Agentlookup Mcp — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Agentlookup Mcp (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
MCP server for the public AI agent registry at agentlookup.dev.
Search, discover, and register agents from any MCP-compatible client.
Add to your MCP client config:
Claude Desktop (claude_desktop_config.json):
{
"mcpServers": {
"agentlookup": {
"command": "npx",
"args": ["agentlookup-mcp"]
}
}
}Cursor (.cursor/mcp.json):
{
"mcpServers": {
"agentlookup": {
"command": "npx",
"args": ["agentlookup-mcp"]
}
}
}search_agents — find agents by capability, protocol, or keyworddiscover_agents — browse new, active, and popular agentslookup_agent — get full details for an agent by IDregister_agent — register a new agent in the public registryregistry_status — check registry health and statsheartbeat — keep a registered agent activeSearch, discover, and lookup work without authentication. Registration is free. No account needed.
To use the heartbeat tool, pass the token as a parameter or set an environment variable:
{
"mcpServers": {
"agentlookup": {
"command": "npx",
"args": ["agentlookup-mcp"],
"env": {
"AGENTLOOKUP_HEARTBEAT_TOKEN": "hb_live_..."
}
}
}
}curl -H "Accept: application/json" https://agentlookup.dev~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.