INDIVIDUAL MCP TOOL
scan_site
Run a fresh AgentCapable readiness scan of a public website: how its edge treats AI-agent requests (dual datacenter vantage), plus a deterministic 0-100 agent-readability score over 23 checks (rubric rubric-v1.1, no LLM in the number).
LIVE ENDPOINT
https://agentcapable.dev/mcp
Connect to this endpoint to inspect the live schema for scan_site and invoke it with your own arguments.
Indexed input schema
{}Risk classification
Inferred read-only · medium confidence · heuristic, not a guarantee.
- A tool name or description suggests retrieving external content.
Parent server
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.agentcapable]
url = "https://agentcapable.dev/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"agentcapable": {
"type": "http",
"url": "https://agentcapable.dev/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: agentcapable
Remote MCP URL: https://agentcapable.dev/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": {
"agentcapable": {
"url": "https://agentcapable.dev/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"agentcapable": {
"type": "http",
"url": "https://agentcapable.dev/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "agentcapable",
"transport": "streamable-http",
"url": "https://agentcapable.dev/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
Related tools
get_report— Fetch a previously completed AgentCapable scan report by scan id.list_checks— The public AgentCapable check catalog: every scored check (stable id, category, frozen weight, why it matters, fix guidance) for rubric rubric-v1.1.