io.github.cyanheads/met-museum-mcp-server
REMOTE · MET-MUSEUM.CASEYJHAND.COM · 2 COMPONENTS
Search the Met collection, browse by department or update date, fetch full records and CC0 images.
Available components
Last scanned (14 hours ago)
Scores higher than 95% of remote servers
Reachable. Last reached 6 Nov 2026.
Category Education and Research
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security83
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation. See how to fix → View diagnostics → Partial
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
- DNSSEC is configured correctly; the domain's records validate against the full chain to the root. View diagnostics → Pass
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability73
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 2528 tokens (~505/item across 5 items; 4 tools + 1 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
Checks we ran (13)
- TLS certificate
- Authorization
- HTTPS
- HSTS header
- DNSSEC
- Transport
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Does not apply to this hosted endpoint (2)
- Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
- Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
The score does not measure everything. What the score does not measure →
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 6 Nov 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 4 Nov 26 +2
- The server rewrote its instructions, which are the text every model session reads security
- Tool “met_get_object” rewrote its description, which is the text the model reads security
- Tool “met_search_collections” rewrote its description, which is the text the model reads security
- Schema quality: 2188 → 2528 ▼ functional
- Schema quality: unverified → 100 ▲ functional
- New resource “met-museum-guide” functional
- Server version: 0.9.0 → 0.10.0 functional
- “met_list_objects” reworded the description of “limit” cosmetic
- “met_search_collections” reworded the description of “dateBegin” cosmetic
- “met_search_collections” reworded the description of “dateEnd” cosmetic
- “met_search_collections” reworded the description of “geoLocation” cosmetic
- “met_search_collections” reworded the description of “limit” cosmetic
- “met_search_collections” reworded the description of “matchField” cosmetic
- “met_search_collections” reworded the description of “medium” cosmetic
- “met_search_collections” reworded the description of “q” cosmetic
- 15 Oct 26 0
- The server rewrote its instructions, which are the text every model session reads security
- Tool “met_get_object” rewrote its description, which is the text the model reads security
- Server version: 0.8.0 → 0.9.0 functional
- “met_get_object” reworded the description of “objectIDs” cosmetic
- “met_search_collections” reworded the description of “limit” cosmetic
- “met_list_objects” reworded the description of “limit” cosmetic
- 4 Oct 26 −1
- Schema quality: 409 → 506 ▼ functional
- 30 Sept 26 0
- The server rewrote its instructions, which are the text every model session reads security
- Tool “met_get_object” rewrote its description, which is the text the model reads security
- Tool “met_list_departments” rewrote its description, which is the text the model reads security
- Schema quality: 1185 → 1639 ▼ functional
- Server version: 0.6.0 → 0.7.0 functional
- New tool “met_list_objects” functional
- “met_get_object” reworded the description of “objectIDs” cosmetic
- 28 Sept 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 25 Sept 26 0
- Schema quality: 536 → 395 ▲ functional
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 19 Sept 26 0
- Server version: 0.5.2 → 0.5.3 functional
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 6 Nov 2026 · Probed https://met-museum.caseyjhand.com/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=caseyjhand.com | CN=WE1,O=Google Trust Services,C=US | 2 Nov 2026 | 31 Jan 2027 | ECDSA 256 | ECDSA-SHA256 | 995a30681ab772540e934241ca1d576c |
| SANs: caseyjhand.com, *.caseyjhand.com | ||||||
| CN=WE1,O=Google Trust Services,C=US (CA) | CN=GTS Root R4,O=Google Trust Services LLC,C=US | 13 Dec 2023 | 20 Feb 2029 | ECDSA 256 | ECDSA-SHA384 | 7ff31977972c224a76155d13b6d685e3 |
| CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) | CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE | 15 Nov 2023 | 28 Jan 2028 | ECDSA 384 | SHA256-RSA | 7fe530bf331343bedd821610493d8a1b |
Background: What to check on a remote MCP endpoint →
DNSSEC secure
Validation of met-museum.caseyjhand.com. — Secure
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | Trust anchor | 20326, 38696 | 8, 8 | Verified |
| com. | DS published | 19718 | 13 | Verified |
| caseyjhand.com. | DS published | 2371 | 13 | Verified |
| met-museum.caseyjhand.com. | Verified address RRset verified with the apex keys |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
| Header | Value |
|---|---|
| strict-transport-security | max-age=63072000; includeSubDomains; preload |
| x-content-type-options | nosniff |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://met-museum.caseyjhand.com/mcp | Verified | 200 | |
| http (plaintext) | http://met-museum.caseyjhand.com/mcp | HTTPS enforced | 301 | https://met-museum.caseyjhand.com/mcp |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
met_get_object Get Met Objects ~361
Fetch full records for one or more Met Museum object IDs. Fetches up to 20 distinct IDs per call; a list of up to 500 (a full search or list page) is accepted, and the distinct IDs past the first 20 come back unrequested in remainingIDs for a follow-up call. 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. Set includeImages to also receive the CC0 images of up to 3 returned records as image content a vision-capable model can look at.
| Name | Type | Req | Description |
|---|---|---|---|
| includeImages | boolean | – | 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 a… |
| objectIDs | array | yes | One or more Met object IDs to fetch, up to 500 — a full met_search_collections or met_list_objects page. A repeated ID is fetched and returned once, at its first position. The first 20 distinct IDs a… |
| Name | Type | Req | Description |
|---|---|---|---|
| error | object | – | Present when the call failed. Absent on success. |
| failed | array | – | Object IDs that failed to fetch with per-ID error context. |
| images | array | – | Image outcome for each record in objects[], in request order; failed[] and remainingIDs get no entry. Present only when includeImages is true. |
| notice | string | – | Present when the call held more than 20 distinct object IDs: it says how many distinct IDs the call held and that the ones past the first 20 are in remainingIDs, not requested. |
| objects | array | – | Successfully fetched objects. |
| remainingIDs | array | – | The distinct object IDs past the first 20, in request order. These were not requested; they are separate from the failed[] entries an upstream block, throttle, or outage left unrequested, which fall… |
No examples provided.
met_list_departments List Met Departments ~52
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.
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| departments | array | – | All 19 curatorial departments at The Metropolitan Museum of Art. |
| error | object | – | Present when the call failed. Absent on success. |
No examples provided.
met_list_objects List Met Objects ~425
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.
| Name | Type | Req | Description |
|---|---|---|---|
| departmentId | integer | – | Restrict the list 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_depar… |
| limit | integer | – | Maximum number of object IDs to return in this page. A page holds at most 500 IDs: a larger value reads a 500-ID page and the notice says so — continue from nextOffset. |
| offset | integer | – | 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 to… |
| updatedSince | string | – | 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") — no time part and no other date format. It compares the UTC d… |
| Name | Type | Req | Description |
|---|---|---|---|
| effectiveQuery | string | – | The filters as applied, as name=value pairs with JSON-encoded values — an updatedSince before 1753-01-01 shows as 1753-01-01, the date sent — or "no filter (whole collection)". limit and offset are l… |
| error | object | – | Present when the call failed. Absent on success. |
| nextOffset | – | – | The offset to pass on the next call to continue paging, or null when this page ends the list (truncated is false). |
| notice | string | – | Present when total is 0: names the filters that matched nothing and how to widen the list. Also present when a limit above 500 was read as a 500-ID page with IDs still remaining: says the page was re… |
| objectIDs | array | – | Object IDs for this page in ascending order, up to `limit` results and never more than 500. |
| offset | integer | – | The resolved offset this page was read from — 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 not… |
| remaining | integer | – | Count of IDs after this page: total minus (offset + returned), floored at 0. 0 means no further page exists. |
| returned | integer | – | Count of object IDs in this page. |
| total | integer | – | Total number of objects matching the filters. Paging reaches every one of them — there is no 10,000 window here. |
| truncated | boolean | – | True when IDs remain after this page (offset + returned < total); false when this page ends the list. |
No examples provided.
met_search_collections Search Met Collection ~1,269
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 one 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.
| Name | Type | Req | Description |
|---|---|---|---|
| dateBegin | integer | – | First year of the date window, inclusive. Negative integers for BCE (e.g., -500 for 500 BCE). Requires dateEnd. The window keeps only objects whose whole date span (objectBeginDate to objectEndDate o… |
| dateEnd | integer | – | Last year of the date window, inclusive. Negative integers for BCE. Requires dateBegin. The window keeps only objects whose whole date span (objectBeginDate to objectEndDate on met_get_object) lies i… |
| departmentId | integer | – | 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_depart… |
| geoLocation | array | – | Filter by geographic origin: one place, whole and case-sensitive as the Met spells it, as a one-element array (e.g., ["Greece"], ["Japan"]). A different case ("greece"), a fragment ("Gree"), or a "|"… |
| hasImages | boolean | – | 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 r… |
| isHighlight | boolean | – | Opt-in filter, true only — omit it rather than passing false, which the search ignores. Selects objects the Met has designated as highlights — major works central to the collection. |
| isOnView | boolean | – | 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 specifi… |
| limit | integer | – | Maximum number of object IDs to return in this page. A page holds at most 500 IDs, the Met search maximum: a larger value reads a 500-ID page and the notice says so — continue from nextOffset. Paging… |
| matchField | string | – | Restrict the keyword match to one field: "title" matches object titles only, "tags" matches subject tags only, "artistOrCulture" matches the artist an object is attributed to (artistDisplayName on me… |
| medium | string | – | Filter by one object classification, case-sensitive and spelled as the Met spells it (e.g., "Paintings", "Drawings", "Prints", "Ceramics", "Sculpture", "Photographs", "Textiles") — "paintings" or "Pa… |
| offset | integer | – | 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 10,0… |
| q | string | yes | Keyword query, matched across title, artist name, culture, medium, tags, and other text fields; matchField narrows the match to titles, tags, or artists and cultures. Broad terms return large ID sets… |
| Name | Type | Req | Description |
|---|---|---|---|
| effectiveQuery | string | – | The search as applied: q and each filter set, as name=value pairs with JSON-encoded values in parameter order, without limit or offset. |
| error | object | – | Present when the call failed. Absent on success. |
| nextOffset | – | – | 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 ex… |
| notice | string | – | Present when total is 0, when total exceeds 10,000, when a limit above 500 was read as a 500-ID page with matches still remaining, or when departmentId is 7 or 17; several apply as one string. For a… |
| objectIDs | array | – | Object IDs for this page, up to `limit` results and never more than 500. For departmentId 7 or 17, only the requested department's matches among the positions this page read, so it can hold fewer tha… |
| offset | integer | – | The resolved offset this page was read from — 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 pa… |
| remaining | integer | – | Count of reachable matches after this page: the smaller of total and 10,000, minus (offset + the positions this page read), floored at 0 — positions read as described under truncated. An empty page r… |
| returned | integer | – | Count of object IDs in this page. |
| total | integer | – | Total number of objects in the Met collection matching the search. Can exceed 10,000, the most that paging reaches. |
| truncated | boolean | – | 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 e… |
No examples provided.
How do I install the io.github.cyanheads/met-museum-mcp-server server?
io.github.cyanheads/met-museum-mcp-server is a hosted endpoint at https://met-museum.caseyjhand.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · met-museum.caseyjhand.com
claude mcp add --transport http cyanheads-met-museum-mcp-server 'https://met-museum.caseyjhand.com/mcp'
What is the io.github.cyanheads/met-museum-mcp-server server?
io.github.cyanheads/met-museum-mcp-server is listed in the public MCP registry as io.github.cyanheads/met-museum-mcp-server. Search the Met collection, browse by department or update date, fetch full records and CC0 images. This page covers its hosted endpoint (https://met-museum.caseyjhand.com/mcp).
Is the io.github.cyanheads/met-museum-mcp-server server safe to use?
io.github.cyanheads/met-museum-mcp-server scores 88 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the io.github.cyanheads/met-museum-mcp-server server expose?
io.github.cyanheads/met-museum-mcp-server exposes 4 tools: met_list_departments, met_search_collections, met_list_objects, met_get_object. Their descriptions and schemas cost roughly 2,107 tokens of context every time the server is loaded.
Does the io.github.cyanheads/met-museum-mcp-server server require authentication?
No. We connected to io.github.cyanheads/met-museum-mcp-server without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the io.github.cyanheads/met-museum-mcp-server server still maintained?
io.github.cyanheads/met-museum-mcp-server is still listed as active in the MCP registry. We last reached this channel on 6 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What did VerifyMCP test on the io.github.cyanheads/met-museum-mcp-server server?
VerifyMCP ran 13 checks on io.github.cyanheads/met-museum-mcp-server, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.