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 4.6/5 across 3 of 3 tools scored.
Each tool has a clearly distinct purpose: listing departments, searching collections, and retrieving object records. No ambiguity in which tool to use for a given task.
All tools follow a consistent `met_verb_noun` pattern (e.g., `met_list_departments`, `met_search_collections`, `met_get_object`), making naming predictable and easy to understand.
With only 3 tools, the surface is minimal but covers the essential workflow. However, given the scope of the Met API, additional tools for browsing departments or retrieving highlights would be expected.
The tools cover discoverability (departments), search, and retrieval, but lack browsing without search terms or additional features like exhibitions or object highlights, leaving moderate gaps for a full collection exploration.
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_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. 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?
Annotations already declare readOnlyHint and idempotentHint true. The description adds significant extra behavioral details: parallel fetching with concurrency limits, partial-success handling (404 per ID), public domain image handling, null fields for constituents/tags. No contradiction.
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 efficient (4 sentences), front-loaded with the main action, then structured details. No extraneous 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 one parameter, existing annotations, and presence of output schema, the description covers: purpose, parameter source, limits, parallelism, partial failure, public domain constraints, null field behavior. Complete for correct agent usage.
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 value by linking objectIDs to met_search_collections and explaining batch/parallel behavior, going beyond the schema's documentation.
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 'Fetch full records for one or more Met Museum object IDs' with specific verb (fetch), resource (full records), and scope (multiple IDs). It distinguishes from siblings by referencing met_search_collections as the source of 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?
The description provides context on when to use (after obtaining IDs from met_search_collections) and explains limits (up to 20 IDs) and behavior. It lacks explicit 'when not to use' but implies alternatives through sibling naming.
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_collections 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 declare readOnlyHint and idempotentHint. The description adds that the list is fetched live each call to remain accurate, which is useful behavioral context 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?
Two succinct sentences that front-load the purpose and add context, with no unnecessary verbiage.
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 an existing output schema, the description fully covers what the tool does, its return value, and its relation to sibling tools.
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?
With zero parameters, schema coverage is 100%, so the description does not need to add parameter details. It adequately describes the output.
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 specifies that the tool returns the 19 curatorial departments at The Metropolitan Museum of Art with numeric IDs and display names, directly distinguishing it from siblings like met_search_collections.
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 explicitly advises using this tool before met_search_collections to discover valid departmentId values, providing clear usage context, though it does not mention when not to use it.
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 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. isOnView restricts results to works currently on display in a Met gallery.
| 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. | |
| 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. Combine with a keyword to answer "what is on display right now?" — pairs well with isHighlight for must-see works. | |
| 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?
Beyond the readOnlyHint and idempotentHint annotations, the description adds valuable behavioral details: search relevance is keyword-based, medium maps to classification field, distinction between isPublicDomain and hasImages, and isOnView restricts to displayed works. 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 coherent paragraph that is front-loaded with the main purpose. It is fairly concise but contains some longer sentences; minor improvement could be made for tighter wording.
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 the complexity (11 parameters, output schema exists), the description covers all necessary aspects: what it returns, how to use results (chain to met_get_object), parameter usage tips, and edge cases. It is sufficiently complete without needing to explain return values due to output schema presence.
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?
Although schema coverage is 100%, the description adds significant meaning beyond the schema, such as explaining that medium should not be a material description, warning about combining isPublicDomain with departmentId, and clarifying geoLocation's AND-combining behavior.
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 optional filters, returns total match count and object IDs, and distinguishes from sibling tools by explicitly referencing the chaining pattern with met_get_object.
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 provides explicit guidance on when to use this tool (e.g., for searching) and directs to chain results with met_get_object. It also advises on filter usage but does not explicitly state when not to use the tool, though the context is clear.
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!