId or geoLocation filters to sharpen results. 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.
| Name | Required | Description | Default |
|---|---|---|---|
| q | Yes | Keyword query. Searched across title, artist name, culture, medium, tags, and other text fields. Use concise, specific terms — broad queries return large ID sets. Tip: departmentId and geoLocation sharpen results far more than a longer query string. | |
| limit | No | Maximum number of object IDs to return from the full result set. The API returns all matches (up to tens of thousands) — this caps what is handed back. Chain the returned IDs to met_get_object in batches of up to 20. | |
| 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". | |
| dateEnd | No | Latest object date (year, inclusive). Negative integers for BCE. Requires dateBegin. | |
| 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. For freely reusable CC0 images, use isPublicDomain instead — hasImages includes copyrighted works whose images cannot be reproduced. | |
| 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; use a single value for broader results. 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. Use to surface iconic pieces rather than browsing the full corpus. | |
| departmentId | No | Restrict results to one curatorial department. Use met_list_departments to get valid IDs (1–21, not all integers are valid). Can be combined with other filters; combining with isPublicDomain works but returns far fewer results than expected — use isPublicDomain alone when CC0 coverage is the goal. | |
| 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. Can be combined with departmentId but severely restricts results (the search index only indexes a subset of public-domain objects per department); prefer using isPublicDomain alone and filtering by department from the returned object records. |
Output Schema
| 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. Pass to met_get_object (up to 20 at a time) to retrieve full records. |
| truncated | Yes | True when total > returned. Increase `limit`, refine filters, or add keywords to narrow results. |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and idempotentHint=true. The description goes beyond by detailing search relevance (keyword-based, not semantic), medium parameter mapping (classification field, not material), interdependence of dateBegin and dateEnd, AND-combination of geoLocation values, and limitations of combining isPublicDomain with departmentId. No contradictions with 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?
The description is a single, well-structured paragraph with no redundant sentences. Each sentence provides essential information. Minor improvement could be breaking into bullet points, but current form is concise 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 10 parameters (1 required), no enums, and existence of an output schema (not needed in description), the cover is thorough. It addresses purpose, return type, chaining to met_get_object, key parameter behaviors, and usage tips. The description fully equips an agent to correctly invoke and interpret results from this search tool.
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 description coverage is 100%, so baseline is 3. The description adds significant extra context: explains that medium should be a classification category ('Paintings') not material description; notes that broad queries return large ID sets; clarifies that geoLocation values are AND-combined; advises using met_list_departments for valid department IDs; and warns that combining isPublicDomain with departmentId severely restricts results. This far exceeds baseline.
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 explicitly states the action ('Search the Metropolitan Museum of Art collection by keyword and optional filters'), the resource, and the output ('returns total match count and a page of object IDs'). It distinguishes from siblings by instructing to chain IDs to met_get_object and referencing met_list_departments for valid 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 clear when-then guidelines: 'Always chain the returned IDs to met_get_object (up to 20 at a time) to retrieve full records.' Also gives when-not advice: 'prefer using isPublicDomain alone and filtering by department from the returned object records' after cautioning against combining with departmentId. Explicit alternatives (met_list_departments) and tips for improving results (use departmentId or geoLocation) are included.
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.
Discussions
No comments yet. Be the first to start the discussion!