Databutler Stats is a remote MCP server that gives an AI agent 6 tools, among them bayes_update, confidence_interval, descriptive_stats. It answers at https://databutler.dev/api/mcp/stats over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 6 of 6 times since 11 September 2026; the last check, on 23 October 2026, succeeded.
Exact statistics & probability: distributions, hypothesis tests, CIs, Bayesian updates, regression.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
bayes_update | Discrete Bayesian update: given competing hypotheses each with a prior and the likelihood of the observed evidence, return normalised posteriors. Priors are renormalised to sum to 1. Inputs: hypotheses |
confidence_interval | Confidence interval for a mean (t-based; from data, or n/mean/sd) or a proportion (Wilson; successes/n). kind = mean | proportion; confidence default 0.95. Inputs: kind, confidence, data, n, mean, sd |
descriptive_stats | Summary statistics for a numeric array: mean, median, sd, variance, quartiles, IQR, skewness, min/max. Inputs: data |
distribution | Evaluate a probability distribution (normal, t, chi2, binomial, poisson): pdf/pmf and cdf at a value, and/or the quantile at a probability, plus mean & variance. Params per dist: normal {mean,sd}, t {df}, chi2 {df}, binomial {n,p}, poisson Inputs: dist, params, at, p |
hypothesis_test | Run a significance test and get the statistic, p-value, and a plain-language interpretation with assumptions. test = one-sample-t {data, mu0}, two-sample-t {data1, data2}, one-proportion-z {successes, n, p0}, two-proportion-z {successes1,n1 Inputs: test, data, data1, data2, mu0, successes |
linear_regression | Simple linear regression of y on x: slope, intercept, r, r², slope std error and p-value, equation. Inputs: x, y |
Every block below points at https://databutler.dev/api/mcp/stats. Pick your client and copy.
claude mcp add --transport http databutler-stats https://databutler.dev/api/mcp/stats
{
"mcpServers": {
"databutler-stats": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://databutler.dev/api/mcp/stats"]
}
}
}{
"mcpServers": {
"databutler-stats": {
"url": "https://databutler.dev/api/mcp/stats"
}
}
}{
"servers": {
"databutler-stats": {
"type": "http",
"url": "https://databutler.dev/api/mcp/stats"
}
}
}{
"context_servers": {
"databutler-stats": {
"url": "https://databutler.dev/api/mcp/stats"
}
}
}{
"mcpServers": {
"databutler-stats": {
"serverUrl": "https://databutler.dev/api/mcp/stats"
}
}
}{
"mcpServers": {
"databutler-stats": {
"url": "https://databutler.dev/api/mcp/stats"
}
}
}name: Databutler Stats
version: 0.0.1
schema: v1
mcpServers:
- name: Databutler Stats
type: streamable-http
url: https://databutler.dev/api/mcp/stats{
"mcpServers": {
"databutler-stats": {
"httpUrl": "https://databutler.dev/api/mcp/stats"
}
}
}{
"mcpServers": {
"databutler-stats": {
"type": "http",
"url": "https://databutler.dev/api/mcp/stats"
}
}
}{
"mcpServers": {
"databutler-stats": {
"url": "https://databutler.dev/api/mcp/stats"
}
}
}goose://extension?url=https%3A%2F%2Fdatabutler.dev%2Fapi%2Fmcp%2Fstats&type=streamable_http&id=databutler-stats&name=Databutler%20Stats
It answered our last check on 23 October 2026 in 190 ms. Over 6 checks since 11 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.
6, as returned by the server's own tools/list on 17 September 2026: bayes_update, confidence_interval, descriptive_stats, distribution, hypothesis_test, linear_regression.
It answered our last check on 23 October 2026 in 190 ms. Over 6 checks since 11 September 2026 it answered 6.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://databutler.dev/api/mcp/stats. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: io.github.physics-star-cat. Endpoint host: databutler.dev. ARD identifier: urn:air:io.github.physics-star-cat:mcp:databutler-stats.
First indexed 10 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.