Command Palette

Search for a command to run...

UnylyUnyly
Browse all

Stats

FreeNot checked

MCP server: descriptive statistics over a numeric array.

GitHubEmbed

About

MCP server: descriptive statistics over a numeric array.

README

npm mcp

MCP server: descriptive statistics over a numeric array. Returns count, sum, mean, median, min, max, sample stddev/variance, and configurable percentiles (linear interpolation, NumPy-default). No deps.

Tool

summary

{ "values": [1, 2, 3, 4, 5, 6, 7, 8, 9, 10] }

{
  "count": 10, "sum": 55,
  "mean": 5.5, "median": 5.5,
  "min": 1, "max": 10,
  "stddev": 3.027650, "variance": 9.166667,
  "percentiles": { "p25": 3.25, "p50": 5.5, "p75": 7.75, "p90": 9.1, "p95": 9.55, "p99": 9.91 }
}

Default percentiles: [25, 50, 75, 90, 95, 99]. Override via percentiles: [...].

Configure

{ "mcpServers": { "stats": { "command": "npx", "args": ["-y", "@mukundakatta/stats-mcp"] } } }

License

MIT.

from github.com/MukundaKatta/stats-mcp

Installing Stats

This server has no published package — it is built from source. Open the repository and follow its README.

▸ github.com/MukundaKatta/stats-mcp

FAQ

Is Stats MCP free?

Yes, Stats MCP is free — one-click install via Unyly at no cost.

Does Stats need an API key?

No, Stats runs without API keys or environment variables.

Is Stats hosted or self-hosted?

Self-hosted: the server runs locally on your machine via the install command above.

How do I install Stats in Claude Desktop, Claude Code or Cursor?

Open Stats on unyly.org, pick your client tab (Claude Desktop, Claude Code, Cursor) and press Install — the config is generated automatically, no JSON editing.

Related MCPs

Compare Stats with

Not sure what to pick?

Find your stack in 60 seconds

Author?

Embed badge for your README

Browse similar

All ai MCPs