MCP Analytics

Direct link to the right account page for anything not doable in chat: billing, browser upload, report management. Hand the user the link and guide them.

Platform documentation and info: how it works (Answer, Analytics, Custom Analytics), usage.

AI help desk: which analysis fits your question, interpreting results, fixing errors. Multi-turn.

Get your data in. Pass `data` as an array of row objects to create the dataset immediately and get a dataset_ref ready for path_resolver; omit it to get an upload link for a file only the user can reach. Add replace_ref (uuid://ID:KEY) with data to REFRESH an existing dataset...

List and search your uploaded datasets, with fuzzy matching on name, description, and tags. Returns each dataset's uuid:// reference (the `usage` field) for use as dataset_ref in path_resolver and path_tool_run. The id alone ('uuid://dsv2_...') also works for your own datasets...

Browse the analyses you can run: the ones you commissioned plus the platform Standard Library (prebuilt tools; each result tagged source:'own' or 'standard_library'). Plain-language match; no query lists everything, your own first. Nothing fits? Commission it with path_resolver.

Get an analysis's parameter schema. ALWAYS call before path_tool_run.

The estimate as you review it WITH the user: the question as understood, the estimated answer (sample, marked), every place and its question, the page link, a review checklist. Before path_bespoke.

Apply the user's layout wishes to the estimate's page through the layout agent; a new named arrangement, nothing overwritten, no number changes.

Before estimating: how did we answer this objective before, on this data or any data? Prior packages and library runs with their tools, mappings, bespoke module names, method and verdicts. Platform-wide, read-only.

Before naming a library tool: does it fit THIS dataset for THIS question? Column mapping, missing required inputs, method-fit verdict, the places it delivers. Read-only.

Read an analytics package back: status, every run under it, the report link once delivered.

List and search the objects you own across every question: the curated charts, tables and figures of each delivered package, grouped by objective.

Check a commissioned build in-chat: stage progress, queue position, rejection reason if the data didn't match the objective, honest ETA, report link when delivered.

Ask a question across all your delivered analyses: a synthesized answer with citations back to specific reports.

Your report library: every analysis delivered, with status and links. Pass semantic_query to search report content in plain language.

Query your org's data warehouse free: browse the catalog (tables with column roles + computed metrics), semantically find data, plain-language ask, or named templates. Requires warehouse enablement (business plans).

Standing re-runs of analyses you own: action='create' (weekly/monthly against a re-runnable data reference, connector:// or an https:// link; report emailed after each run), 'list', or 'cancel'.

Get a shareable browser link for a report, viewable without authentication.

Browse a delivered report's individual cards (charts, tables, insights) inline in chat.

Which path a question about data should take (reuse, rerun, answer, tool_run, estimate, bespoke, ask or none), with the reason, every path's score and time, and the ready input for the path it picks. Executes nothing and charges nothing.

Hand back the report already delivered for this question on this data. Time: as path_resolver quotes.

Run a delivered analysis again, on its own dataset or a new one: the same tools and mappings, no rebuild. package_id may also be the person's own report link (a /rpt/ link or its rpt_ token) or estimate id (est_); it reruns their newest delivered package for it. Time: as path_...

A read of the data (a total, an average, a count, the top group), computed on every row, in this response. When the question is not a read it says so and names the next step. Time: as path_resolver quotes. No key yet? Call it with objective and data (a small table, up to 200 r...

Run one or more tested library tools on this dataset, with charts and a written report. No custom build. Time: as path_resolver quotes.

A rough answer over a sample and the layout of the full report, for the person to confirm before anything is ordered. Time: as path_resolver quotes.

Order a custom analysis built for this data from a confirmed estimate, optionally with library tools alongside. Needs the person's yes and an idempotency key; a retry returns the first order. Time: as path_resolver quotes.