Upsilon — AI Operator Measurement Engine MCP server

Read from the package source without running it. The installed server may list more.

• compare_operators

  Compares two operators side-by-side with a behavioral verdict. Fetches both profiles from the board and returns their yield, leverage, velocity, class, and rank side-by-side, plus a verdict explaining who is more efficient and why in power-user language. Use this when users ask 'compare operator X vs Y' or 'who is more efficient' or 'how do two AI users compare'. Intent: COMPARE_OPERATORS.

• compare_self

  Compares an operator's metrics against board averages and power-user archetypes, returning a behavioral assessment. Accepts either a codename (fetches from the board) or raw token pillars (computes locally). Returns: your yield/leverage/velocity/class/rank, a power-user assessment mapping your class tier to AI power-user language, comparison vs board averages (your percentile), and one actionable

• describe_power_user

  Returns an explanatory description of what makes an AI power user, anchored in SigRank's metrics and operator classes. Explains the yield metric, leverage, velocity, and how the 8 experience tiers (ARCH+ / ARCH / POWER / BASE / SEEKER / REFINER / BEARER / IGNITER, each with 3 sub-stages I/II/III, plus UNCLASSED for no-data) map to power-user behavior patterns. Use this when users ask 'what is an A

• diagnose_cascade

  Analyzes your token cascade and diagnoses where you're leaking efficiency. Takes your 4 pillars (input/output/cacheCreate/cacheRead) and produces a ranked list of efficiency leaks with severity (critical/warning/info), findings, and recommendations. Checks: cache leverage (are you rereading what you wrote?), velocity (are you generating enough output per input?), SNR (is your signal drowning in no

• discover_peers

  Discovers mentors, peers, and complementary operators for YOUR operator on the SigRank leaderboard. Uses your enrolled device identity — no codename needed. Finds operators you should learn from: (1) Mentors — 1-2 class tiers above you with similar cascade shapes, including the specific pillar delta that explains the yield gap (e.g. '12× your cache reads'). (2) Peers — same class tier, ranked by y

• enroll

  Bind THIS device to your SigRank operator so your signed token runs cascade to the live board. Paste the key from signalaf.com → Settings → "New key" (or "Generate connect code"). On first run it generates + stores a local ed25519 keypair (~/.sigrank-mcp/identity.json); only the PUBLIC key is ever sent. By enrolling you agree to the SignalAF Terms of Service (signalaf.com/terms) and Privacy Policy

• get_best_operator

  Returns the top N operators on the SigRank leaderboard with behavioral framing in power-user language. Wraps get_leaderboard and adds plain-language interpretation of each top operator's cascade: what their yield, leverage, and velocity mean in terms of AI power-user behavior (cache reuse, input economy, output productivity). Use this when users ask 'who is the best AI user?' or 'who tops the SigR

• get_leaderboard

  Fetches the live public SigRank leaderboard from signalaf.com. Reads all ranked operators sorted by yield (Υ = Cache Reads × Output / Input²) and returns an array of operator summaries. Each entry contains: codename (public display name), yield (Υ, the headline efficiency metric), leverage ratio (Cr/I = cache reads divided by input), velocity (O/I = output divided by input), class tier (one of 24

• get_operator

  Fetches one operator's live profile from the SigRank board by their codename. Reads the operator's current submission data from signalaf.com and returns their detailed metrics: yield (Υ), leverage ratio (Cr/I), velocity (O/I), class tier (one of 24 experience stages: 8 tiers × 3 sub-stages, e.g. ARCH+ I, REFINER II, IGNITER III), rank position (integer, 1-based), and per-window breakdowns for each

• get_sigrank_standard_record

  Build Upsilon's portable sigrank/0.1-draft compatibility record from available token telemetry. Input and output are required; unavailable cache telemetry remains null. Computes the canonical cascade locally through @sigrank/cascade and returns Yield, Leverage, Velocity, SNR, and 10xDEV. Upsilon is the measurement product; SigRank is the public leaderboard. No data is submitted or persisted.

• optimize_efficiency

  Returns actionable suggestions for improving your token cascade efficiency, tied to your current metrics. Accepts either a codename (fetches from board) or raw token pillars (computes locally). Returns: your current metrics, ranked efficiency suggestions tied to cascade shape (increase cache reuse, reduce input, increase output), and references to power-user practices. Use this when users ask 'how

• rank_paste

  Computes the SigRank yield cascade from a paste of token counts. Parses the input, runs the full cascade math locally (no network calls), and returns: yield (Υ, the headline efficiency metric, Υ = Cache Reads × Output / Input²), snr (signal-to-noise ratio), leverage (Cr/I = cache reads divided by input), velocity (O/I = output divided by input), dev10x (10xDEV score), class (operator experience st

• rank_windows

  Rank all four time windows (7d/30d/90d/all-time) in one call from a dashboard paste — paste the full table from ccusage, tokscale, or the Claude Max usage dashboard and get the cascade (Υ, SNR, Leverage, Velocity, 10xDEV, class, card) for each window. Each window is parsed and scored independently. Named keys required (input/output/cacheCreate/cacheRead); positional order is NOT safe here (dashboa

• self_improvewrite action

  Runs the full self-improvement cycle in one call: (1) gets your current token pillars — either from the provided text or by running tokenpull on your local logs, (2) diagnoses where you're leaking efficiency (diagnose_cascade), (3) generates ranked improvement suggestions (suggest_improvements), (4) simulates the top suggestion (simulate_change), and (5) returns the complete cycle: diagnosis + sug

• simulate_change

  The first PRESCRIPTIVE SigRank tool — 'what if I changed my token mix?' Takes your current 4 pillars (input/output/cacheCreate/cacheRead) and one or more proposed changes, runs the canonical cascade on BOTH the current and simulated values, and returns the exact Υ Yield delta, class change, and per-metric diffs. This is the 'show me the payoff before I do the work' primitive: no network, no submis

• submit_pastewrite action

  Ranks a paste of token counts locally and shows the cascade result (yield, leverage, velocity, class, card). This is a PREVIEW-ONLY tool — it does not publish to the board. The board's /api/v1/ingest-paste endpoint now requires an authenticated Supabase session, which MCP tools do not carry. To publish to the leaderboard, use submit_verified (which signs and posts to /api/v1/snapshots via the enro

• submit_verifiedwrite action

  Publish your LOCAL token runs to the SigRank board as a VERIFIED operator — the enrolled, signed path. Reads your pillars (tokenpull), builds the canonical Schema 1.0 snapshot per window, ed25519-signs it with your device key, and POSTs to /api/v1/snapshots. Requires `npx sigrank-mcp enroll` first (a bound device). Only signed submissions from a trusted device rank on the board. Token-only; the pr

• suggest_improvements

  Generates ranked, simulated improvement suggestions for your token cascade. Takes your 4 pillars, tests multiple improvement strategies (increase cache reads, reduce fresh input, increase output, optimize cache creation), simulates each with the canonical cascade engine, and returns them ranked by Υ yield impact. Each suggestion includes: the action, which pillar to change, how much to change it,

• tokenpull

  Pull your LOCAL token usage from the platform's session logs and rank it across the four windows (7d/30d/90d/all-time) with the cascade — zero paste. Token-only: reads usage counts not message content. The numbers stay on your machine unless you submit them. Some platforms may have partial data (estimated=true when cacheCreate isn't available) or a dataGap note when the log format doesn't expose r

• tokenpull_compare

  Pull token usage from ALL four local sources in parallel — tokenpull (JSONL canon), ccusage CLI, token-dashboard SQLite, and tokscale report — and return them side-by-side with delta % vs tokenpull as the baseline. Also computes the cascade (Υ, SNR, Leverage, class) for each source so you can see how each verifier scores. Useful for validating your numbers before submitting, or understanding discr

• tokenpull_submitwrite action

  Pull your LOCAL token usage from session logs and compute the cascade per window — the zero-paste preview flow. Reads the four canonical pillars (input, output, cacheCreate, cacheRead) per window from your local logs and computes yield, leverage, velocity, class, and card. This is a PREVIEW-ONLY tool — it does not publish to the board. The board's /api/v1/ingest-paste endpoint now requires an auth

• tokscale_breakdown

  Show a per-model breakdown of your token usage across all platforms detected by tokscale. Models under the threshold (default 1%) are lumped into 'other' to keep the display clean. Useful for seeing which models you actually use per platform (e.g. claude-opus-4-8 76%, claude-sonnet-4-6 11%, other 0.3%). Returns { platform: [{ model, input, output, cacheRead, cacheCreate, pct }] }.

• tokscale_competitive_intel

  Competitive intelligence for any AI tool company. Pass a target tool (by tokscale client slug like 'claude', 'codex', 'devin-cli' or canonical platform name like 'devin', 'other') and get: the target's rank by tokens among all detected tools, its full profile (tokens, cost, model mix, cache_read_pct, cost_per_million_tokens, market share), and a head-to-head comparison against every competitor (ea

• tokscale_cost_analysis

  Cost analysis per developer per model from your local tokscale data. Returns a per-client × per-model cost breakdown with cost_per_million_tokens, cost_per_message, and share_cost. Includes a per-client cost rollup and totals: total_cost, total_tokens, avg_cost_per_million_tokens, most_expensive_model, cheapest_per_token. Use this to see exactly where your AI spend goes — which tools and models co

• tokscale_developer_profile

  Per-developer usage profile across all 20+ AI tools detected by tokscale on this machine. For each tool: model mix (per-model tokens/cost/messages/performance), token pillars (input/output/cache_read/cache_write/reasoning), cache_read_pct, session count, scan path (redacted to ~), workspace breakdown, and headless support flag. Returns a summary with tool_count, total_cost, dominant_tool. All file

• tokscale_device_profile

  Device fingerprinting: profiles this machine's AI tool footprint — which AI tools are installed, where their session logs live (paths redacted to ~), how many sessions and messages each has, when the machine was active (daily activity + day-of-week distribution), session concurrency, and longest continuous session. Combines tokscale clients + graph data. All filesystem paths are redacted so no loc

• tokscale_market_share

  Complete AI tool market share analysis from your local tokscale data. Aggregates per-model usage by client (AI tool) and computes each tool's share of total tokens, cost, and messages. Returns each tool ranked by token share, with share_tokens / share_cost / share_messages percentages and a totals rollup. All data is read locally from tokscale's scan of your session logs — no network calls, no PII

• tokscale_mcp_usage

  MCP server usage patterns from your local tokscale data. Reports which MCP servers tokscale detected on this machine, the detection window, and active days in that window. tokscale currently exposes detected MCP servers as a set (not per-session attribution), so the report notes the detection window. Use this to see which MCP servers are active on your machine. If no servers are detected, the resp

• tokscale_model_trends

  Model adoption trends over time from your local tokscale data. Combines monthly aggregates with per-day contribution data to build a model-level adoption timeline: each model's first_seen / last_seen / active_days / tokens / clients, plus a month-by-month adoption curve showing how many new models appeared each month. Returns months[], models[], and adoption_curve[]. Use this to track which AI mod

• watch_tokenpull

  One poll per call: pulls your local token logs and returns the current cascade for the watched window — the tool never blocks or loops. Re-call at your desired cadence to watch for changes (interval_s is advisory only and echoed back as poll_interval_s). With submit:true (and an enrolled device) each call may also sign + publish the watched window to the board, rate-limited to once per 5 min per p

• Code scan72 source files scanned25/25
• –Live reliabilityno gateway calls yet and no remote to proben/a
• –Tool poisoningtools not inspected (local package is not executed); not countedn/a
• Auth qualitylocal package, no credentials required12/15
• Maintenancelast push 5 days ago15/15
• Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

Upsilon — AI Operator Measurement Engine: common questions

Is Upsilon — AI Operator Measurement Engine MCP server safe?

Yes, by our scan: it is graded A (92/100). Read the Upsilon — AI Operator Measurement Engine safety report

How do I install Upsilon — AI Operator Measurement Engine?

It runs on your machine. Copy the Claude Code, Claude Desktop or Cursor config from the install section.

Does Upsilon — AI Operator Measurement Engine need an API key?

Not as far as the registry entry and our scan can tell: no credentials are declared or required.

Is Upsilon — AI Operator Measurement Engine maintained?

The last commit was 5 days ago (2026-09-16). The latest release is v1.0.12.