SigRank MCP server

rank_paste

Read-onlyIdempotent

Compute SigRank yield from pasted token counts. Paste input, output, and cache numbers to get efficiency metrics and operator stage without submitting to the board.

Instructions

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 stage — 24 stages = 8 tiers × 3 sub-stages I/II/III, e.g. ARCH+ I, REFINER II, IGNITER III, or UNCLASSED for empty input), mode (detected working mode), and a deterministic prose "card" summarizing the result in plain English. Accepts two input formats: (1) JSON object {"input":N,"output":N,"cacheCreate":N,"cacheRead":N} or (2) four whitespace-separated numbers in order: input output cacheCreate cacheRead. Returns an error if the input is malformed or has negative values. Use this for a quick one-off ranking without submitting to the board. Do NOT use this to submit your score — use submit_paste instead, which both ranks and publishes. Do NOT use this if you want to rank all four time windows at once — use rank_windows for that. After calling this, use submit_paste to publish the result if you want to appear on the leaderboard.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`text`	Yes	Token counts to rank. Two formats accepted: (1) JSON object {"input":N,"output":N,"cacheCreate":N,"cacheRead":N} where all values are non-negative integers, or (2) four whitespace-separated numbers in order: input output cacheCreate cacheRead. Get these from `ccusage` output, the Claude Max usage dashboard, tokscale, or any token reader. Example valid input: {"input":1000000,"output":500000,"cacheCreate":50000,"cacheRead":800000}

Output Schema

TableJSON Schema

Name	Required	Description
`snr`	No	Signal-to-noise ratio
`card`	No	Deterministic prose summary of the cascade result
`mode`	No	Detected working mode (BUILD/EDIT/DEBUG/MAINTAIN/IDLE) + confidence
`class`	Yes	Operator class tier (dev10x taxonomy)
`yield`	Yes	Υ Yield — the headline efficiency metric (Cache Reads × Output / Input²)
`dev10x`	No	10xDEV score (log10 of the cascade product)
`pillars`	No	The four raw token pillars the cascade was computed from
`leverage`	No	Cr/I — cache reads divided by input
`velocity`	No	O/I — output divided by input
`warnings`	No	Parse or data warnings if any

Schema Changelog

Changes observed during successful MCP inspections.

Changed9 schema fields changedv0.19.6Aug 11, 2026

changedOutput schema / properties / class / description

Previous value: -"Operator class tier"New value: +"Operator class tier (dev10x taxonomy)"

changedOutput schema / properties / class / enum

Previous value: -[
-  "Burner",
-  "Builder",
-  "10xer"
-]New value: +[
+  "ARCH+ I",
+  "ARCH+ II",
+  "ARCH+ III",
+  "ARCH I",
+  "ARCH II",
+  "ARCH III",
+  "POWER I",
+  "POWER II",
+  "POWER III",
+  "BASE I",
+  "BASE II",
+  "BASE III",
+  "SEEKER I",
+  "SEEKER II",
+  "SEEKER III",
+  "REFINER I",
+  "REFINER II",
+  "REFINER III",
+  "BEARER I",
+  "BEARER II",
+  "BEARER III",
+  "IGNITER I",
+  "IGNITER II",
+  "IGNITER III",
+  "UNCLASSED"
+]

addedOutput schema / properties / dev10x

Added value: +{
+  "description": "10xDEV score (log10 of the cascade product)",
+  "type": "number"
+}

addedOutput schema / properties / mode

Added value: +{
+  "description": "Detected working mode (BUILD/EDIT/DEBUG/MAINTAIN/IDLE) + confidence",
+  "type": "object"
+}

addedOutput schema / properties / pillars

Added value: +{
+  "description": "The four raw token pillars the cascade was computed from",
+  "type": "object"
+}

removedOutput schema / properties / tenx_dev

Removed value: -{
-  "description": "10xDEV score",
-  "type": "number"
-}

addedOutput schema / properties / yield

Added value: +{
+  "description": "Υ Yield — the headline efficiency metric (Cache Reads × Output / Input²)",
+  "type": "number"
+}

removedOutput schema / properties / yield_

Removed value: -{
-  "description": "Υ Yield — the headline efficiency metric (Cache Reads × Output / Input²)",
-  "type": "number"
-}

changedOutput schema / required

Previous value: -[
-  "yield_",
-  "class"
-]New value: +[
+  "yield",
+  "class"
+]

Addedv0.19.4Jul 27, 2026
Removedv0.19.3Jul 26, 2026
Addedv0.19.2Jul 23, 2026
RemovedJul 22, 2026

Changed1 schema field changedv0.16.0Jul 7, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "card": {
+      "description": "Deterministic prose summary of the cascade result",
+      "type": "string"
+    },
+    "class": {
+      "description": "Operator class tier",
+      "enum": [
+        "Burner",
+        "Builder",
+        "10xer"
+      ],
+      "type": "string"
+    },
+    "leverage": {
+      "description": "Cr/I — cache reads divided by input",
+      "type": "number"
+    },
+    "snr": {
+      "description": "Signal-to-noise ratio",
+      "type": "number"
+    },
+    "tenx_dev": {
+      "description": "10xDEV score",
+      "type": "number"
+    },
+    "velocity": {
+      "description": "O/I — output divided by input",
+      "type": "number"
+    },
+    "warnings": {
+      "description": "Parse or data warnings if any",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "yield_": {
+      "description": "Υ Yield — the headline efficiency metric (Cache Reads × Output / Input²)",
+      "type": "number"
+    }
+  },
+  "required": [
+    "yield_",
+    "class"
+  ],
+  "type": "object"
+}

Changed2 schema fields changedv0.6.10Jul 4, 2026

addedInput schema / description

Added value: +"Requires the token counts as a string. No other parameters are accepted."

changedInput schema / properties / text / description

Previous value: -"ccusage JSON or \"input output cacheCreate cacheRead\""New value: +"Token counts to rank. Two formats accepted: (1) JSON object {\"input\":N,\"output\":N,\"cacheCreate\":N,\"cacheRead\":N} where all values are non-negative integers, or (2) four whitespace-separated numbers in order: input output cacheCreate cacheRead. Get these from `ccusage` output, the Claude Max usage dashboard, tokscale, or any token reader. Example valid input: {\"input\":1000000,\"output\":500000,\"cacheCreate\":50000,\"cacheRead\":800000}"

First observedv0.6.9Jun 24, 2026

TDQS

A4.9/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, destructiveHint=false, and idempotentHint=true. The description adds crucial context beyond annotations: 'runs the full cascade math locally (no network calls)', 'deterministic prose' (idempotency), and error behavior ('Returns an error if the input is malformed or has negative values'). It also discloses the exact metric formulas and stage classification, making the tool's behavior fully transparent. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but densely packed without fluff. It is front-loaded with the core purpose, then systematically covers outputs, input formats, error conditions, and usage guidance. Every sentence adds information, though it could arguably be trimmed slightly; however, for a tool with this complexity and the need to distinguish from siblings, the length is justified. The structure is logical and scannable.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite the tool's complexity, the description is entirely self-contained. It covers purpose, usage boundaries, input syntax, output semantics, error handling, local computation, and integration with submit_paste. The output schema is present, yet the description still explains each return field (yield, snr, etc.) and even the classification stages. With one parameter and no nested objects, this is more than complete—it is exceptionally thorough.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, but the description adds substantial meaning beyond the schema. It explains both accepted input formats in detail, specifies the order of numbers, clarifies that values must be non-negative integers, and provides a concrete example: '{"input":1000000,"output":500000,"cacheCreate":50000,"cacheRead":800000}'. It also links the parameters to the output metrics (e.g., yield formula), giving the agent a deeper understanding than the schema alone.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb+resource: 'Computes the SigRank yield cascade from a paste of token counts.' It clearly distinguishes from siblings by explicitly naming submit_paste and rank_windows as alternatives, and describes the precise outputs (yield, snr, leverage, velocity, dev10x, class, mode, prose card). This leaves no ambiguity about what the tool does.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly states when to use ('Use this for a quick one-off ranking without submitting to the board') and when not to use it, naming two alternatives: 'Do NOT use this to submit your score — use submit_paste instead' and 'Do NOT use this if you want to rank all four time windows at once — use rank_windows for that.' It also advises calling submit_paste afterward to publish. This is exemplary usage guidance with concrete exclusions and alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.