Categories › AI & Agents › Agent memory & context
Procedure Cost Checker: the site's own MCP server — dataset, enquiry (enquiry = a human handoff,...
Remote server: your requests and data go to procedurecostchecker.com. Claude Code: claude mcp add --transport http site https://procedurecostchecker.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 Procedure Cost Checker dataset. Call this first to ledataset_search — Rows of the Procedure Cost Checker dataset whose cells contain the query (case-insensitive), up to 50.dataset_row — The rows of the Procedure Cost Checker dataset where a column equals a value exactly (case-insensitive).dataset_compare — The rows of the Procedure Cost Checker 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 Procedure Cost Checker dataset (grouping commas and currency are handled; ndataset_top — The highest (or lowest) rows of the Procedure Cost Checker 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 Procedure Cost Checker dataset. Read this to attribute a figure cenquiry_describe — Read first. States plainly what submit_enquiry does on Procedure Cost Checker: it starts an enquiry with Procedure Cost Checker, whose team enquiry_fields — Every field of the Procedure Cost Checker enquiry: key, label, type, whether required, help text and the allowed options where there are anysubmit_enquiry — Submits an enquiry to Procedure Cost Checker: NOT a purchase, NOT a guaranteed quote. Step 1: call with the answers (keyed by field key fromNot tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.