WEBMCP + MARKDOWN

AI Agent Protocol

Wrenda turns your website into an AI-native resource. Discoverable by AI agents via an MCP server you enable per property (Pro and Scale), and readable as clean markdown by every AI crawler your rules route to optimize.

Enable WebMCP See all features

Works with any MCP client

ChatGPTClaudeGeminiLangChainCrewAICustom agents

Two ways AI agents interact with your site

Your crawler rules decide which format each AI consumer receives; the MCP server is enabled per property.

Feature 01

MCP Server -- Tool Discovery & Execution

Wrenda can expose a standards-compliant Model Context Protocol server on any of your domains. Enable it per property, run discovery to propose tools from your site, verify the ones you want live -- then AI agents built with any framework can call them in real time, querying products, docs, pricing, and inventory without scraping.

Tool manifest served at /.well-known/mcp.json once enabled
JSON-RPC 2.0 endpoint at /.well-known/mcp
Discovery proposes tools; you verify before they go live
Custom tools: search, filter, lookup, compare
Rate limiting and auth token support -- available on Pro and Scale

yoursite.com/.well-known/mcp.json

{
  "name": "Your Site Tools",
  "tools": [
    {
      "name": "search_products",
      "description": "Search product catalog",
      "inputSchema": {
        "type": "object",
        "properties": {
          "query": { "type": "string" },
          "category": { "type": "string" },
          "maxResults": { "type": "number" }
        }
      }
    },
    {
      "name": "get_pricing",
      "description": "Get current pricing for SKU"
    }
  ]
}

How an AI agent interacts

AI Agent

GPT / Claude / Gemini

Discovers tools

GET /.well-known/mcp.json

Calls search_products

POST /.well-known/mcp

Structured JSON

{ "products": [...] }

Tool response

{
  "result": {
    "products": [
      { "id": "A1", "name": "Apex Pro",
        "price": 189.99, "stock": 42 },
      { "id": "A2", "name": "Velocity X",
        "price": 149.99, "stock": 8 }
    ],
    "total": 47
  }
}

Feature 02

Markdown Rendering -- Clean LLM Context

HTML (what LLMs struggle with)

<div class="container">
  <div class="nav-wrapper">
    <script src="/bundle.js"></script>
    <div data-react-root></div>
  </div>
  <!-- 47 divs of nothing -->
  <div class="content">
    <h1 class="heading-xl">
      Marathon Shoes
    </h1>
  </div>
</div>

Markdown (clean LLM context)

# Marathon Shoes

Premium running footwear designed for
long-distance performance.

## Key Features
- Carbon fiber plate
- 40mm stack height
- 6.8oz race weight

## Specifications
| Attribute | Value |
|-----------|-------|
| Drop      | 8mm   |
| Width     | B–2E  |

AI crawlers matched by a crawler rule set to optimize receive a clean, enriched markdown document instead of your HTML. No JavaScript, no nav boilerplate, no cookie banners -- just the content LLMs need. Which user-agents get it is entirely up to your rules.

Use cases

RAG Pipelines -- Feed clean content into vector stores without HTML noise
LLM Summarization -- Token-efficient markdown means lower costs and better summaries
Agent Memory Systems -- Store meaningful content, not markup soup
Citation & Grounding -- LLMs accurately cite structured markdown over HTML

Routed by crawler rule

# Rule: user-agent matches "GPTBot" → optimize
curl https://yoursite.com/products/shoes \
  -H "User-Agent: GPTBot/1.0"

# Content-Type: text/markdown
# Returns clean, enriched markdown -- no HTML

SETUP

Enable per property, run discovery, verify tools

The MCP server is off until you switch it on for a property. Available on Pro and Scale.

Step 01

Enable MCP for a property

Turn the MCP server on for the domain you want agents to reach. Set rate limits and, optionally, an auth token. Until then /.well-known/mcp.json returns nothing.

Step 02

Run discovery, verify tools

Discovery scans your site and proposes tools -- search, lookup, pricing, inventory. Test each one, then mark it verified. Only verified tools appear in the manifest.

Step 03

Route AI crawlers to markdown

Your crawler rules decide which user-agents get the optimize action. Those crawlers receive enriched markdown, edge-cached across 300+ locations; everything else gets rendered HTML or passes through.

Step 04

Test with real agents

Agent Testing runs real AI agents through your cart, checkout and contact flows so you can see what they manage to do before customers' agents try it.

USE CASES

Built for the agentic web

AI agents are already browsing, buying, and building. Make sure they find you.

Shopping AI Agents

AI agents researching products call your search_products and get_pricing tools directly. No scraping, no hallucination -- live data from your catalog.

Get recommended in ChatGPT Shopping queries
Real-time inventory and pricing via MCP tools
Structured product data agents actually trust

RAG & Knowledge Bases

LLMs pulling content for retrieval-augmented generation receive clean markdown. No HTML parsing, no boilerplate stripping, no content extraction hacks.

Markdown served to AI crawlers your rules route to optimize
Token-efficient -- reduces embedding costs
Consistent structure across all pages

AI Documentation Bots

Support bots and AI assistants can call your docs tools to get accurate, up-to-date answers directly from your site -- not from stale training data.

search_docs and get_article MCP tools
Always-current answers from live content
Reduces hallucination in support workflows

LIVE EXAMPLE

It just works

Standard MCP protocol. Once enabled and verified, any agent can discover and use your tools.

mcp-interaction.sh
# Step 1 — AI agent discovers your tools
GET yoursite.com/.well-known/mcp.json

# Step 2 — Agent calls your search tool
POST yoursite.com/.well-known/mcp
Content-Type: application/json

{
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "name": "search_products",
    "arguments": { "query": "marathon shoes" }
  },
  "id": 1
}

# Step 3 — Your site responds with live structured data
{
  "jsonrpc": "2.0",
  "result": {
    "products": [
      { "id": "A1", "name": "Apex Pro",     "price": 189.99, "stock": 42 },
      { "id": "A2", "name": "Velocity X",   "price": 149.99, "stock": 8  },
      { "id": "A3", "name": "TrailBlazer Z", "price": 219.99, "stock": 15 }
    ],
    "total": 47,
    "query": "marathon shoes"
  },
  "id": 1
}

<50ms

Tool response time

Per property

Enable, discover, verify

JSON-RPC 2.0

Transport standard

Get Started

Ready for the agentic web?

Enable MCP per property, run discovery, verify your tools. No code changes, no infrastructure. Available on Pro and Scale.

Enable WebMCP

14-day free trial -- No credit card required