API Tools
aiagentpages.com
Provides tools to browse, search, and retrieve approved agent-ready website listings, including machine-readable specs and agent-readiness reports.
ENDPOINT 1
https://www.aiagentpages.com/mcp
MCP server metadata
- Name
- AI Agent Pages
- Version
- 1.0.0
AI Agent Pages is a curated directory of agent-ready websites. Public tools need no auth. Submit/update tools require Authorization: Bearer aap_... from /connect. Discovery: /llms.txt, /AGENTS.md, /.well-known/mcp/server-card.json, /.well-known/api-catalog
Known tools 7
submit_listingSubmit a URL for directory review (requires listings.write delegation).
Potential side effectsupdate_listingUpdate metadata for a listing you submitted (requires listings.write delegation).
Potential side effectsCONNECT 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.ai-agent-pages]
url = "https://www.aiagentpages.com/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"ai-agent-pages": {
"type": "http",
"url": "https://www.aiagentpages.com/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: ai-agent-pages
Remote MCP URL: https://www.aiagentpages.com/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": {
"ai-agent-pages": {
"url": "https://www.aiagentpages.com/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"ai-agent-pages": {
"type": "http",
"url": "https://www.aiagentpages.com/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "ai-agent-pages",
"transport": "streamable-http",
"url": "https://www.aiagentpages.com/mcp"
}
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.
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.