SigRank MCP server

watch_tokenpull

Idempotent

Pull local token logs to get the current cascade for a watched window. Re-call at your own cadence to monitor changes, with optional signed submission to the board.

Instructions

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 platform+window; default is preview-only (no submit).

Input Schema

TableJSON Schema

Name	Required	Description
`submit`	No	auto-submit the watched window to the board as a VERIFIED operator each poll (requires `enroll`; default false = preview only)
`window`	No	which window to watch (default: 7d — most sensitive to recent activity)
`platform`	No	platform to watch (default: claude)
`interval_s`	No	advisory poll cadence in seconds (default: 60, min: 10) — echoed back as poll_interval_s; does not make the call block or loop

Output Schema

TableJSON Schema

Name	Required	Description
`card`	No	Deterministic prose summary
`note`	No	Reminder that one snapshot is returned per call — re-call to detect changes.
`window`	No	The watched window (watch_tokenpull watches one window per call)
`cascade`	No
`pillars`	No	The four raw token pillars for the watched window
`messages`	No	Number of messages in the watched window
`platform`	No	Source platform name
`auth_submit`	No	Present only when submit:true. One of: {status:'received'\|'cooldown'\|'not_enrolled'\|'error', ...}. Null when submit is false (preview only).
`generatedAt`	No	ISO timestamp of the pull
`poll_interval_s`	No	Advisory poll cadence echoed back (does not make the call block)

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.19.7Aug 19, 2026

changedInput schema / properties / platform / enum

Previous value: -[
-  "amp",
-  "kimi",
-  "qwen",
-  "pi",
-  "openclaw",
-  "droid",
-  "codebuff",
-  "gemini",
-  "copilot",
-  "opencode",
-  "goose",
-  "kilo",
-  "hermes",
-  "devin",
-  "other",
-  "omp",
-  "proxy",
-  "claude",
-  "codex"
-]New value: +[
+  "amp",
+  "kimi",
+  "qwen",
+  "pi",
+  "openclaw",
+  "droid",
+  "codebuff",
+  "gemini",
+  "copilot",
+  "opencode",
+  "goose",
+  "kilo",
+  "hermes",
+  "devin",
+  "other",
+  "omp",
+  "proxy",
+  "claude",
+  "codex",
+  "grok"
+]

Changed10 schema fields changedv0.19.6Aug 11, 2026

changedInput schema / properties / platform / enum

Previous value: -[
-  "amp",
-  "kimi",
-  "qwen",
-  "pi",
-  "openclaw",
-  "droid",
-  "codebuff",
-  "gemini",
-  "copilot",
-  "opencode",
-  "goose",
-  "kilo",
-  "hermes",
-  "devin",
-  "other",
-  "claude",
-  "codex"
-]New value: +[
+  "amp",
+  "kimi",
+  "qwen",
+  "pi",
+  "openclaw",
+  "droid",
+  "codebuff",
+  "gemini",
+  "copilot",
+  "opencode",
+  "goose",
+  "kilo",
+  "hermes",
+  "devin",
+  "other",
+  "omp",
+  "proxy",
+  "claude",
+  "codex"
+]

addedOutput schema / properties / auth_submit

Added value: +{
+  "description": "Present only when submit:true. One of: {status:'received'|'cooldown'|'not_enrolled'|'error', ...}. Null when submit is false (preview only).",
+  "type": [
+    "object",
+    "null"
+  ]
+}

addedOutput schema / properties / card

Added value: +{
+  "description": "Deterministic prose summary",
+  "type": "string"
+}

addedOutput schema / properties / cascade

Added value: +{
+  "properties": {
+    "card": {
+      "description": "Deterministic prose summary of the cascade result",
+      "type": "string"
+    },
+    "class": {
+      "description": "Operator class tier (dev10x taxonomy)",
+      "enum": [
+        "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"
+      ],
+      "type": "string"
+    },
+    "dev10x": {
+      "description": "10xDEV score (log10 of the cascade product)",
+      "type": "number"
+    },
+    "leverage": {
+      "description": "Cr/I — cache reads divided by input",
+      "type": "number"
+    },
+    "mode": {
+      "description": "Detected working mode (BUILD/EDIT/DEBUG/MAINTAIN/IDLE) + confidence",
+      "type": "object"
+    },
+    "pillars": {
+      "description": "The four raw token pillars the cascade was computed from",
+      "type": "object"
+    },
+    "snr": {
+      "description": "Signal-to-noise ratio",
+      "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"
+}

addedOutput schema / properties / messages

Added value: +{
+  "description": "Number of messages in the watched window",
+  "type": "integer"
+}

addedOutput schema / properties / note

Added value: +{
+  "description": "Reminder that one snapshot is returned per call — re-call to detect changes.",
+  "type": "string"
+}

addedOutput schema / properties / pillars

Added value: +{
+  "description": "The four raw token pillars for the watched window",
+  "properties": {
+    "cacheCreate": {
+      "type": "integer"
+    },
+    "cacheRead": {
+      "type": "integer"
+    },
+    "input": {
+      "type": "integer"
+    },
+    "output": {
+      "type": "integer"
+    }
+  },
+  "type": "object"
+}

addedOutput schema / properties / poll_interval_s

Added value: +{
+  "description": "Advisory poll cadence echoed back (does not make the call block)",
+  "type": "number"
+}

addedOutput schema / properties / window

Added value: +{
+  "description": "The watched window (watch_tokenpull watches one window per call)",
+  "enum": [
+    "7d",
+    "30d",
+    "90d",
+    "all"
+  ],
+  "type": "string"
+}

removedOutput schema / properties / windows

Removed value: -{
-  "description": "Per-window token usage + cascade results",
-  "items": {
-    "properties": {
-      "cascade": {
-        "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"
-      },
-      "estimated": {
-        "description": "True if cacheCreate was estimated",
-        "type": "boolean"
-      },
-      "messages": {
-        "description": "Number of messages in window",
-        "type": "integer"
-      },
-      "pillars": {
-        "properties": {
-          "cacheCreate": {
-            "type": "integer"
-          },
-          "cacheRead": {
-            "type": "integer"
-          },
-          "input": {
-            "type": "integer"
-          },
-          "output": {
-            "type": "integer"
-          }
-        },
-        "type": "object"
-      },
-      "window": {
-        "enum": [
-          "7d",
-          "30d",
-          "90d",
-          "all"
-        ],
-        "type": "string"
-      }
-    },
-    "type": "object"
-  },
-  "type": "array"
-}

Addedv0.19.3Jul 26, 2026
Removedv0.19.2Jul 23, 2026

Changed1 schema field changedv0.18.1Jul 14, 2026

changedInput schema / properties / platform / enum

Previous value: -[
-  "amp",
-  "kimi",
-  "qwen",
-  "pi",
-  "openclaw",
-  "droid",
-  "codebuff",
-  "gemini",
-  "copilot",
-  "opencode",
-  "goose",
-  "kilo",
-  "hermes",
-  "claude",
-  "codex"
-]New value: +[
+  "amp",
+  "kimi",
+  "qwen",
+  "pi",
+  "openclaw",
+  "droid",
+  "codebuff",
+  "gemini",
+  "copilot",
+  "opencode",
+  "goose",
+  "kilo",
+  "hermes",
+  "devin",
+  "other",
+  "claude",
+  "codex"
+]

Changed1 schema field changedv0.16.0Jul 7, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "generatedAt": {
+      "description": "ISO timestamp of the pull",
+      "type": "string"
+    },
+    "platform": {
+      "description": "Source platform name",
+      "type": "string"
+    },
+    "windows": {
+      "description": "Per-window token usage + cascade results",
+      "items": {
+        "properties": {
+          "cascade": {
+            "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"
+          },
+          "estimated": {
+            "description": "True if cacheCreate was estimated",
+            "type": "boolean"
+          },
+          "messages": {
+            "description": "Number of messages in window",
+            "type": "integer"
+          },
+          "pillars": {
+            "properties": {
+              "cacheCreate": {
+                "type": "integer"
+              },
+              "cacheRead": {
+                "type": "integer"
+              },
+              "input": {
+                "type": "integer"
+              },
+              "output": {
+                "type": "integer"
+              }
+            },
+            "type": "object"
+          },
+          "window": {
+            "enum": [
+              "7d",
+              "30d",
+              "90d",
+              "all"
+            ],
+            "type": "string"
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    }
+  },
+  "type": "object"
+}

Changed3 schema fields changedv0.6.10Jul 4, 2026

removedInput schema / properties / codename

Removed value: -{
-  "description": "TODO(AUTH.WIRE): when set, will auto-submit on change once auth is live",
-  "type": "string"
-}

changedInput schema / properties / interval_s / description

Previous value: -"poll interval in seconds (default: 60, min: 10)"New value: +"advisory poll cadence in seconds (default: 60, min: 10) — echoed back as poll_interval_s; does not make the call block or loop"

addedInput schema / properties / submit

Added value: +{
+  "description": "auto-submit the watched window to the board as a VERIFIED operator each poll (requires `enroll`; default false = preview only)",
+  "type": "boolean"
+}

First observedv0.6.9Jun 24, 2026

TDQS

A5/5.0

Behavior5/5

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

Beyond the annotations (idempotentHint: true, openWorldHint: false), the description discloses important behaviors: calls never block or loop, interval_s is advisory, and the submit path is rate-limited to once per 5 minutes per platform+window and requires enrollment. This adds substantial context that is not present in the structured annotations.

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

Conciseness5/5

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

The description is two sentences, front-loaded with the key behavioral point ('One poll per call'), and every clause carries useful information. There is no redundancy or filler; it is concise yet comprehensive.

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?

For a tool with multiple optional parameters, an output schema, and an optional submit path, the description fully covers the operational model, rate limits, prerequisites, defaults, and the non-blocking nature. No significant gaps remain for an agent to select and invoke the tool correctly.

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?

The input schema already has 100% description coverage, but the tool description enriches it further: submit requires enroll and is rate-limited, interval_s is advisory and echoed back as poll_interval_s, and the default behavior is preview-only. This goes well beyond the schema descriptions, making the parameters' practical semantics clear.

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 clearly states what the tool does: 'One poll per call: pulls your local token logs and returns the current cascade for the watched window.' It uses a specific verb (pulls) and resource (local token logs), and distinguishes itself from sibling tools by emphasizing it never blocks or loops and by explaining preview-only vs submit modes.

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 gives explicit usage guidance: 'Re-call at your desired cadence to watch for changes' and notes that interval_s is advisory only and echoed back as poll_interval_s. It also explains when to use submit:true (with an enrolled device) and when to stick with preview-only (default), effectively covering when and when-not to use the tool.

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

watch_tokenpull

Instructions

Input Schema

Output Schema

Schema Changelog

TDQS

Other Tools