MCP For Claude Marketplace
Missing Value Imputer

Missing Value Imputer MCP Connector for Claude

F

Automatically fill NaN and missing values in datasets using Mean, Median, Mode, or Zero strategies deterministically local. Essential ML data preparation.

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

Preparing a dataset for machine learning requires handling missing values. Asking an LLM to find and replace NaN entries row-by-row in a 10,000-row JSON consumes an absurd amount of context tokens and is guaranteed to corrupt your data.

This MCP delegates the imputation logic to a local engine powered by simple-statistics. The AI sends the raw data, and the engine mathematically computes the exact Mean, Median, or Mode across all valid entries, then seamlessly replaces every missing value — all in memory, all local.

The Superpowers

  • Zero Hallucination: The fill value is computed exactly from your data by the CPU, never estimated by a language model.
  • Multiple Strategies: Choose Mean, Median, Mode, or Zero filling depending on your statistical needs.
  • Fast and Private: Processes thousands of rows in milliseconds entirely on your machine.
  • Transparent Reporting: Returns the exact fill value applied and the number of rows imputed for full auditability.
data-cleaningmachine-learning-prepstatistical-analysisdata-imputationnan-handlingdeterministic-math

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

impute_missing_values

Deterministically fill NaN/missing values in a dataset using Mean, Median, Mode, or Zero

See how to talk to your AI agent using Missing Value Imputer.

Fill all missing values in the 'Age' column with the median age of the dataset.

Done. The computed median age was 34 years. 15 missing rows were successfully imputed. Here is a preview of the first 10 cleaned rows.

Use the mean strategy to fix the NaN values in the 'Salary' column before I train my model.

The missing salary fields have been replaced with the exact mean of $85,420. 42 rows were imputed. The dataset is now clean and ready for model training.

Replace all missing discount entries with zero since no discount should be assumed.

I've replaced 243 missing Discount entries with 0. This preserves the business logic that no discount was applied to these transactions.

No. The engine processes the JSON payload entirely in memory and returns the cleaned array back to the AI. Your original files are never touched.

Related Connectors

BP

Baota Panel / 宝塔面板 API MCP

10 tools Official

Leading server management panel in China — manage websites, databases, and system resources via AI.

A+ View details →
LI

LiftedWork MCP

6 tools Official

Connect job seekers with employment opportunities through a platform that matches skills to openings and tracks applications.

A+ View details →
KI

Kindful MCP

12 tools Official

Manage nonprofit fundraising and donor relationships via Kindful — query contacts, track transactions, and monitor campaigns directly from your AI agent.

A+ View details →
CC

Concord CLM MCP

10 tools

Enable your AI agent to manage contracts, send documents for signature, and track agreement statuses via the Concord CLM API.

A+ View details →