# MCP Analytics

> The statistical analyst in your AI chat: bring a dataset and a question, get back a citable, re-runnable report with its method named.

- **Domain**: `mcpanalytics.ai`
- **Provider**: MCP Analytics (https://mcpanalytics.ai)
- **Kind**: a2a_agent
- **Live-responds (last probe)**: False
- **Signed card**: False
- **Streaming**: False
- **Quality score**: 73%

## Skills
- **account link** — 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.
- **about** — Platform documentation and info: how it works, tiers, usage.
- **agent advisor** — AI help desk: which analysis fits your question, interpreting results, fixing errors. Multi-turn.
- **datasets upload** — Get your data in. Pass `data` as an array of row objects to create the dataset immediately and get a dataset_ref ready for create_analysis; omit it to get an up
- **datasets list** — List and search your uploaded datasets, with fuzzy matching on name, description, and tags. Returns each dataset's uuid:// reference for use in create_analysis 
- **discover tools** — Browse the analyses you can run: the ones you commissioned plus the platform Standard Library (prebuilt tools; each result tagged source:'own' or 'standard_libr
- **tools schema** — Get an analysis's parameter schema. ALWAYS call before run_analysis.
- **run analysis** — Run an analysis on your data. Returns a shareable interactive report URL with statistics you can cite, re-run and share, and the method named.
- **create analysis** — Commission a NEW analysis built for your question. tier is REQUIRED. The user picks. Easiest: fuzzy_request (plain language) + dataset_ref + tier. Snapshot = in
- **modify analysis** — Modify an EXISTING analysis into a new version: reword the question, swap the method, or add a variable. Pass tool_name + changes (plain language). Rebuilds on 
- **request estimate** — START HERE for a new question: free, ~30 s. A rough answer over a sample plus the layout of the complete package, every place named with the question it will an
- **review estimate** — 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 r
- **adjust estimate** — Apply the user's layout wishes to the estimate's page through the layout agent; a new named arrangement, nothing overwritten, no number changes.
- **answer now** — A read of the data (average, count, total, highest/lowest by group, a value in a month) answered in this response, in seconds. Not a read -> immediate=false wit
- **decide path** — Step 0 for a new question: which path answers it on this data. One record: route (reuse | answer | package | ask | none), a score with its reason for each of an
- **find precedent** — 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
- **check tool fit** — 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. R
- **order analytics package** — Order what the estimate promised after reviewing it: library tools that fit, a bespoke build, or both, computed on the whole dataset; one reviewed page delivere
- **package status** — Read an analytics package back: status, every run under it, the report link once delivered.
- **rerun package** — Run a delivered package again, on its own data or new data: the same tools, the same curated objects, the same layout, as a new package with its own link.
- **my objects** — List and search the objects you own across every question: the curated charts, tables and figures of each delivered package, grouped by objective.
- **build status** — 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 delive
- **ask library** — Ask a question across all your delivered analyses: a synthesized answer with citations back to specific reports.
- **reports list** — Your report library: every analysis delivered, with status and links. Pass semantic_query to search report content in plain language.
- **warehouse** — Query your org's data warehouse free: browse the catalog (tables with column roles + computed metrics), semantically find data, plain-language ask, or named tem
- **schedules** — Standing re-runs of analyses you own: action='create' (weekly/monthly against a re-runnable data reference, connector:// or an https:// link; report emailed aft
- **reports view** — Get a shareable browser link for a report, viewable without authentication.
- **report cards** — Browse a delivered report's individual cards (charts, tables, insights) inline in chat.

## URLs
- Agent card: https://mcpanalytics.ai/.well-known/agent.json
- Page (HTML): https://agenstry.com/agents/mcpanalytics.ai
- Documentation: https://mcpanalytics.ai/docs/quickstart