INDIVIDUAL MCP TOOL

diff_scans

Compares two scans of a domain and returns a human-readable summary of what changed (grade, total, individual signals, llms.txt reachability).

agentlitmus.comnone authenticationAvailability not checked

LIVE ENDPOINT

https://www.agentlitmus.com/api/mcp

No auth detected

Connect to this endpoint to inspect the live schema for diff_scans and invoke it with your own arguments.

{}

Inferred read-only · medium confidence · heuristic, not a guarantee.

No write-capable action terms were found; this is not proof that invocation has no side effects.

CONNECT WITH APPROVAL

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

Codex

~/.codex/config.toml

[mcp_servers.agentlitmus]
url = "https://www.agentlitmus.com/api/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "agentlitmus": {
      "type": "http",
      "url": "https://www.agentlitmus.com/api/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: agentlitmus
Remote MCP URL: https://www.agentlitmus.com/api/mcp

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": {
    "agentlitmus": {
      "url": "https://www.agentlitmus.com/api/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "agentlitmus": {
      "type": "http",
      "url": "https://www.agentlitmus.com/api/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "agentlitmus",
  "transport": "streamable-http",
  "url": "https://www.agentlitmus.com/api/mcp"
}

MCP Inspector

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

scan_site — Scan a URL and grade how ready it is for AI agents.
get_scan_report — Fetch a previously generated AgentLitmus scan report by its id.
get_domain_history — Returns past AgentLitmus scans for a domain, newest first, with date, grade, and total score, so an agent can see how a site's agent-readiness has trended over time.