QualityKit
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": true
} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| qualitykit.auditA | Primary audit: route inventory, technical SEO, metadata, content, schema, links. Separates defects from opportunities. Optional rendered HTML via includeRendered+siteUrl. |
| qualitykit.ai_auditB | AI discoverability audit: crawlability, extractability, entity clarity, citation readiness, structured understanding, topical coverage. Heuristic scores with evidence — no citation guarantees. |
| qualitykit.planC | Content and architecture opportunities: briefs, blog scaffold plan, schema, internal links. Advise-only. |
| qualitykit.growB | Brand-aligned growth: score Search Console queries against the Site Profile, return top opportunities and deprioritised demand, with safe vs approval fixes. Uses Cloud GSC + profile when API key is set. |
| qualitykit.get_site_profileB | Return the approved Site Profile (brand, ICP, products, voice, pages, keyword relevance), confidence, and freshness. Ephemeral repo draft when Cloud is not connected. |
| qualitykit.refresh_site_profileC | Prefer Cloud model refresh when Pro + MODEL_* are configured (stale fields only; material stays pending). Offline: returns a host-agent brief from repo evidence. |
| qualitykit.update_site_profileA | Apply a partial Site Profile patch. Brand identity, ICP, and products stay pendingApproval until approveMaterial or approvePending. Persists to Cloud when API key is set. |
| qualitykit.fixB | Technical findings → unified diffs/FileSpecs. page-* / gsc-query-* opportunityIds → buildContracts for the host agent (no invented page files). Never writes the repo. Use safeAutoOnly for low-risk technical fixes only. |
| qualitykit.verifyB | Re-audit after changes or against proposedFiles. Checks finding IDs and optional opportunityIds (route presence). Returns readyToShip; with Pro credentials, records mark_applied / shipped. |
| monitor.statusA | Fetch latest QualityKit Cloud monitoring run when QUALITYKIT_API_KEY is set. Otherwise returns self_hosted / not_run coverage (free local mode). |
| visibility.reportA | Search Console growth via QualityKit Cloud when QUALITYKIT_API_KEY + QUALITYKIT_API_BASE are set. Pass period 7d|28d|90d|365d for % deltas, trend, series summary, ranked opportunities, and changeOutcomes. Otherwise not_connected stub. |
| visibility.mark_appliedA | After grow → fix → verify (and deploy), snapshot Search Console metrics for grow topChanges ids so later visibility.report shows per-change impression deltas. Requires QUALITYKIT_API_KEY + QUALITYKIT_API_BASE. GSC data often lags 1–3 days. |
| opportunities.listC | Pro: list persisted grow/GSC opportunities (found|approved|shipped|snoozed). Requires QUALITYKIT_API_KEY + QUALITYKIT_API_BASE. |
| opportunities.updateB | Pro: set opportunity status to found|approved|shipped|snoozed (snooze defaults to 7 days). Requires QUALITYKIT_API_KEY + QUALITYKIT_API_BASE. |
| opportunities.syncB | Pro: upsert grow topChanges and/or live GSC ranked opportunities into the Cloud backlog. Pass projectRoot to run local grow, or items. Returns counts by status (found N). Requires QUALITYKIT_API_KEY + QUALITYKIT_API_BASE. |
| codebase.analyzeB | Secondary: detect framework, router, routes, metadata, robots, sitemap, blog, business hints. Prefer qualitykit.audit for full audits. |
| seo.auditC | Secondary alias of the audit engine. Prefer qualitykit.audit. |
| seo.plan_changesC | Secondary: technical SEO file specs. Prefer qualitykit.fix / qualitykit.plan. |
| blog.scaffoldC | Specialized: App Router + MDX blog file specs when justified. Prefer qualitykit.plan first. |
| schema.planC | Specialized: Organization/WebSite/BlogPosting JSON-LD plans. No sitewide FAQ schema. |
| links.planD | Specialized: contextual internal-link suggestions. |
| content.briefC | Specialized: at most three content briefs. Prefer qualitykit.plan. |
| seo.validateC | Specialized validation of project or proposed files. Prefer qualitykit.verify for finding-level verification. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| audit-site | Workflow: qualitykit.audit → grow → optional plan → fix diffs → apply approved → verify. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Technical SEO rules | Crawlability, metadata, sitemaps, and safe fix boundaries |
| AEO / AI visibility rules | Answer readiness, entities, schema, and AI crawler policy |
| Content quality rules | Briefs, blog architecture, linking, and integrity standards |
TDQS
Scored across 23 tools
Several tools are explicitly redundant: seo.audit is self-described as an 'alias of the audit engine' with 'Prefer qualitykit.audit', and seo.plan_changes, codebase.analyze, blog.scaffold, links.plan, content.brief, and schema.plan all overlap with qualitykit.plan/fix. The 'prefer X' notes help an attentive agent, but six planning-adjacent tools and three audit-adjacent tools create real misselection risk.
A namespace.action pattern (qualitykit.*, seo.*, opportunities.*, visibility.*) is mostly followed, which keeps names readable and grouped. However verb forms vary widely within that pattern — bare verbs/nouns (plan, grow, fix, verify, status) mixed with verb_noun (get_site_profile, mark_applied, plan_changes) — so the surface is not fully predictable.
23 tools is heavy for this domain, and the count is inflated by deprecated/secondary aliases (seo.audit, seo.plan_changes, codebase.analyze) plus three narrow specialized planners that the primary plan tool already covers. Trimming the aliases would leave a tighter, more defensible set.
The audit → plan → fix → verify → monitor → visibility loop is present, along with Site Profile get/refresh/update and an opportunities backlog. But update_site_profile references approveMaterial and approvePending tools that are not in this surface, leaving a dead end, and there is no project/workspace management or explicit deploy step.