datadiffer MCP Server

by gauthierpiarrette Your server? Claim it

local only

datadiffer runs on your own machine — the client starts it, so there is no endpoint to ping. 83 installs a week from pypi. Last commit 28 Jul 2026.

Read-only table diffs with segment attribution: which slice of your data changed.

Installs per day peak 19 · avg 8 · +84% w/w

a month agotoday

Installs / week

pypi · datadiffer

Stars

8 open issues

28 Jul 2026

Last commit

from GitHub

MIT

License

Python

Nothing serious here today

Today is the operative word: we check datadiffer every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add datadiffer -- uvx datadiffer

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "datadiffer": {
      "command": "uvx",
      "args": [
        "datadiffer"
      ]
    }
  }
}

~/.codex/config.toml

[mcp_servers.datadiffer]
command = "uvx"
args = ["datadiffer"]

.cursor/mcp.json

{
  "mcpServers": {
    "datadiffer": {
      "command": "uvx",
      "args": [
        "datadiffer"
      ]
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "datadiffer": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "datadiffer"
      ]
    }
  }
}

Optional settings from the registry entry, left out of the block above: DATADIFFER_CONFIG (Path to datadiffer.toml holding named connections (run `datadiffer init` to scaffold one). Credentials never pass through tool arguments).

Alternatives to datadiffer

same job, measured the same way

Klar

by getklar

Read-only access to your Klar marketing attribution and profit data.

answering

Learn the Dao — Tao Te Ching

by learnthedao

Read, search and cite all 81 chapters of the Tao Te Ching, with per-rendering attribution.

4 tools answering

Consequential Analytics

by consequential

Read-only access to your Consequential eCommerce marketing analytics and attribution data.

answering

MySQL (read-only, switchable)

by shibbirweb

Read-only MySQL access, with the database and server switchable mid-conversation.

80 installs/wk local only

Human Survey

by sunsiyuan

Self-reported attribution: which channel and which creator your users first heard you from.

65 installs/wk local only

Showboard

by rohanbeingsocial

Your coding agent answers with dashboards: charts and tables from read-only SQL, Excel and CSV.

307 installs/wk local only

tktmanager Battle Intelligence

by tktmanager

Read-only season data with a purchased season; battle reports with a battle-report subscription.

answering

Orange Peel

by orangepeel

Cited Hermès price & resale market data as MCP tools, with attribution. Not affiliated.

6 tools answering

datadiffer — questions

Answers built from our own checks of this server.

Why is there no uptime for datadiffer?

datadiffer runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package datadiffer was installed 83 times last week.

How do I connect datadiffer?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls datadiffer straight from pypi; nothing to host, nothing to sign up for.

How many people use datadiffer?

The pypi package datadiffer was installed 83 times in the last week. Week over week that is +84%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is datadiffer open source?

Yes — it is published under the MIT licence, written in Python, 0 stars on GitHub and 8 open issues. The source link is on this page, so you can read exactly what it does with your data before you connect it.