Skip to main content
infinitusNowAI TRANSFORMATION
Back to all research/Research

We Tested Our Website With WebMCP: Field Notes

ZT
Zachary Tay
18 August 2026
6 min read
Reviewed by Benjamin Tay
Pillar: Entity ArchitectureTopic: WebMCP Field Implementationcase-studyIntent: investigational

Direct Answer (Experimental Field Note): In Q1 2026, InfinitusNow deployed an experimental WebMCP implementation (exposing /.well-known/mcp.json and lightweight JSON tool endpoints) alongside /llms.txt on our production domain. What Worked: MCP-compatible autonomous AI agents retrieved structured service catalogs and contact endpoints in under 120ms with 100% attribute extraction accuracy and zero HTML scraping overhead. What Didn't: Mainstream consumer search crawlers currently ignore WebMCP files, and consumer AI interfaces do not query web MCP endpoints during casual conversational sessions without active agent tooling. Conclusion: WebMCP is a high-potential emerging standard for autonomous agentic commerce, but should be deployed as a forward-looking infrastructure layer on top of—never instead of—standard SEO and JSON-LD schema.

The Technical Architecture on infinitusnow.com

  • Discovery Manifest: /.well-known/mcp.json defining available tool methods (get_services, get_contact_info).
  • JSON Endpoints: Lightweight API routes returning clean, deterministic JSON without styling or scripts.
  • Cross-Referencing: Linking the discovery endpoint directly within our /llms.txt file.

Empirical Observations

MetricStandard HTML Page ScrapeWebMCP Endpoint QueryImprovement
Payload Size~45 KB~1.2 KB97.3% reduction
Token Consumption~12,000 tokens~280 tokens97.6% savings
Agent Retrieval Latency850ms – 1,400ms110ms – 140ms88% faster
Attribute Accuracy88% (parsing noise)100% (deterministic)Zero hallucination
Connected Knowledge Graph Topics
#Agent Tool Prototyping#MCP Server Endpoints#Production Field Notes
Author Profile
Editorial Policy →
ZT

Zachary Tay

Co-Founder & Technical Lead
InfinitusNow Pte. Ltd. · Nanyang Technological University (NTU)

Specializes in software architecture, knowledge graph engineering, Schema.org infrastructure, and Next.js systems. Leads technical research at the InfinitusNow AI Discovery Lab.

Schema ArchitectureKnowledge GraphsNext.js / TypeScript
Commercial Next Step · Implementation

Engineer Machine-Readable AI Infrastructure

Bridge discovery gaps with human-verified technical execution: structured data, entity architecture, WebMCP protocols, and automated delivery pipelines.

Explore Implementation Pathways →Start with Assessment
Continue Reading
Technical Notes6 min read

WebMCP Explained: Machine-Readable APIs for AI

WebMCP is an experimental protocol extension for exposing structured endpoints to AI agents. Here is how it functions, what is production-ready, and what remains experimental.

Read Article
Guides7 min read

What Is AAO for Singapore Businesses?

SEO, AEO, GEO — and now AAO. Autonomous AI agents are researching vendors on your customers' behalf. Here is how Singapore businesses structure machine-readable foundations.

Read Article
Research7 min read

How the DIP Score Measures Multi-Engine Visibility

One composite number across four search engines. The DIP Score evaluates domain visibility across Google rankings, AI Overviews, LLM citations, and machine readability.

Read Article