Categories › AI & Agents › Models, LLM APIs, routing, serving, training & GPUs
Hreflangly: the site's own MCP server — dataset; every answer cites the site.
Remote server: your requests and data go to hreflangly.com. Claude Code: claude mcp add --transport http site https://hreflangly.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 Hreflangly dataset. Call this first to learn the schedataset_search — Rows of the Hreflangly dataset whose cells contain the query (case-insensitive), up to 50.dataset_row — The rows of the Hreflangly dataset where a column equals a value exactly (case-insensitive).dataset_compare — The rows of the Hreflangly 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 Hreflangly dataset (grouping commas and currency are handled; non-numeric rdataset_top — The highest (or lowest) rows of the Hreflangly 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 Hreflangly dataset. Read this to attribute a figure correctly.Not tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.