Registry is answering right now. Last checked 10 min ago. It exposes 5 tools. Last commit 14 Jul 2026.
The MCP server that vets MCP servers: identity, risk grade and per-tool risk before you install.
Today is the operative word: we check Registry every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 10 min ago.
claude mcp add registry --transport http https://api.policylayer.com/mcp
https://api.policylayer.com/mcp
[mcp_servers.registry]
url = "https://api.policylayer.com/mcp"
{
"mcpServers": {
"registry": {
"url": "https://api.policylayer.com/mcp"
}
}
}
{
"servers": {
"registry": {
"type": "http",
"url": "https://api.policylayer.com/mcp"
}
}
}
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
check_mcp_server
check_mcp_stack
get_change_events
search_registry
check_tool
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://api.policylayer.com/mcp | streamable-http | answering | 335 ms | 10 min ago |
Security verdicts for agent skills and MCP servers, from sandbox runs, before you install them.
Security grades (A-F) for MCP servers. Check one before you install or trust it. mcpgrade.dev
Check the trust/security score of MCP servers, agents, skills & CLIs before you install them.
Scan for prompt injection, secrets, PII, and vet MCP servers before installation
Check an MCP server before you install it — outside-in trust ratings for 7,000+ operators.
Check the danger grade of any public MCP server before you connect.
Pre-install canonical-identity verification for MCP servers and skills, with signed verdicts.
Scan AI agent skills, MCP server packages and MCP configs before you install them. Static analysis.
Answers built from our own checks of this server.