Categories › AI & Agents › Multi-agent, orchestration & workflows
Buffrota: the site's own MCP server — dataset, enquiry (enquiry = a human handoff, not a...
Remote server: your requests and data go to buffrota.com. Claude Code: claude mcp add --transport http site https://buffrota.com/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
dataset_columns — The columns, which of them are numeric, the row count and the provenance banner of the Buffrota dataset. Call this first to learn the schemadataset_search — Rows of the Buffrota dataset whose cells contain the query (case-insensitive), up to 50.dataset_row — The rows of the Buffrota dataset where a column equals a value exactly (case-insensitive).dataset_compare — The rows of the Buffrota dataset whose column is any of the given values, in the order given, for "X vs Y" questions.dataset_stats — count, min, max, mean, median and sum of a numeric column of the Buffrota dataset (grouping commas and currency are handled; non-numeric rowdataset_top — The highest (or lowest) rows of the Buffrota dataset by a numeric column: "which is the most/least X".dataset_provenance — The source, the date it was computed, the licence and the citation for the Buffrota dataset. Read this to attribute a figure correctly.enquiry_describe — Read first. States plainly what submit_enquiry does on Buffrota: it starts an enquiry with Buffrota, whose team reads it and replies directlenquiry_fields — Every field of the Buffrota enquiry: key, label, type, whether required, help text and the allowed options where there are any. Pass answerssubmit_enquiry — Submits an enquiry to Buffrota: NOT a purchase, NOT a guaranteed quote. Step 1: call with the answers (keyed by field key from enquiry_fieldNot tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.