Power your agent
The publisher's own URL. Not a PlugMCP endpoint.
Host a copy with our keys and logs.
https://myagi.bot/api/mcpThe Claude button above opens Claude with the name and URL filled in. You still confirm it there.
claude mcp add --transport http bot.myagi-openagent-registry https://myagi.bot/api/mcpRun in a terminal.
{ "mcpServers": { "bot.myagi-openagent-registry": { "command": "npx", "args": [ "-y", "mcp-remote", "https://myagi.bot/api/mcp" ] } }}claude_desktop_config.json
Remote URL or a command on your machine? How the two installs differ
Run on PlugMCP
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
LaunchFrom the publisher
The open registry, scanner, and leaderboard for agent-ready websites and services.
OpenAgent Registry (OAR) does three things in one place:
llms.txt, agents.txt / agents.json, , , + Content Signals, OpenAPI, OAuth discovery, RSL licensing, MCP/A2A registry presence - and aggregates upstream registries instead of re-doing their work.Score any website's AI-agent readiness. Open Agent Registry scanner + platform tools.
AGENTS.md.well-known/agent-card.jsonrobots.txtSources of authoritative scoring credit (registries / standards bodies):
Community resources used for domain discovery only (no score credit; we use these to know which sites to scan):
llms.txtllms.txt validation toolkitWhat OAR adds that none of the above does today:
Pre-alpha but live. Public deploy: https://openagent-registry.vercel.app.
After the v0.1 import, the registry tracks 1,400+ services across 6 industry categories, sourced from the original seed plus an import of llms-txt-hub. Every service has a live score, a label, and a generated approval-path checklist. Looking for contributors - especially for approval-path data per service (the moat).
pnpm install
pnpm dev
Then open http://localhost:3000.
See docs/rubric.md. Every signal is weighted, every weight is published, every score is reproducible from the JSON profile. No black-box scoring.
The current rubric (summary):
Labels:
llms.txtWithin each category, services are ranked by their AgentRank score. The category page is the SEO-friendly editorial surface: "Top agent-ready rental sites, [month] [year]".
See CONTRIBUTING.md. The three highest-leverage contributions today:
data/seed.json (a category, a homepage URL, optional notes) - opens a PR; CI runs a scan against it.© 2026 MCP Directory.
Score any website's AI-agent readiness. Open Agent Registry scanner + platform tools.
{ "mcpServers": { "bot.myagi-openagent-registry": { "url": "https://myagi.bot/api/mcp", "headers": {} } }}Tools
No tool list yet. Remote servers get one after the first health check.
FAQ
Copy the http config for Cursor, Claude Desktop, Claude Code, or VS Code on this page. It uses the publisher's install, not a PlugMCP proxy.
No required environment variable is listed on this record.
Myagi Open Agent Registry is reached over HTTP.
Last checked 2026-11-07. Score any website's AI-agent readiness. Open Agent Registry scanner + platform tools.