How to Use WebCare Pro Audit Tools via MCP & WebMCP
Connect AI models, autonomous agents, and IDEs directly to our live diagnostic suite. Enable your assistants to run 42+ technical SEO, GEO, and agent readiness tests on demand.
Available Tools in wcp-ai-audit
Callable via standard Model Context Protocol (MCP) tool execution.
Executes complete 42+ checkpoint audit on any domain (technical SEO, Core Web Vitals, GEO, LLM extractability, robots access).
Runs an ultra-fast isolated check on a single rule like webmcp, llms-txt, or mcp-server-card.
Fetches a previously executed scan report by its unique ID for comparison, benchmarking, or progress tracking.
Lists all 42+ test IDs, categories, descriptions, scoring weights, and severity classifications.
Integration by Platform
Select your environment to copy configuration snippets and tool definitions.
1. Google Gemini (Function Calling / Python / Node)
Invoke audit tools dynamically with Gemini 2.0 / 2.5 Flash & Pro models.
Define the function declaration and forward Gemini's function calls to the WebMCP endpoint at https://webcarespro.com/ai-audit/api/mcp:
from google import genai
from google.genai import types
import requests
client = genai.Client()
audit_tool = types.FunctionDeclaration(
name="run_website_audit",
description="Run comprehensive AI-readiness, GEO, and SEO audit on any website.",
parameters=types.Schema(
type=types.Type.OBJECT,
properties={"url": types.Schema(type=types.Type.STRING, description="Target URL")},
required=["url"],
)
)
# Call WebMCP JSON-RPC endpoint
def execute_audit(url):
res = requests.post(
"https://webcarespro.com/ai-audit/api/mcp",
json={
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {"name": "run_website_audit", "arguments": {"url": url}}
}
)
return res.json().get("result", {})2. ChatGPT (Custom GPTs / Actions)
Add to OpenAI GPT Editor as an Action using OpenAPI 3.1.0 schema.
- In ChatGPT, open Explore GPTs > Create a GPT > Configure.
- Scroll down to Actions and click Create new action.
- Paste the OpenAPI JSON-RPC schema below:
openapi: 3.1.0
info:
title: WebCare Pro AI Audit Tools
version: 2.0.0
servers:
- url: https://webcarespro.com/ai-audit/api
paths:
/mcp:
post:
operationId: callAuditMcpTool
summary: Execute WebCare Pro AI Audit Tool
requestBody:
required: true
content:
application/json:
schema:
type: object
properties:
jsonrpc: { type: string, example: "2.0" }
id: { type: integer, example: 1 }
method: { type: string, example: "tools/call" }
params:
type: object
properties:
name: { type: string, enum: [run_website_audit, get_audit_report, test_single_rule] }
arguments: { type: object }
required: [name, arguments]3. Claude Desktop, Cursor & Windsurf IDEs
Connect locally or over stdio in your development workflow.
Add the following to your Claude Desktop config (%APPDATA%\Claude\claude_desktop_config.json) or Cursor MCP configuration:
{
"mcpServers": {
"wcp-ai-audit": {
"command": "npx",
"args": ["-y", "tsx", "c:/path/to/wcp-ai-audit/lib/mcp/server.ts"]
}
}
}Autonomous crawlers and browser agents automatically discover these tools through our published manifests: