Home / MCP / Data Wrangling MCP Server
Provides a standardized MCP server for data wrangling tasks including data aggregation and descriptive statistics.
Configuration
View docs{
"mcpServers": {
"data_wrangler": {
"command": "uv",
"args": [
"--directory",
"/path/to/mcp-data-wrangler",
"run",
"mcp-data-wrangler"
]
}
}
}You can run an MCP server dedicated to Data Wrangling tasks, enabling standardized data preprocessing, transformation, and analysis within the MCP ecosystem. This server focuses on aggregating data and computing descriptive statistics, making it easier to integrate wrangling steps into your workflows.
To use this MCP server, connect your MCP client to the provided MCP endpoint or start the local stdio server as described. You will be able to perform data wrangling operations such as aggregation and descriptive statistics on your datasets, then feed the results into downstream MCP pipelines.
Prerequisites you need before starting:
Install Node.js and npm on your machine to access the MCP inspector tooling.
Clone the project repository to your local machine and navigate into the project directory.
Option 1: Run as an MCP server using the local runtime (stdio) with uv. This starts the server in-process and exposes an MCP endpoint for you to connect a client to.
Option 2: Launch the MCP inspector to debug or explore the Data Wrangling server and then run it via the inspector if you prefer an interactive debugging flow.
The Data Wrangling MCP server provides two core capabilities: data aggregation and descriptive statistics. Ensure your client is configured to send appropriate data structures for wrangling and that the environment has access to the datasets you intend to process.
Aggregates data from multiple sources, supports grouping, sum/avg/count computations, and produces summarized results for downstream analysis.
Calculates descriptive statistics such as mean, median, mode, standard deviation, and percentiles to provide quick insights into datasets.