Skip to main content
Glama
Sign In
awwwards-mcp

awwwards-mcp

by INSANE0777
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

verify_flow

Compare up to six scroll, click, and wait steps between a build and reference page, then mark a step as matching only when both sides complete and path, scroll, hashes, and element counts agree.

Instructions

Step-aligned comparison of interaction flows: runs the same 1–6 scroll/click/wait steps on a build and a reference page (two fresh headless launches, desktop or mobile), then compares path, scroll delta, skeleton hash, text hash and element count after each step. A step is same only when both sides are complete and untruncated; truncated or failed states are unknown. No screenshots: hashes are evidence, not visual truth. A click can still trigger client-side mutations. Runs on URLs you are authorized to inspect. Use verify_build for a scored structure/motion comparison; build_project converts a local file into a project and never verifies. Needs the optional Playwright dependency.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "buildUrl": "<buildUrl>",
      "referenceUrl": "<referenceUrl>",
      "steps": "<steps>"
    },
    "name": "verify_flow"
  }
}

Input Schema

NameRequiredDescriptionDefault
stepsYes1-6 actions run on both pages in order; each scroll/click is followed by a 150 ms settle
buildUrlYesURL of the build to exercise (http(s), local dev server or deployed)
viewportNodesktop = 1440x900; mobile = 390x844 iPhone-class; both run in fresh headless launches
referenceUrlYesURL of the reference page to compare against
waitStrategyNo'load' (default) waits for load plus a 3 s settle; 'networkidle' waits for network quiet

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changedv1.15.1
    • addedInput schema / properties / buildUrl / description
      Added value: +"URL of the build to exercise (http(s), local dev server or deployed)"
    • addedInput schema / properties / referenceUrl / description
      Added value: +"URL of the reference page to compare against"
    • addedInput schema / properties / steps / description
      Added value: +"1-6 actions run on both pages in order; each scroll/click is followed by a 150 ms settle"
    • changedInput schema / properties / steps / items / oneOf
      Previous value: -[
-  {
-    "properties": {
-      "action": {
-        "const": "scroll",
-        "type": "string"
-      },
-      "y": {
-        "maximum": 100000,
-        "minimum": 0,
-        "type": "integer"
-      }
-    },
-    "required": [
-      "action",
-      "y"
-    ],
-    "type": "object"
-  },
-  {
-    "properties": {
-      "action": {
-        "const": "click",
-        "type": "string"
-      },
-      "selector": {
-        "maxLength": 300,
-        "minLength": 1,
-        "type": "string"
-      }
-    },
-    "required": [
-      "action",
-      "selector"
-    ],
-    "type": "object"
-  },
-  {
-    "properties": {
-      "action": {
-        "const": "wait",
-        "type": "string"
-      },
-      "ms": {
-        "maximum": 10000,
-        "minimum": 0,
-        "type": "integer"
-      }
-    },
-    "required": [
-      "action",
-      "ms"
-    ],
-    "type": "object"
-  }
-]New value: +[
+  {
+    "properties": {
+      "action": {
+        "const": "scroll",
+        "description": "Scroll to an absolute window Y position",
+        "type": "string"
+      },
+      "y": {
+        "description": "Absolute window scroll position in pixels (0-100000), not a relative delta",
+        "maximum": 100000,
+        "minimum": 0,
+        "type": "integer"
+      }
+    },
+    "required": [
+      "action",
+      "y"
+    ],
+    "type": "object"
+  },
+  {
+    "properties": {
+      "action": {
+        "const": "click",
+        "description": "Click the element matching a CSS selector",
+        "type": "string"
+      },
+      "selector": {
+        "description": "CSS selector to click on both pages",
+        "maxLength": 300,
+        "minLength": 1,
+        "type": "string"
+      }
+    },
+    "required": [
+      "action",
+      "selector"
+    ],
+    "type": "object"
+  },
+  {
+    "properties": {
+      "action": {
+        "const": "wait",
+        "description": "Wait for a fixed number of milliseconds",
+        "type": "string"
+      },
+      "ms": {
+        "description": "Wait time in milliseconds (0-10000)",
+        "maximum": 10000,
+        "minimum": 0,
+        "type": "integer"
+      }
+    },
+    "required": [
+      "action",
+      "ms"
+    ],
+    "type": "object"
+  }
+]
    • addedInput schema / properties / viewport / description
      Added value: +"desktop = 1440x900; mobile = 390x844 iPhone-class; both run in fresh headless launches"
    • addedInput schema / properties / waitStrategy / description
      Added value: +"'load' (default) waits for load plus a 3 s settle; 'networkidle' waits for network quiet"
  2. Addedv1.14.0

TDQS

A4.5/5.0
Behavior4/5

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

Goes well beyond annotations: two fresh headless launches, per-step comparison signals, truncated/failed states treated as 'unknown', 'No screenshots: hashes are evidence, not visual truth', and 'A click can still trigger client-side mutations' — which usefully qualifies the destructiveHint=false under open-world execution. Uniform 150ms settle and waitStrategy behavior are in the schema, not lost here.

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?

Dense but front-loaded: purpose first, then execution semantics, then caveats, then sibling routing. Nearly every clause carries information, though the sentence is long and the Playwright note at the end is easy to skim past.

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

Completeness4/5

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

Given no output schema, the description explains what is compared and how each step is classified (same vs unknown), which is what an agent needs to interpret results. It does not specify the concrete result shape (per-step verdicts, failure reporting), leaving some ambiguity about return structure.

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% and each step variant is documented, so the baseline is 3. The description adds non-obvious semantics: the same step sequence runs on BOTH pages, 1–6 limit, scroll/click/wait as the allowed action set, and desktop-or-mobile viewport in fresh launches — meaning beyond what the field descriptions state.

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?

Opens with a specific verb+resource: 'Step-aligned comparison of interaction flows', then details what is executed on which two pages. It explicitly distinguishes itself from both verify_build (scored structure/motion comparison) and build_project (never verifies), so an agent can pick correctly among siblings.

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?

Directly routes the agent: 'Use verify_build for a scored structure/motion comparison' and 'build_project ... never verifies', plus the authorization precondition 'Runs on URLs you are authorized to inspect'. Also names a dependency requirement (optional Playwright).

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

Deploy Server

Other Tools