Browser.ai
New in v18.15.0

WebMCP Readiness Audit

Grade your MCP server for Claude in Chrome readiness using a 6-tier audit.

As Claude moves into web browsers, MCP servers must meet higher standards. This audit tests your server against the WebMCP standard for AI-native web automation.

6-Tier Evaluation Framework

Each tier tests a different part of MCP server readiness. Scores give more weight to core features than advanced ones.

Tier 1

Server Implementation

25%

Core MCP protocol rules and response handling

  • Server responds to MCP requests
  • Latest protocol version (2024-11-05)
  • JSON-RPC error handling
  • Response time < 5s
Tier 2

Tool Discoverability

20%

Tools exposed with proper schemas and descriptions

  • Tools exposed via tools/list
  • Descriptive tool descriptions
  • Input schemas defined
  • Property descriptions
Tier 3

Instrumentation

15%

Monitoring, health checks, and OAuth metadata

  • /health endpoint
  • /info endpoint with metadata
  • OAuth Protected Resource metadata
Tier 4

Consistency

15%

Session handling, saved state, and recovery

  • Session management tools
  • Self-healing/recovery tools
  • Consistent response structure
Tier 5

Agent Optimizations

15%

Vision, natural language, and cognitive persona support

  • Screenshot/vision capabilities
  • Natural language inputs
  • Persona-based testing
  • Accessibility testing
Tier 6

Documentation

10%

AI-readable docs and machine-friendly metadata

  • /llms.txt or /webmcp.txt
  • Documentation endpoint

Grade Scale

Your overall score is calculated from weighted tier scores. Here's what each grade means:

A
90-100
Excellent - Full WebMCP compatibility
B
80-89
Good - Small gaps in readiness
C
70-79
Fair - Some features are missing
D
60-69
Poor - Major readiness issues
F
<60
Failing - Critical protocol or feature gaps

Common Issues & Remediation

The most common issues found during WebMCP audits, sorted by impact.

SeverityIssueTierRemediation
CRITICALServer not responding to MCP requestsTier 1Verify MCP endpoint is accessible and returns 200 OK
MEDIUMOld protocol versionTier 1Upgrade to protocol version 2024-11-05
CRITICALNo tools exposedTier 2Implement and register at least one MCP tool
HIGHTools lack input schemasTier 2Add JSON Schema for all tool inputs
MEDIUMMissing descriptionsTier 2Add help text to all tools (at least 10 characters)
MEDIUMNo /health endpointTier 3Add GET /health endpoint for monitoring
LOWNo OAuth metadataTier 3Add /.well-known/oauth-protected-resource for Claude.ai
MEDIUMNo session managementTier 4Add session save/load tools for keeping state
LOWNo self-healingTier 4Add selector healing or retry tools
MEDIUMNo vision/screenshot supportTier 5Add screenshot tool for visual verification
MEDIUMNo /llms.txt fileTier 6Create /llms.txt with AI-readable server documentation

Quick Start

Audit any MCP server with a single command.

# Audit your MCP server
npx cbrowser webmcp-ready https://your-server.com/mcp
# With authentication
npx cbrowser webmcp-ready https://your-server.com/mcp --api-key YOUR_KEY
# Generate HTML report
npx cbrowser webmcp-ready https://your-server.com/mcp --html

MCP Tool

Use the webmcp_ready_audit MCP tool directly from Claude Desktop or Claude.ai.

webmcp_ready_audit

Audit an MCP server for Claude in Chrome / WebMCP readiness. Uses 6-tier scoring: Server (25%), Tools (20%), Instrumentation (15%), Consistency (15%), Agent Features (15%), Docs (10%).

url (required)
MCP server URL to audit
apiKey (optional)
API key if server requires auth
oauthToken (optional)
OAuth token if server uses OAuth
timeout (optional)
Timeout in ms (default: 30000)

Pro Tips

Start with Tier 1

Fix critical server issues first. Without a working MCP endpoint, agents cannot use any of your tools.

Add llms.txt

Adding an llms.txt file is a quick win. It helps agents learn your server's features before they call any tools.

OAuth for Claude.ai

Want your server as a Claude.ai custom connector? Add OAuth Protected Resource metadata at /.well-known/oauth-protected-resource.

Test with CBrowser

Use CBrowser's demo server as a reference. Run the audit on https://demo.cbrowser.ai/mcp to see what an A-grade server looks like.

Ready to Test Your MCP Server?

Run a WebMCP audit to see your score. Then follow the tier-by-tier steps to improve readiness.