get_user_dataset_file
Read-only
Read the rows of one of the user's saved datasets AS PUBLISHED — the file behind its latest_url, or a dated version. THIS is how a dashboard or an answer reads a dataset: the published file is reviewed at publish, point-in-time, and the same bytes every consumer gets. Never replay the dataset's saved query instead (run_saved_query re-runs live SQL: different rows, no review). A claude.ai artifact can't reach flexreportfinapi.com itself, so its page calls this tool.
Fetches the file server-side and parses json, jsonl, csv, tsv, xml, rss and atom files
into rows; rss/atom come back one row per item {title, link, description, pub_date,
guid, categories, company_symbols, research_url}. `research_url` (every format, rows
with a ticker) is the feed readers' research link: show it as part of the item, but
never fetch it or offer it as a way to download a report (get_latest_report is the
user's route). parquet and xlsx files can't be parsed here: give the user latest_url
instead.
Returns {dataset_name, format, version, published_at, row_count, rows}. Quote
`published_at` as the data's as-of. A file over the server's size cap errors instead
of returning — use the user's own reader on latest_url for that one.
Requires auth (your MCP client attaches the OAuth bearer automatically).
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| version | No | Omit for the newest file. Else a build date (YYYY-MM-DD, its newest file) or a file's exact `published_at` from list_user_datasets. | |
| dataset_name | Yes | The dataset's `name`, as list_user_datasets shows it. |