AI & Machine Learning

machineread.ai

Runs a machine-readable audit for a URL, evaluating AI agent accessibility and search-discovery readiness.

WebMCP1 endpoint1 known toolsFirst detected August 29, 2026Last detected August 29, 2026

ENDPOINT 1

https://www.machineread.ai

No auth detected

MCP server metadata

Name: WebMCP

Capabilities

declarative

Known tools 1

run_machineread_audit

Run the MachineRead Essentials audit for a public HTTP(S) URL. Returns a deterministic AuditSummary with 13 check groups, agent-readiness gates, benchmark context, and locked advanced rows. Use when the user wants to audit a URL for AI agent accessibility, search-discovery readiness, or general machine readability.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.webmcp]
url = "https://www.machineread.ai"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "webmcp": {
      "type": "http",
      "url": "https://www.machineread.ai"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: webmcp
Remote MCP URL: https://www.machineread.ai

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "webmcp": {
      "url": "https://www.machineread.ai"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "webmcp": {
      "type": "http",
      "url": "https://www.machineread.ai"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "webmcp",
  "transport": "streamable-http",
  "url": "https://www.machineread.ai"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.