Is Upsilon — AI Operator Measurement Engine safe and trustworthy?

tashan scores Upsilon — AI Operator Measurement Engine on public evidence — tashan score 71.0/100, it is currently active, note: a single primary maintainer (bus-factor risk), no known advisories against the current release. Audit scope: OSV advisories, install-time scripts, build provenance and declared permission surface. We do not review source code or execute the capability.

How do I install Upsilon — AI Operator Measurement Engine?

In Claude Code: run `claude mcp add sigrank -- npx -y sigrank`. In Cursor / Claude Desktop, add it to mcp.json / claude_desktop_config.json.

Who maintains Upsilon — AI Operator Measurement Engine?

source: SunrisesIllNeverSee/sigrank-mcp.

‹ The Index

Upsilon — AI Operator Measurement Engine

npm

Upsilon measurement engine with 25 local tools and SigRank proof access via the sigrank package.

Works with: Claude Code, Cursor, Claude Desktop, Codex CLI, Gemini CLI, Cline, Windsurf, VS Code (installable)
installable: each client documents how to load an MCP server of this type — that is the client's promise, not a claim verified against this capability

Category: Communication — see all ranked ›

Install (Claude Code):

claude mcp add sigrank -- npx -y sigrank

deep

“7 tools documented (rank_windows, watch_tokenpull…); 9 worked examples; setup and auth covered; states a limit — “When stdout is not a TTY (i.e”; read with 1 linked doc(s)”

This grade is wrong ›

tashan score: 71.0
Instruction depth: 86.0 (deep — documents every tool, with worked examples, setup and a stated limitation)
Adoption: 2.6k/wk
Upkeep: 73.0
Freshness: 99.0
Evidence coverage: 100% of the inputs this score can use
Health: active
License: MIT

Security audit

Every finding is shown in full — which advisory, the version that fixes it, and the exact command run at install time. Nothing in this audit is behind a licence.

No known advisoriesclearchecked against OSV for 1.0.40 — this package, not its dependency tree

No access inferred from declared dependenciesnothing it depends on reaches files, shell or network. This reads declarations only — built-in APIs are invisible to it, so absence of a declaration is not absence of access

No build provenanceno attestation — the published artifact cannot be traced to its source

What changed recently

2026-08-17 sigrank published 0.0.205, was 0.0.195 A new release is available.
2026-08-19 sigrank published 0.0.221, was 0.0.205 A new release is available.
2026-08-27 sigrank published 1.0.1, was 0.0.221 A new release is available.

You are reading this because you came looking. tashan Pro gives tashan doctor the history behind it, so a run over your own config says which of YOURS moved.

You searched for one. Check the rest of your stack:

npx tashan-cli doctor

Reads the config already on your machine and names what is dead, deprecated or running code at install time. No account, nothing uploaded.

tashan Pro$6/mo

We recorded 4 changes to Upsilon — AI Operator Measurement Engine in the last 45 days. Pro tells you on the day — for the servers in your own config, not the ones you thought to look up.

Every score since we started measuring, for any capability
The named replacement when something you run is dying — not just that it is
tashan doctor over the config you already have, on your machine

Start a 7-day trial › Everything measured on this page stays free.

Show your score

Measured this well? Put the live badge in your README — it updates as the score does.

[![tashan](https://tashan.sh/badge/pkg-sigrank.svg)](https://tashan.sh/capability/pkg-sigrank.html)

npm ↗ · source ↗ · pkg:sigrank

Already running this? Check your whole config — free, in your browser, nothing installed. Or npx tashan-cli doctor locally, which sends nothing at all.

Measured 2026-09-13 · scorer s5 · how · something wrong here?