Postbuild MCP

Official

by xdlabs-io

Overview Schema Source Related Servers Discussions Admin

JavaScript

Hybrid

Preview 7 Targeted HTML Product & Comparison Pages

postbuild_pseo

Read-onlyIdempotent

Generate a read-only preview of seven targeted SEO HTML pages tailored to a URL, classifying its site vertical and filtering routes by intent without writing files.

Instructions

Generate a read-only preview of 7 targeted HTML product and comparison pages (features, comparison, workflow guide, developer guide, checklist, FAQ, AI search reference) tailored to url. Performs a live HTTP GET on url to classify the site vertical (saas_ai, ecommerce, agency_b2b, or local_service), filters the 7 generated routes by intent when supplied, and compacts unchanged fields across repeated session calls unless bypass_cache: true is set (returns 3 preview routes without authentication, or all 7 with a Launch Pass license pb_live_...; never writes to disk). Use this tool to inspect generated page slugs, target keywords, and HTML copy in memory; do not use it to write HTML files into a repository (postbuild_fix) or to run the 8-point site readiness audit (postbuild_scan).

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "postbuild_pseo"
  }
}

Input Schema

Name	Required	Description	Default
`url`	No	Public HTTP/HTTPS URL of the product to tailor the 7 page drafts for (default: 'https://www.postbuild.dev').	https://www.postbuild.dev
`intent`	No	Case-insensitive substring filter on route search intent (e.g. 'Comparison', 'Alternative', 'Pricing', 'Guide', 'High Intent').
`bypass_cache`	No	When true, bypasses stateful session delta compaction and returns full HTML and metadata for every matched route (default: false).

Output Schema

Name	Required	Description	Default
`_mcp`	No	Stateful session cache metadata (`watermark`, `mode`, `total`).
`records`	Yes	Generated HTML product and comparison page route definitions.

Schema Changelog

Changes observed during successful MCP inspections.

Changed7 schema fields changedv2.1.24Nov 12, 2026

addedInput schema / additionalProperties
```
Added value: +false
```
addedInput schema / properties / bypass_cache / default
```
Added value: +false
```

changedInput schema / properties / bypass_cache / description

Previous value: -"Bypass stateful delta cache"New value: +"When true, bypasses stateful session delta compaction and returns full HTML and metadata for every matched route (default: false)."

changedInput schema / properties / intent / description

Previous value: -"Optional intent filter (Comparison, Alternative, Pricing, Guide)"New value: +"Case-insensitive substring filter on route search intent (e.g. 'Comparison', 'Alternative', 'Pricing', 'Guide', 'High Intent')."

addedInput schema / properties / url / default
```
Added value: +"https://www.postbuild.dev"
```

changedInput schema / properties / url / description

Previous value: -"Target URL"New value: +"Public HTTP/HTTPS URL of the product to tailor the 7 page drafts for (default: 'https://www.postbuild.dev')."

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "_mcp": {
+      "description": "Stateful session cache metadata (`watermark`, `mode`, `total`).",
+      "properties": {
+        "mode": {
+          "description": "Payload mode ('full' or 'delta').",
+          "type": "string"
+        },
+        "total": {
+          "description": "Number of matched product page routes.",
+          "type": "number"
+        },
+        "watermark": {
+          "description": "Current route state watermark (e.g. 'v1').",
+          "type": "string"
+        }
+      },
+      "type": "object"
+    },
+    "records": {
+      "description": "Generated HTML product and comparison page route definitions.",
+      "items": {
+        "properties": {
+          "h1": {
+            "description": "Primary H1 headline tailored to the scanned product.",
+            "type": "string"
+          },
+          "html": {
+            "description": "Complete standalone HTML document draft.",
+            "type": "string"
+          },
+          "intent": {
+            "description": "Search intent classification (e.g. 'High Intent Comparison', 'Technical Guide').",
+            "type": "string"
+          },
+          "metaDescription": {
+            "description": "Meta description tag content.",
+            "type": "string"
+          },
+          "slug": {
+            "description": "URL path slug for the generated page (e.g. 'vs-alternatives', 'features').",
+            "type": "string"
+          },
+          "targetKeyword": {
+            "description": "Primary SEO/AI search target keyword.",
+            "type": "string"
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    }
+  },
+  "required": [
+    "records"
+  ],
+  "type": "object"
+}

First observedv2.1.23Nov 12, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Goes well beyond the annotations by disclosing a live HTTP GET against the supplied URL, a four-way vertical classification (saas_ai, ecommerce, agency_b2b, local_service), stateful delta compaction across session calls, and 'never writes to disk'. It also discloses an auth gate: 3 routes without authentication versus all 7 with a Launch Pass license (pb_live_...), which is a material behavioral fact an agent needs. Slight deduction because the license/limit mechanics are compressed into a single parenthetical rather than spelled out.

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

Conciseness3/5

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

Front-loads the core action, but the bulk is one very long run-on sentence with stacked parentheticals (route list, vertical enum list, cache aside, auth aside), which makes it harder to parse than it needs to be. Content mostly earns its place; the packaging does not.

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?

For a 3-parameter, read-only preview tool with a full output schema and rich annotations, the description covers cost-bearing facts: network fetch, auth-dependent result count, cache bypass, and no disk writes. Return-value detail is correctly omitted since an output schema exists. Minor gap around what 'compacted' output actually looks like across repeated calls.

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 baseline is 3; the description still adds meaning by explaining that url drives a live fetch and vertical classification, that intent filters the 7 generated routes rather than doing arbitrary search, and that bypass_cache governs the session-delta compaction behavior. These are consequences the schema strings only hint at.

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 (generate a read-only preview) and resource (7 named page routes: features, comparison, workflow guide, developer guide, checklist, FAQ, AI search reference) tailored to a URL. It explicitly names the siblings it is not (postbuild_fix for writing files, postbuild_scan for the readiness audit), so an agent can separate it from neighbors without opening schemas.

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?

Gives a positive use case ('inspect generated page slugs, target keywords, and HTML copy in memory') and explicit exclusions with the sibling that owns each excluded job ('do not use it to write HTML files into a repository (postbuild_fix)' and 'not to run the 8-point site readiness audit (postbuild_scan)'). The intent-filter condition is also stated inline.

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

Deploy Server