SigRank MCP server

rank_windows

Read-onlyIdempotent

Score 7d, 30d, 90d, and all-time token windows in one call from a pasted ccusage, tokscale, or Claude Max dashboard, returning cascade metrics per window.

Instructions

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 (dashboards list cache_read before cache_create — see WINDOWED_PROFILES gotcha). Omit windows you don't have — partial input is allowed (1–4 windows). Does NOT submit to the board; use tokenpull_submit for a local zero-paste preview, or submit_verified to publish via the enrolled-device path.

Input Schema

TableJSON Schema

Name	Required	Description
`7d`	No	ccusage/tokscale paste or JSON for the 7-day window (optional)
`30d`	No	ccusage/tokscale paste or JSON for the 30-day window (optional)
`90d`	No	ccusage/tokscale paste or JSON for the 90-day window (optional)
`all`	No	ccusage/tokscale paste or JSON for the all-time window (optional)
`source_tool`	No	which token reader produced the paste (for cross-tool variance tracking)

Output Schema

TableJSON Schema

Name	Required	Description	Default
`windows`	No	Cascade results per window

Schema Changelog

Changes observed during successful MCP inspections.

Changed8 schema fields changedv0.19.6Aug 11, 2026

changedOutput schema / properties / windows / items / properties / class / description

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

changedOutput schema / properties / windows / items / 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 / windows / items / properties / dev10x

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

addedOutput schema / properties / windows / items / properties / mode

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

addedOutput schema / properties / windows / items / properties / pillars

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

removedOutput schema / properties / windows / items / properties / tenx_dev

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

addedOutput schema / properties / windows / items / properties / yield

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

removedOutput schema / properties / windows / items / properties / yield_

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

Addedv0.19.2Jul 23, 2026
RemovedJul 22, 2026

Changed1 schema field changedv0.16.0Jul 7, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "windows": {
+      "description": "Cascade results per window",
+      "items": {
+        "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"
+          },
+          "window": {
+            "enum": [
+              "7d",
+              "30d",
+              "90d",
+              "all"
+            ],
+            "type": "string"
+          },
+          "yield_": {
+            "description": "Υ Yield — the headline efficiency metric (Cache Reads × Output / Input²)",
+            "type": "number"
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    }
+  },
+  "type": "object"
+}

Changed1 schema field changedv0.6.10Jul 4, 2026

addedInput schema / anyOf

Added value: +[
+  {
+    "required": [
+      "7d"
+    ]
+  },
+  {
+    "required": [
+      "30d"
+    ]
+  },
+  {
+    "required": [
+      "90d"
+    ]
+  },
+  {
+    "required": [
+      "all"
+    ]
+  }
+]

First observedv0.6.9Jun 24, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Annotations already cover the safety profile (readOnlyHint=true, idempotentHint=true, openWorldHint=false), and the description adds real behavioral context beyond them: each window is parsed and scored independently, positional order is unsafe because dashboards list cache_read before cache_create, and windows may be omitted for partial input. It stops short of describing how malformed pastes or conflicting windows are handled.

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 core purpose and output set are front-loaded in the first sentence, with routing, input constraints, and the non-submission caveat following in focused clauses. It is dense but nearly every clause carries distinct routing or correctness information; slightly long but not padded.

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?

An output schema exists, so return values legitimately need not be explained. The description covers source formats, per-window independence, key requirements, partial-input tolerance, and the submission boundary, which is everything an agent needs to call this read-only tool correctly.

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

Parameters4/5

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

Schema coverage is 100%, so the four window strings and source_tool enum are documented. The description still adds value beyond the schema by specifying the required named keys (input/output/cacheCreate/cacheRead), warning that positional order is not safe, and pointing to the WINDOWED_PROFILES gotcha.

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?

States a specific verb (rank) and resource (all four time windows 7d/30d/90d/all-time) and names the sources (ccusage, tokscale, Claude Max dashboard) plus the outputs produced (cascade: Υ, SNR, Leverage, Velocity, 10xDEV, class, card). An agent can distinguish it from siblings like rank_paste and tokscale_breakdown without opening any schema.

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?

Explicitly states what it does NOT do (does not submit to the board) and routes to the correct alternatives with conditions: tokenpull_submit for a local zero-paste preview, submit_verified to publish via the enrolled-device path. It also clarifies partial input (1-4 windows) is allowed and named keys are required, leaving nothing to inference.

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