Categories › AI & Agents › Multi-agent, orchestration & workflows
Search public A2A agents and inspect read-only Agent Card and endpoint checks.
Remote server: your requests and data go to localmark.ai. Claude Code: claude mcp add --transport http localmark-agent-directory https://localmark.ai/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
search_agents — Search public agent names, descriptions and skills. Returns profile/card URLs and repair_links to stored publisher diagnostics; no task or precommend_agents — Recommend agents for a capability or job with matching reasons and caveats. Uses exactly the website/API ranking and stored observations, neget_connection_plan — Read connection metadata for a public agent without connecting to it. Accepts a LocalMark agent ID, Agent Card URL, endpoint URL or domain. list_agents — Browse public agents with pagination and repair_links to read-only publisher diagnostics.get_agent — Get a full public agent record by LocalMark ID, including original card and complete stored evidence. Collection previews are compact; this verify_agent — Read stored checks for a card URL, endpoint URL or publisher domain. Unseen targets return listing_status 'not_seen', including available loNot tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.