SizeRef Size Charts
Server Details
Audit, normalise and export size charts as clean tables and JSON-LD. No AI; keeps no charts sent.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 3 tools
The three tools map to distinct workflow stages: audit for read-only diagnostics, normalise for repairing or generating a chart, and export for producing output formats. The audit versus normalise boundary could momentarily confuse when a chart has gaps, but the descriptions make clear that audit only reports while normalise produces a chart or questions.
All tool names use snake_case, begin with a verb, and end with the size chart object: audit_size_chart, export_agent_ready_chart, normalise_size_chart. The longer export name still follows the same predictable verb_object pattern.
Three tools are well matched to a narrow workflow of checking, normalising, and exporting size charts. Each tool covers substantial functionality, so the surface does not feel thin despite the small count.
The surface covers the core check, fix, and export lifecycle, including handling gaps by returning questions instead of a chart. A minor gap is the lack of direct product-page or URL ingestion, but the documented pasted-chart inputs and tool limits keep the workflow coherent.
Available Tools
3 toolsaudit_size_chartAudit a size chartARead-onlyIdempotentInspect
Checks a size chart and reports what is wrong with it or still unanswered, without changing it. Takes a size chart, never a person's measurements. Limits: one call per request; up to 60 sizes, 40 columns or measurements a size, and 64 characters a size label or measurement name; each table cell is read up to 200 characters. Send a chart in SizeRef chart format v1, or a table as html, csv, or headers and rows. variant_sizes compares the chart's size labels with the product's; product_title decides whether hips are kept for long tops such as a kurta or a dress; product_text gives the fit when the table does not state it. results[] holds one result per table found; the top-level verdict is the worst table's, so read results[] for each table. It cannot see the product page, so a pasted table is at best needs_fix until normalise_size_chart gets the answers.
Inputs: chart, table, product_text, product_title, +1 more.
export_agent_ready_chartExport a size chartARead-onlyIdempotentInspect
Writes a valid SizeRef chart v1 as SizeRef JSON, schema.org JSON-LD, CSV and plain text, and lists anything left out and why. Takes a size chart, never a person's measurements. Limits: one call per request; up to 60 sizes, 40 columns or measurements a size, and 64 characters a size label or measurement name; each table cell is read up to 200 characters. jsonld is a whole block, ready to paste into the product page, with its JSON escaped so no value can end the block. jsonld_note says how the theme can link each variant size to the matching @id; that step is optional.
Inputs: chart_v1 (required), formats, product.
normalise_size_chartNormalise a size chartARead-onlyIdempotentInspect
Turns a size table, or a chart with gaps, into SizeRef chart format v1 from what the table states plus the answers you pass. Nothing is inferred from the numbers. Takes a size chart, never a person's measurements. Limits: one call per request; up to 60 sizes, 40 columns or measurements a size, and 64 characters a size label or measurement name; each table cell is read up to 200 characters. When something is left open it returns questions with the allowed answers instead of a chart. A page with several tables needs table_index. product_title decides whether hips are kept for long tops such as a kurta or a dress; product_text gives the fit when the table does not state it.
Inputs: chart, table, answers, table_index, +2 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Technical SEO audits from ChatGPT or the web: health score, prioritised fixes, CSV and PDF reports.
Clean messy tabular data and render publication-ready PNG charts from your AI assistant.
SEO audits and AI crawler checks. Honest findings only; no invented scores.
Audit any URL for ChatGPT, Claude & Perplexity GEO citation readiness, llms.txt & Schema.org.
Related MCP Servers
AlicenseAqualityBmaintenanceTechnical SEO and AI search readiness auditor that scans live URLs for AI crawler rules (OAI-SearchBot, ClaudeBot, PerplexityBot), llms.txt, sitemap.xml, OpenGraph, JSON-LD, and checkout reachability, and generates drop-in fix files.8MIT- AlicenseAqualityCmaintenanceCompany profiles, site audits and page-to-JSON for AI agents.6MIT
- AlicenseAqualityBmaintenanceFree, rules-based checks for e-commerce product pages: AI shopping readiness (structured data, reviews, return and shipping terms, GTINs, AI crawler access), Google Merchant Center compliance, store SEO audit and Shopify checkout deadlines. No AI calls, nothing stored.24MIT
- AlicenseNot gradedqualityBmaintenanceEnables users to audit websites and online stores for generative and answer-engine readiness, generate deployable llms.txt and llms-full.txt files, JSON-LD schema, and AI crawler rules, analyze robots access for AI bots, and extract clean page content for LLM use.MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.