Developer · Local MCP server

Dataloupe

Offline MCP server to explore CSV/JSON/Parquet/Excel: preview, query, diff, render interactive HTML.

Visit Dataloupe's website

What the MCP Registry states

The entry as published to the official MCP Registry (read 2026-10-04), latest version.

Registry name
io.github.aurelio-nakamura/dataloupe
Version
0.15.0
Status
Active
Category
developer
Transport
stdio (local process)
Package
OCI image (Docker)
Published
2026-09-01
Updated
2026-09-01
Publisher
aurelio-nakamura (GitHub) · 2 servers with pages here
Listed under
Excel MCP servers
Website
aurelio-nakamura.github.io/dataloupe/
Repository
github.com/aurelio-nakamura/dataloupe
Source
Registry API entry

Packages

RegistryPackageVersionTransportEnvironment variables
OCI image (Docker)runtime: dockerghcr.io/aurelio-nakamura/dataloupe:0.15.0—stdioDATALOUPE_MCP_ROOT

How to connect Dataloupe

Dataloupe runs locally from a container image in an OCI registry such as Docker Hub or GitHub Container Registry: ghcr.io/aurelio-nakamura/dataloupe:0.15.0. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Docker or another OCI container runtime; started with docker run — the usual command is docker run -i --rm -e DATALOUPE_MCP_ROOT ghcr.io/aurelio-nakamura/dataloupe:0.15.0. It reads the environment variable DATALOUPE_MCP_ROOT; set it in the client's configuration for this server. Required arguments: -i, --rm and --mount.

In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):

{
  "mcpServers": {
    "dataloupe": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "DATALOUPE_MCP_ROOT",
        "ghcr.io/aurelio-nakamura/dataloupe:0.15.0"
      ],
      "env": {
        "DATALOUPE_MCP_ROOT": "<value>"
      }
    }
  }
}

Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect

More from aurelio-nakamura (GitHub)

All 2 →
ServerRunsEndpoint or package
cmdxrayOffline MCP server: explains shell commands token-by-token and flags destructive ones for AI agents.Local · stdionpm: cmdxray

More developer servers

All 6,250 →
ServerRunsEndpoint or package
Datadog MCPFull Datadog API access: monitors, logs, metrics, traces, dashboards, and observability tools.Local · stdionpm: datadog-mcp
dataecho.aiDeploy files, sites, and Dockerfile apps to live URLs + private drives for agent memory.Remote · HTTPdataecho.ai
DatahogoScan a project for security issues locally with the open-source Data Hogo engine.Local · stdionpm: @datahogo/mcp
DataLinkMCP server for secure database access (PostgreSQL, MySQL, SQLite)Local · stdionpm: @pilat/mcp-datalink
datamcp — Hosted Model Context Protocol for Databases, APIs, and Agent MemoryPostgreSQL, MySQL, OpenAPI/Swagger, and shared Agent Memory with scoped access.Remote · HTTPapi.datamcp.app
Datamuse MCPUse this MCP server to wordplay. Rhymes, related words, spell checks, and word suggestions for...Local · stdionpm: @mrfentmen/datamuse-mcp
Datasaudi MCPSaudi economic & social statistics (GASTAT/DataSaudi) in English or Arabic. Keyless, no database.Local · stdioPyPI: datasaudi-mcp
DataSentryLocal-first MCP server for data-quality discovery, evidence, drift, and controlled repair.Local · stdioPyPI: datasentry-ai