MCP For Claude Marketplace
DataFrame Aggregator Engine

DataFrame Aggregator Engine MCP Connector for Claude

C

Perform blazingly fast GroupBy and Aggregations on massive CSVs local. Save millions of AI tokens and get mathematically perfect sums, means, and counts.

1 tools Official Updated Jun 28, 2026 Official Vinkius Partner
More Details Connect to Claude

If you feed a 1,000,000-row CSV to an LLM and ask it to 'group by Region and sum the Revenue', the AI will either crash due to context limits or hallucinate the result.

This MCP delegates heavy data wrangling to arquero, an industry-standard high-performance JS data engine. The AI orchestrates the query, passes the raw CSV, and the engine computes exact sums, means, and counts instantly.

The Superpowers

  • Massive Token Savings: The AI only reads the aggregated output, not the millions of raw rows.
  • Zero Hallucination: Deterministic math performed by your CPU — not estimated by a language model.
  • Blazing Fast: Powered by Arquero, the gold-standard JS data wrangling library used in academic visualization research.
  • Multi-Aggregation: Apply different aggregation types to different columns in a single call.
data-wranglingcsv-processingdata-aggregationgroup-byhigh-performance-computingdata-processing

1 tools expose this connector's capabilities to your AI agent.

aggregate_dataframe

Perform extremely fast, deterministic GroupBy, Pivot, and Aggregations on massive CSV strings offline

See how to talk to your AI agent using DataFrame Aggregator Engine.

Group this sales CSV by 'Region' and calculate the sum of 'Revenue' and the average 'Discount'.

Aggregation complete. North America: Revenue $4.2M, Avg Discount 12%. Europe: Revenue $3.1M, Avg Discount 8%. Asia: Revenue $2.8M, Avg Discount 15%.

Find the average 'Age' and 'Salary' grouped by 'Department' in this HR dataset.

I've rolled up the data by Department. Engineering averages 34 years and $120k salary. Marketing averages 31 years and $95k salary.

Count the number of active users in each country from this 4.5 million row export.

Arquero processed 4.5 million rows in 1.2 seconds. The US has 2.1M active users, UK has 800k, Germany has 420k, and France has 310k.

The engine runs locally via Node.js, meaning it can handle gigabytes of CSV data as long as your machine has sufficient RAM. There is no artificial size cap.

Related Connectors

PA

PandaDoc MCP

10 tools Official

Create, send, and track documents, proposals, and e-signatures via PandaDoc — manage the entire document lifecycle from any AI agent.

A+ View details →
AP

Appcues MCP

11 tools Official

Manage your Appcues flows, segments, and user experiences with AI — track activity and publish content effortlessly.

F View details →
EV

Eventmix MCP

12 tools Official

Organize events with integrated registration, payment processing, and attendee communication for conferences and meetups.

A+ View details →
GA

Gatling MCP

10 tools Official

Manage load testing via Gatling Enterprise — list and start simulations, monitor test runs and request stats, and handle generator pools directly from any AI agent.

A+ View details →