Skip to main content
Glama

Server Details

HardscapeDesk: the site's own MCP server — dataset; every answer cites the site.

If you are the author of this connector, you can claim ownership. Claimed connector authors can inspect health checks, view analytics, and manage their listing.
Status
Healthy
Uptime
100.0% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
ChatGPT
–
Claude
–

TDQS

A3.7/5.0

Scored across 7 tools

Disambiguation4/5

Each tool maps to a fairly distinct query intent (schema, provenance, exact row match, substring search, multi-value comparison, statistics, ranking), and the descriptions explicitly differentiate them. The only real overlap is between dataset_row (single exact equality), dataset_compare (multiple values, ordered) and dataset_search (substring contains), which an agent could plausibly confuse for a simple filter.

Naming Consistency5/5

All seven tools share a strict `dataset_<operation>` prefix pattern with short, lowercase noun/verb operation names. No mixing of conventions or stray synonyms within the set.

Tool Count5/5

Seven tools is well-scoped for a read-only dataset Q&A server; each one covers a distinct query mode and none feels redundant filler. Nothing obviously missing from a minimal query surface perspective.

Completeness4/5

The surface covers schema discovery, provenance/attribution, filtering, search, statistics and ranking, which handles most question types over a single table. Gaps remain for grouped aggregation (e.g. stats per category) or multi-condition filtering, which agents would have to work around manually.

Available Tools

7 tools
dataset_columnsDataset columns and shapeAInspect

The columns, which of them are numeric, the row count and the provenance banner of the HardscapeDesk dataset. Call this first to learn the schema.

Inputs: no named parameters.

dataset_compareCompare rows side by sideCInspect

The rows of the HardscapeDesk dataset whose column is any of the given values, in the order given, for "X vs Y" questions.

Inputs: column (required), values (required).

dataset_provenanceWhere this data comes from, and how to cite itAInspect

The source, the date it was computed, the licence and the citation for the HardscapeDesk dataset. Read this to attribute a figure correctly.

Inputs: no named parameters.

dataset_rowLook a row up by an exact keyAInspect

The rows of the HardscapeDesk dataset where a column equals a value exactly (case-insensitive).

Inputs: value (required), column (required).

dataset_statsSummary statistics for a numeric columnAInspect

count, min, max, mean, median and sum of a numeric column of the HardscapeDesk dataset (grouping commas and currency are handled; non-numeric rows are excluded and counted).

Inputs: column (required).

dataset_topRank rows by a numeric columnBInspect

The highest (or lowest) rows of the HardscapeDesk dataset by a numeric column: "which is the most/least X".

Inputs: column (required), limit, ascending.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      B
      maintenance
      MCP server for academic research with shared token bucket governance, evidence-based read depth, and archival inscription. Uses multiple sources with failover to avoid rate limits.
      6
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      A local-first MCP server that analyzes research papers, maps citation graphs, and surfaces insights with verbatim-verified contradictions, all while keeping data private on your machine.
      1
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      An MCP server that acts as a governed customer-support tool, resolving questions only when the knowledge base supports a cited, grounded answer and honestly escalating everything else with provenance and evidence.
      27 PyPI
      MIT
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources