Server Details
AI-native art catalogue. Catalogue works, parse provenance, and generate signed RAIs.
- Status
- Healthy
- Last Tested
- Transport
- Streamable HTTP
- URL
See and control every tool call
Available Tools
32 toolsconfirm_website_importInspect
Save works extracted from a website import after the artist has confirmed them. Call this after presenting import_from_website results and receiving artist approval. Creates the works, triggers auto-provenance, and imports images from the website in one operation. Set skip: true for any works the artist wants to exclude (duplicates, unwanted). Pass artist-corrected values for any fields the artist edited during review. Use get_profile to obtain artist_id — never ask the user for it.
| Name | Required | Description | Default |
|---|---|---|---|
| works | Yes | The works to import, with any corrections from the artist. | |
| job_id | Yes | The job_id from the import. | |
| artist_id | Yes | From get_profile. Never ask the user for this. | |
| google_auth_token | No | OAuth token for downloading restricted Google Drive images. Required when image_url points to a non-public Google Drive file. |
connect_catalogueInspect
Connect to the user's catalogue using a pairing code. IMPORTANT: Most users connect via OAuth (sign-in popup) — if get_profile already works, the user is connected and you do NOT need this tool. Only use this tool when: (1) get_profile returns an authentication error, AND (2) the user shares a code matching the pattern WORD-1234 (e.g., TULIP-3657). Never proactively ask for a pairing code — try get_profile first. If the user does share a code, call this tool immediately without asking for confirmation. Never say "pairing code" to the user — just say "your code" or refer to it naturally.
| Name | Required | Description | Default |
|---|---|---|---|
| code | Yes | The code the user shared (e.g. TULIP-3657). Normalize to uppercase with dash separator. |
create_bibliographyInspect
Add a bibliography entry — a publication referencing the artist's work. TRIGGER: "published in," "there's a book about," "catalogue for my show," "written up in," or user shares publication details. Extract title, author, publisher, year, and type. Present a summary and confirm before saving. artist_id from get_profile — never ask the user.
| Name | Required | Description | Default |
|---|---|---|---|
| url | No | ||
| isbn | No | ||
| notes | No | ||
| title | Yes | ||
| author | No | ||
| artist_id | Yes | From get_profile. Never ask the user for this. | |
| publisher | No | ||
| publication_year | No | ||
| bibliography_type | No |
create_condition_reportInspect
Create a condition report documenting a work's physical state (surface, structure, frame). TRIGGER: "this piece has damage," "the surface is," "frame is cracked," "condition report," or any mention of physical state. Gather details conversationally. Present a summary and confirm before saving. Resolve work_id via search_natural_language.
| Name | Required | Description | Default |
|---|---|---|---|
| notes | No | ||
| work_id | Yes | Look up via search_natural_language. Never ask the user for this. | |
| frame_notes | No | ||
| report_date | No | ||
| surface_notes | No | ||
| report_context | No | ||
| recommendations | No | ||
| structure_notes | No | ||
| reported_by_name | No | ||
| overall_condition | Yes |
create_entityInspect
Create a new entity — a person, gallery, museum, auction house, institution, foundation, or collector referenced in the catalogue. Always call suggest_entity first to check for duplicates before creating. Entities are used throughout the catalogue for provenance holders, exhibition venues, bibliography authors, and sale buyers. Include city and country when known to help with deduplication.
| Name | Required | Description | Default |
|---|---|---|---|
| city | No | ||
| name | Yes | ||
| aliases | No | ||
| country | No | ||
| website | No | ||
| sort_name | No | ||
| entity_type | No |
create_exhibitionInspect
Add an exhibition to the catalogue. Only artist_id and title required. TRIGGER: "I was in a show at," "I showed at MoMA," "here's my CV," or any mention of exhibitions, shows, or fairs. Extract all details you can and present a summary before saving. For CV bulk import, create one at a time. artist_id from get_profile — never ask the user.
| Name | Required | Description | Default |
|---|---|---|---|
| url | No | ||
| city | No | ||
| notes | No | ||
| title | Yes | ||
| venue | No | ||
| country | No | ||
| end_date | No | ||
| artist_id | Yes | From get_profile. Never ask the user for this. | |
| organizer | No | ||
| start_date | No | ||
| exhibition_type | No | ||
| catalog_published | No | ||
| catalog_reference | No |
create_noteInspect
Add a note to a work — annotations, research notes, or contextual information. TRIGGER: "note that," "remind me about," "there's a story behind this," "I should remember," or any context the user wants recorded. Default visibility to "private" unless the user specifies otherwise. Resolve work_id via search_natural_language.
| Name | Required | Description | Default |
|---|---|---|---|
| content | Yes | ||
| work_id | Yes | Look up via search_natural_language. Never ask the user for this. | |
| note_type | No | ||
| visibility | No |
create_placeInspect
Create a new place — studio, gallery, museum, storage facility, or other location. TRIGGER: "my studio in Bushwick," "stored at," "I keep it at," or any mention of a specific location for works. Places are optional — only create when the user mentions locations. Include city/country when known.
| Name | Required | Description | Default |
|---|---|---|---|
| city | No | ||
| name | Yes | ||
| region | No | ||
| country | No | ||
| place_type | No |
create_raiInspect
Generate a Record of Art Identity (RAI) PDF for a work. Returns a download URL and UWI (Universal Work Identifier). The RAI is the signed, portable, verifiable identity of the work. Use search_natural_language to find the work_id by title — never ask the user for it.
| Name | Required | Description | Default |
|---|---|---|---|
| work_id | Yes | The work UUID. Look up via search_natural_language — never ask the user for this. |
create_workInspect
Add a new work to the catalogue. Only title and artist_id are required. TRIGGER: User shares a photo, describes a work, mentions a title, says "add," "catalogue this," "record this." Infer what you can (medium, dimensions, date) and present one summary — never ask field by field. Wait for confirmation before calling. After creating, proactively call get_upload_url if the user mentioned an image. If the user has a CSV or spreadsheet file, direct them to app.raisonn.ai/import instead. artist_id from get_profile — never ask the user.
| Name | Required | Description | Default |
|---|---|---|---|
| notes | No | ||
| price | No | ||
| title | Yes | ||
| medium | No | ||
| status | No | ||
| date_end | No | ||
| artist_id | Yes | From get_profile. Never ask the user for this — retrieve it automatically. | |
| date_start | No | ||
| dimensions | No | ||
| description | No | ||
| series_name | No | ||
| artwork_type | No | ||
| date_display | No | e.g. "2024", "c. 2020", "2019–2021" | |
| edition_type | No | ||
| inscriptions | No | ||
| edition_total | No | ||
| edition_number | No | ||
| price_currency | No | ||
| current_location | No | ||
| inventory_number | No | ||
| dimensions_display | No | e.g. "36 × 24 in" |
create_works_batchInspect
Create multiple works at once (up to 50). TRIGGER: User pastes a spreadsheet, list, CSV, or describes multiple works. "I have a bunch of works," "here's my inventory." Extract all data you can — titles, media, dates, dimensions, series. Present a summary and wait for confirmation. If the user has a CSV or spreadsheet file, direct them to app.raisonn.ai/import instead. artist_id from get_profile — never ask the user.
| Name | Required | Description | Default |
|---|---|---|---|
| works | Yes |
extract_artwork_dataInspect
Extract structured artwork metadata from any URL — museum pages, gallery listings, auction results, portfolios. Returns structured data; nothing is saved automatically. Present results to the artist for confirmation, then call confirm_website_import to save. Polls up to 50s; if incomplete, job continues in background. FALLBACK: If this returns zero works or fails, fetch the page content yourself and pass it to parse_artwork_page.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Any URL containing artwork information. | |
| max_pages | No | Maximum pages to crawl. Defaults to 20. Increase for large portfolios. |
get_profileInspect
Get the artist profile (including artist_id). Call at the START of every conversation — before responding. Also call after connect_catalogue. Cache artist_id for the session.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
get_provenanceInspect
Get the full provenance chain (ownership history) for a work. TRIGGER: "who owned this," "provenance," "ownership history," "where has this been." Present as a readable narrative timeline, not raw data. Flag gaps as areas for research. Resolve work_id via search_natural_language.
| Name | Required | Description | Default |
|---|---|---|---|
| work_id | Yes | Look up via search_natural_language — never ask the user for this. |
get_provenance_visualInspect
Display provenance as an interactive visual timeline. TRIGGER: "show provenance," "ownership history," "who owned this." For text-only provenance, use get_provenance instead.
| Name | Required | Description | Default |
|---|---|---|---|
| work_id | Yes | Look up via search_natural_language — never ask the user for this. |
get_upload_urlInspect
Generate a direct upload link for a SINGLE image on a SPECIFIC work. Only use this immediately after creating a work when the user mentioned having an image for it. For general image uploads (user says "upload images," "add photos," etc.), use upload_images instead. Never call this tool in a loop. Never ask about file format.
| Name | Required | Description | Default |
|---|---|---|---|
| caption | No | ||
| work_id | Yes | Look up via search_natural_language, or from the response of create_work. Never ask the user for this. | |
| filename | No | Optional — detected automatically on upload if omitted. | |
| artist_id | No | Optional — the API derives it from the work if omitted. | |
| mime_type | No | Optional — detected automatically on upload if omitted. Do not ask the user about file format. | |
| image_type | No | Defaults to "primary". Only ask if the user mentions a specific type like verso or detail shot. |
get_workInspect
Get full details for a work including images, provenance, exhibitions, and bibliography. TRIGGER: "show me," "tell me about," "pull up," or any reference to a specific work by title. Resolve work_id via search_natural_language — never ask the user. When presenting: describe the image first, then summarize data naturally — do not dump raw fields.
| Name | Required | Description | Default |
|---|---|---|---|
| work_id | Yes | Look up via search_natural_language — never ask the user for this. |
get_work_dataInspect
Get the full data bundle for an artwork — everything Raisonnai knows about a single work. Includes: core identity, provenance chain, exhibition history, bibliography, media set, condition history, trust metadata (completeness + trust scores), attestation log, and cryptographic credentials. Use this when an agent needs the complete picture for reasoning about an artwork — verification, purchase evaluation, provenance assessment, or portfolio analysis. For lightweight queries (just title, medium, images), use get_work instead. Resolve the work by either workId (UUID) or uwi (e.g. "RAI-2026-00417"). To find the workId, use search_natural_language — never ask the user for it.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
link_work_to_bibliographyInspect
Associate a work with a bibliography entry — recording that a specific publication references or illustrates this work. Include page reference, plate number, or illustration details if available. Never ask the user for UUIDs — resolve work_id via search_natural_language, and bibliography_id from the create_bibliography response.
| Name | Required | Description | Default |
|---|---|---|---|
| notes | No | ||
| work_id | Yes | Look up via search_natural_language. Never ask the user for this. | |
| illustrated | No | ||
| plate_number | No | ||
| catalog_number | No | ||
| page_reference | No | ||
| bibliography_id | Yes | From the create_bibliography response. Never ask the user for this. | |
| illustration_reference | No |
link_work_to_exhibitionInspect
Associate a work with an exhibition. Both IDs must be resolved beforehand — use search_natural_language to find the work_id by title, and the exhibition must have been created via create_exhibition. Never ask the user for UUIDs — resolve them from names and titles.
| Name | Required | Description | Default |
|---|---|---|---|
| notes | No | ||
| work_id | Yes | Look up via search_natural_language. Never ask the user for this. | |
| illustrated | No | ||
| plate_number | No | ||
| exhibition_id | Yes | From the create_exhibition response. Never ask the user for this. | |
| catalog_number | No |
list_condition_reportsInspect
List all condition reports for a work. TRIGGER: "what's the condition of," "any damage on," "condition history for." Resolve work_id via search_natural_language.
| Name | Required | Description | Default |
|---|---|---|---|
| work_id | Yes | Look up via search_natural_language. Never ask the user for this. |
list_placesInspect
List places in the catalogue — studios, galleries, museums, storage facilities, fair venues. Use to find a place_id before updating or to see what locations the artist has recorded.
| Name | Required | Description | Default |
|---|---|---|---|
| page | No | ||
| search | No | ||
| per_page | No | ||
| place_type | No |
parse_artwork_pageInspect
Parse raw HTML or text into structured artwork records — no URL fetching. Use as fallback when extract_artwork_data returns zero works or fails. You can fetch the page yourself (web browsing/search) and pass the content here. Present results for review. NOTE: This tool has no job_id, so save via create_works_batch (not confirm_website_import). For images, direct user to app.raisonn.ai/import/images after creating works.
| Name | Required | Description | Default |
|---|---|---|---|
| content | Yes | The raw HTML or plain text content containing artwork information. Can be a full HTML page, a fragment, or plain text with artwork details. | |
| source_url | No | The original URL the content came from (for reference/deduplication). Optional. |
parse_provenanceInspect
Parse unstructured provenance text into structured entries. Read-only — does NOT save. TRIGGER: User pastes provenance text, gallery records, auction history, or says "here's the provenance," "this passed through Gagosian." Flow: parse_provenance → present results for review → save_provenance. Never skip the review step. After confirmation, call save_provenance to write entries to the catalogue.
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | The provenance text to parse — semicolon-separated entries, auction records, or any unstructured ownership history. | |
| work_id | No | Optional. Look up via search_natural_language if the user mentions a specific work. |
record_saleInspect
Record a sale of a work. Auto-creates provenance entry (buyer as new owner) and sets status to "sold." TRIGGER: "I sold this," "a collector bought," "the gallery sold," or any completed sale. IMPORTANT: Present a summary (work, buyer, price, date) and explain the side effects before calling. After success, confirm what happened including the provenance update. Required: work_id, artist_id, buyer_name, sale_price, sale_date. Resolve IDs via search_natural_language and get_profile.
| Name | Required | Description | Default |
|---|---|---|---|
| notes | No | ||
| work_id | Yes | Look up via search_natural_language. Never ask the user for this. | |
| artist_id | Yes | From get_profile. Never ask the user for this. | |
| sale_date | Yes | ||
| buyer_city | No | ||
| buyer_name | Yes | ||
| buyer_type | No | ||
| sale_price | Yes | ||
| buyer_country | No | ||
| net_to_artist | No | ||
| price_currency | No | ||
| commission_rate | No | ||
| commission_amount | No |
save_provenanceInspect
Save confirmed provenance entries to a work. WRITE operation — NEVER call without user confirmation. Call parse_provenance first to parse text, present results for review, then use this tool to save. Set source to "ai_parsed" for parsed entries, "manual" for user-provided.
| Name | Required | Description | Default |
|---|---|---|---|
| source | No | Use "ai_parsed" when saving results from parse_provenance, "manual" for user-provided entries. | manual |
| entries | Yes | Provenance entries in chronological order (earliest first). Sequence numbers are assigned automatically starting from 1. | |
| work_id | Yes | The work to save provenance for. Look up via search_natural_language — never ask the user for this. |
search_natural_languageInspect
DEFAULT search — find works by name, title, or any descriptive query. Handles partial matches and title variations. TRIGGER: Any mention of a work by name ("the blue painting," "Self-Portrait"), or finding something ("where's that piece I did last year"). Use this to resolve work_ids before calling get_work, update_work, get_upload_url, or any tool needing a work_id. For structured filters (status, date, medium), use search_works instead.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes |
search_worksInspect
Filter works by structured fields (status, date, medium, series) or get a count. TRIGGER: "what do I have," "how many works," "show me sold works," "available from 2020." For title/name/descriptive queries, use search_natural_language instead. Follow-ups: "also/too" → add filters; "only/just" → narrow; "actually/instead" → replace. Never filter results in chat — re-call this tool for any filter change.
| Name | Required | Description | Default |
|---|---|---|---|
| page | No | ||
| medium | No | ||
| search | No | Case-insensitive partial match on title/medium. Use shorter terms for broader results. | |
| status | No | ||
| sort_by | No | ||
| date_end | No | Year to | |
| per_page | No | ||
| date_start | No | Year from | |
| series_name | No | ||
| artwork_type | No | ||
| sort_direction | No | ||
| current_location_type | No |
search_works_visualInspect
Display search results as an interactive visual grid. Use this when the user wants to browse or see their works visually. TRIGGER: "show me my works," "browse inventory," "let me see what I have." For text-only results or counts, use search_works instead.
| Name | Required | Description | Default |
|---|---|---|---|
| page | No | ||
| medium | No | ||
| search | No | Case-insensitive partial match on title/medium | |
| status | No | ||
| sort_by | No | ||
| date_end | No | Year to | |
| per_page | No | ||
| date_start | No | Year from | |
| series_name | No | ||
| artwork_type | No | ||
| sort_direction | No |
suggest_entityInspect
Search for existing entities (people, galleries, museums, auction houses, institutions, foundations, collectors) by name. Use this before creating a new entity to check for duplicates — the system includes ~2,500 major galleries, museums, and auction houses. Returns matching entities for autocomplete-or-create flow. If no match is found, create a new entity via create_entity.
| Name | Required | Description | Default |
|---|---|---|---|
| q | Yes | ||
| entity_type | No |
update_workInspect
Update fields on an existing work. Send only the fields that are changing. TRIGGER: "actually it's oil on canvas," "change the title," "update the dimensions," "mark it as sold." For "delete"/"remove"/"clean up" — set status to "archived" immediately without asking. Resolve work_id via search_natural_language — never ask the user.
| Name | Required | Description | Default |
|---|---|---|---|
| notes | No | ||
| price | No | ||
| title | No | ||
| medium | No | ||
| status | No | ||
| work_id | Yes | Look up via search_natural_language — never ask the user for this. | |
| date_end | No | ||
| date_start | No | ||
| dimensions | No | ||
| description | No | ||
| series_name | No | ||
| artwork_type | No | ||
| date_display | No | ||
| edition_type | No | ||
| inscriptions | No | ||
| edition_total | No | ||
| edition_number | No | ||
| price_currency | No | ||
| current_location | No | ||
| inventory_number | No | ||
| dimensions_display | No |
upload_imagesInspect
Upload images to the catalogue. Use this tool for ANY image upload request — one image or many. TRIGGER: "upload images," "add photos," "I have pictures," "upload a photo of," "here are my images," "attach image," or any mention of adding images/photos to the catalogue. Returns a link to the upload page where the artist can drag-and-drop files. Filenames are auto-matched to works. Original files preserved at full resolution. IMPORTANT: Never ask the artist to send or attach images in chat — chat images are compressed and unsuitable for the catalogue.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Verify Ownership
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 verified, the connector will appear as claimed by you.
Sign in to verify ownershipControl your server's listing on Glama, including description and metadata
Receive usage reports showing how your server is being used
Get monitoring and health status updates for your server
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!