Home › Databases & Data › Dataloupe
Dataloupe
Offline MCP server to explore CSV/JSON/Parquet/Excel: preview, query, diff, render interactive HTML
Topics: Data Science Tools
Connect
Review any command before running it. Package names and URLs come from the server's own registry entry.
Package (oci)
docker run -i --rm ghcr.io/aurelio-nakamura/dataloupe:0.15.0
Or add to your MCP client config:
{
"mcpServers": {
"dataloupe": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/aurelio-nakamura/dataloupe:0.15.0"
]
}
}
}
DATALOUPE_MCP_ROOT— Directory the server is allowed to read data files from (inside the container). Defaults to /data.
This server takes extra arguments — see its repository.
Related servers
vizro
Create validated, maintainable data charts and dashboards with Vizro tools and templates.
markdownify-mcp
Convert almost any file or web content into Markdown.
jupyter-mcp-server
Interact with Jupyter.
dingo
Data quality evaluation with Dingo: run rule-based and LLM-based evaluations and list its rules and prompts.
mcp-server-data-exploration
Autonomous data exploration of CSV datasets with generated insights.
jupyter-notebook-mcp
Interact with and control Jupyter Notebooks.
Listed in punkpeye/awesome-mcp-servers (MIT)
Data from the Official MCP Registry