tableski
Server Details
Every live trading feed is a table: today it serves your CSV, Parquet and JSON files to AI agents as SQL tables (Apache DataFusion), with joins across files, schema and column statistics. Open source: github.com/yarenty/tableski
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-03-26
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 5 tools
column_statistics and get_schema both describe table structure but clearly differ (stats vs. types/nullability), and query_sql vs export_result differ only in output destination (grid vs. file), which descriptions make explicit. The boundaries are mostly clear; only the query/export pair could occasionally be confused.
Four tools follow a verb_noun pattern (list_tables, get_schema, query_sql, export_result). column_statistics deviates as a noun phrase, a minor inconsistency in an otherwise readable convention.
Five tools is well-scoped for a SQL-over-registered-tables server, with each tool covering a distinct step (discover, inspect, query, export). No filler tools.
Discovery, schema inspection, statistics, querying, and export are all covered, forming a complete analysis workflow. The main gap is no tool to register or unregister tables, presumably handled externally, and no lightweight row-preview separate from full queries.
Publisher details
- Operator
- Skycorp Limited (Ireland, company number 550375) · Publisher source
- Operator website
- https://tableski.io
- Vendor relationship
- First-party
- Documentation
- https://github.com/yarenty/tableski/tree/main/demo
- Privacy policy
- Not provided
- Trust center
- Not available
- Restrictions
- Needs a free tableski.io account and an access token. Free plan: 25 questions a day, 10 a minute; paid plans raise both. · Publisher source
Available Tools
5 toolscolumn_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.
list_tablesAInspect
List every registered table: name, source file, source sheet (for workbooks), rows and columns.
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Every live trading feed is a table (work in progress): data files as SQL tables for AI agents.
The stock market, in SQL — scan, replay, or subscribe across ~12k US tickers and top 100 cryptos.
Aligned market data for AI agents: crypto, stocks, FX and macro on one clock. Local or hosted.
The all-in-one data stack for agents. Upload files, run SQL, evolve tables, and render charts.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceEvery live trading feed is a table: today it serves your CSV, Parquet and JSON files to AI agents as SQL tables (Apache DataFusion), with joins across files, schema and column statistics.1Apache 2.0
- AlicenseAqualityCmaintenanceTurns a folder of CSV, Parquet, and JSON files into a single SQL-queryable source for AI agents, supporting JOINs across files with read-only sandboxed access.62MIT
- AlicenseCqualityBmaintenanceEnables querying and replaying deterministic market data for crypto and US equities from a local Parquet lake via natural language.584Apache 2.0
- AlicenseNot gradedqualityBmaintenanceQuery 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.5MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.