Deflectvo: the site's own MCP server — dataset; every answer cites the site.
Scored across 7 tools
Tools are mostly distinct: columns, provenance, stats, and top are clearly separate. There is some overlap between dataset_compare, dataset_row, and dataset_search for retrieving rows, but the descriptions clarify exact vs substring vs multi-value filtering, reducing confusion.
All tools share the 'dataset_' prefix, providing strong consistency. The second part mixes nouns (columns, provenance, row, stats, top) and verbs (compare, search), which is a minor deviation but still predictable and readable.
With 7 tools, the server is well-scoped for a dataset querying purpose. Each tool addresses a distinct query pattern (schema, provenance, search, exact match, comparison, stats, top/bottom) without redundancy or bloat.
The tool surface covers the main query types needed for exploring a dataset: schema, provenance, search, filter, stats, and ranking. Missing a 'list all' or 'distinct values' tool, but for typical analytical questions the coverage is strong and no dead ends are apparent.
The columns, which of them are numeric, the row count and the provenance banner of the Deflectvo dataset. Call this first to learn the schema.
Inputs: no named parameters.
The rows of the Deflectvo 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 Deflectvo dataset. Read this to attribute a figure correctly.
Inputs: no named parameters.
The rows of the Deflectvo dataset where a column equals a value exactly (case-insensitive).
Inputs: value (required), column (required).
Rows of the Deflectvo 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 Deflectvo dataset (grouping commas and currency are handled; non-numeric rows are excluded and counted).
Inputs: column (required).
The highest (or lowest) rows of the Deflectvo 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…
Funnelvo: 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.
Exitvo: the site's own MCP server — dataset; every answer cites the site.
Duesvo: the site's own MCP server — dataset; every answer cites the site.
Add one secure layer between your agents and this server.