Skip to main content
Glama

Server Details

Every spreadsheet is a table: Excel, CSV, Parquet and JSON as SQL tables for AI agents.

Ownership verified
Status
Healthy
Uptime
100.0% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2025-03-26
URL
Repository
yarenty/tableski
GitHub Stars
1
Server Listing
tableski
ChatGPT
–
Claude
–

TDQS

B3.4/5.0

Scored across 7 tools

Disambiguation4/5

Most tools have clearly distinct roles: list_tables, get_schema, and column_statistics form a natural progression (list → structure → stats), and query_sql vs export_result differ by output destination (grid vs file). The only real ambiguity is between indicators (per-symbol recent bars) and market_snapshot (latest bar across all symbols), which both surface overlapping indicator values and could be confused; descriptions help but don't fully separate them.

Naming Consistency3/5

Half the tools use verb_noun (get_schema, list_tables, query_sql, export_result) while the other half are bare noun phrases (column_statistics, indicators, market_snapshot), giving a mixed convention. All names are snake_case and readable, so it is not chaotic, but the pattern is not predictable.

Tool Count5/5

Seven tools is well within a comfortable range, and each covers a distinct capability: table discovery, schema inspection, statistics, ad-hoc SQL, file export, per-symbol indicators, and a market overview. No tool feels like padding.

Completeness3/5

The read/query/export lifecycle for registered tables is covered, but every tool presumes tables are already 'registered' and there is no tool to register, import, or drop a table, which is a notable dead end for onboarding data. The market side is also thin, with no tool to list or configure tracked symbols directly (it relies on list_tables).

Available Tools

7 tools
column_statisticsBInspect

High-level statistics for every column of a registered table: count, null_count, mean, std, min, max (DataFusion describe).

Inputs: table.

export_resultAInspect

Run a SQL query and write the full result set to a .csv or .xlsx file inside the server's configured export directory. Returns the written path and dimensions.

Inputs: sql (required), file (required).

get_schemaBInspect

Return column names, Arrow data types, and nullability for a registered table (LIMIT 0 scan).

Inputs: table.

indicatorsAInspect

Recent bars with indicators for one symbol: close, changes, SMA 20/50/200, EMA 12/26, MACD with signal and histogram, RSI(14), Bollinger bands (20, 2), ATR(14), drawdown. Newest first. Market data for information only, not financial advice. Source: Kraken public OHLC, bars in UTC, only closed bars.

Inputs: symbol (required), limit, timeframe.

list_tablesAInspect

List every registered table: name, source file, source sheet (for workbooks), rows and columns.

Inputs: no named parameters.

market_snapshotAInspect

Latest closed 1-hour bar for each tracked market symbol (crypto and PAXG as a gold proxy): close, change over the last bar, 24 hours and 7 days, RSI(14), 50/200-bar moving averages, drawdown from the high of the stored history. Use list_tables for the full bars_* and indicators_* tables. Market data for information only, not financial advice. Source: Kraken public OHLC, bars in UTC, only closed bars.

Inputs: symbols.

query_sqlCInspect

Run an arbitrary SQL query against the registered tables (joins across tables/sheets work) and return a pretty-printed result grid.

Inputs: sql (required).

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
      Not graded
      quality
      D
      maintenance
      Enables querying Excel and CSV files using SQL via natural language, allowing AI assistants to analyze data without manual SQL writing.
      1
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Query local CSV, Parquet, JSON and TSV files with real SQL via DuckDB. Gives your AI coding tool ground-truth data access instead of hallucinated answers.
      5
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables AI assistants to query tabular data (CSV/TSV) using natural language with cell-level citations, supporting multi-tenant workspaces, access control, and semantic search.
      27
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables AI agents to query S3 data lakes using natural language, with support for CSV, JSON, Parquet and tools for data discovery, analysis, and metadata exploration.
      1
      MIT
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.