fetch
Retrieve a Zotero item by its key and get its full text, title, URL, and metadata in a JSON envelope.
Instructions
ChatGPT custom connector FETCH endpoint — name is REQUIRED by the MCP-over-web spec (see platform.openai.com/docs/mcp); do not rename. Not intended for general MCP clients — in Claude or other regular MCP contexts use zotero_get_item_fulltext and zotero_get_item_metadata, which return richer markdown. Retrieves a single Zotero item and returns a JSON envelope {"id","title","text","url","metadata":{...}} matching the ChatGPT connector citation viewer. id: an 8-char Zotero item key — typically from a previous search call. Blank/missing returns an empty envelope (no error). url field: Zotero web-library URL when ZOTERO_LIBRARY_ID is set; otherwise a zotero://select/items/ deep-link. text field: extracted fulltext via the same path as zotero_get_item_fulltext; if none can be extracted, falls back to title + authors + abstract so the connector isn't blank. metadata field: itemType, date, DOI, authors, tags, both URLs. SILENT FALLBACK: errors return an envelope with {"metadata":{"error":…}} rather than raising, to keep the ChatGPT connector stable. Example (agent-invoked): fetch(id='RTKZQI8E').
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |