DiffiCat

Diff deploy

diff_deploy

Use when a staging or preview deploy should match production, or a migrated site its old one: it compares the pages of both origins and answers only the pages that are missing, changed or look different. Free up to 40 pages, once per client address, no key needed.

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": {
      "previewUrl": "<previewUrl>",
      "productionUrl": "<productionUrl>"
    },
    "name": "diff_deploy"
  }
}

Input Schema

Name	Required	Description
`paths`	No	Pages to compare, each starting with /; skips discovery.
`maxPages`	No	Without paths: pages discovery compares, default 10.
`checkMode`	No	full (existence, content and visual, the default), text-only (no screenshots) or existence-only.
`threshold`	No	Visual diff tolerance as a fraction from 0 (exact) to 1: 0.05 means 5%. The web app takes a percentage; the API does not.
`previewUrl`	Yes	The preview or staging site (full URL), compared as Site B.
`maxPriceUsd`	No	Spend cap in USD: a job priced above it is refused before any challenge.
`productionUrl`	Yes	The production site (full URL), compared as Site A.
`viewportWidth`	No	Capture width in px.
`idempotencyKey`	No	Retry key: under a prepaid balance, the same value within 24 hours is not charged again and answers DUPLICATE_REQUEST with the first jobId.

Output Schema

Name	Required	Description	Default
`ok`	No
`code`	No
`error`	No
`jobId`	No
`sample`	No
`status`	No
`payment`	No
`jobToken`	No
`followUps`	No
`regressions`	No
`pagesCharged`	No
`pagesChecked`	No
`regressionCount`	No
`allowanceRemaining`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedNov 7, 2026

changedInput schema / properties / idempotencyKey / description

Previous value: -"Optional opaque string a retry repeats: under a prepaid balance the same value within 24 hours is not charged again and answers DUPLICATE_REQUEST with the jobId of the first call."New value: +"Retry key: under a prepaid balance, the same value within 24 hours is not charged again and answers DUPLICATE_REQUEST with the first jobId."

changedInput schema / properties / maxPriceUsd / description

Previous value: -"Optional spend cap in USD. A job priced above it is refused before any challenge, so an auto-paying client is never asked for more."New value: +"Spend cap in USD: a job priced above it is refused before any challenge."

Changed1 schema field changedNov 2, 2026

addedOutput schema / properties / followUps

Added value: +{
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

AddedOct 31, 2026

TDQS

A3.6/5.0

Behavior3/5

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

Adds real value beyond the thin annotations: a free-tier quota ('up to 40 pages, once per client address, no key needed') and a result-filtering rule (only missing/changed/different pages are answered). However, it never discloses that this enqueues an asynchronous job whose result must be fetched via wait_for_comparison or get_report, nor how maxPriceUsd and idempotencyKey behave in practice, which matters for a non-readOnly, open-world tool.

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?

Front-loaded with the usage trigger, and every clause carries information (use case, comparison semantics, output filtering, free-tier limits). The first sentence is long and colon-chained, which slightly hurts scanability, but there is no filler.

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

Completeness3/5

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

An output schema exists, so return shape needn't be explained, and the free-tier and filtering behavior are covered. What is missing for a 9-parameter job-creating tool is the asynchronous lifecycle: that a jobId is produced and must be polled, which an agent needs in order to call this correctly.

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

Parameters3/5

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

Schema coverage is 100%, so every parameter is already documented in the schema, and the description adds almost no parameter-level meaning. The '40 pages' free cap is in mild tension with the schema's maxPages maximum of 50 and the maxPriceUsd spend cap, and the description does not resolve that tension.

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

Purpose4/5

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

States a specific verb and resource: it 'compares the pages of both origins' and returns only missing/changed/different pages. The two-origin comparison distinguishes it implicitly from single-page siblings like check_page and capture_screenshot, but no sibling is named explicitly.

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

Usage Guidelines4/5

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

Opens with an explicit trigger: 'Use when a staging or preview deploy should match production, or a migrated site its old one.' That gives clear when-to-use context, but it names no exclusions or alternatives (e.g. when to use check_page or capture_screenshot instead).

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

All DiffiCat tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?