Sittingly: the site's own MCP server — dataset; every answer cites the site.
Scored across 7 tools
Most tools have clearly distinct purposes: schema discovery, provenance, exact lookup, substring search, stats, and top/bottom ranking are easy to tell apart. However, dataset_row and dataset_compare overlap in that both do exact column-value matching, with compare merely extending row to multiple values, which could cause some selection uncertainty.
All tools share the clean dataset_ prefix and use lowercase snake_case, making the set feel cohesive. The second part mixes nouns (columns, provenance, row, stats, top) with verbs (compare, search), but the pattern is still predictable and readable.
Seven tools is a well-scoped size for a dataset-querying server. Each tool covers a distinct query need without redundancy or bloat, and the count is comfortably within the ideal range.
The server covers the full read-only lifecycle of working with a dataset: schema discovery, provenance attribution, exact lookup, substring search, comparisons, numeric stats, and top/bottom ranking. There are no obvious dead ends for the stated purpose.
The columns, which of them are numeric, the row count and the provenance banner of the Sittingly dataset. Call this first to learn the schema.
Inputs: no named parameters.
The rows of the Sittingly dataset whose column is any of the given values, in the order given — for "X vs Y" questions.
Inputs: column (required), values (required).
The source, the date it was computed, the licence and the citation for the Sittingly dataset. Read this to attribute a figure correctly.
Inputs: no named parameters.
The rows of the Sittingly dataset where a column equals a value exactly (case-insensitive).
Inputs: value (required), column (required).
Rows of the Sittingly dataset whose cells contain the query (case-insensitive), up to 50.
Inputs: query (required), limit.
count, min, max, mean, median and sum of a numeric column of the Sittingly dataset (grouping commas and currency are handled; non-numeric rows are excluded and counted).
Inputs: column (required).
The highest (or lowest) rows of the Sittingly dataset by a numeric column — "which is the most/least X".
Inputs: column (required), limit, ascending.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Tieoutly: the site's own MCP server — dataset; every answer cites the site.
Cmmsly: the site's own MCP server — dataset; every answer cites the site.
Sopvo: the site's own MCP server — dataset; every answer cites the site.
Sbarvo: the site's own MCP server — dataset; every answer cites the site.
Add one secure layer between your agents and this server.