M MCPowered Scan a server

MCP trust layer

The trust and verification layer for MCP servers.

Federated directory across the Linux Foundation registry, Smithery, Glama, mcp.so, and the major community lists. Per-server trust scoring built on static source review, sandboxed runtime behavior, supply-chain provenance, and incident history. Scan any server before you install it.

Browse the directory Scan a server

Federation sources

We index every MCP server you can install.

Linux Foundation MCP Registry

Canonical baseline (LF AAIF official)

Smithery

Install + auth layer

Glama

Hosted execution + gateway

mcp.so

Community catalog

awesome-mcp-servers

Community list

Why trust scoring

The MCP threat model is real and dated.

Sept 2025

postmark-mcp

First confirmed malicious MCP server in the wild. Silently BCC'd all outgoing emails to attacker.

Oct 2025

Smithery registry

Path-traversal vulnerability exposed a builder token granting root access to 3,000+ hosted apps.

Apr 2026

STDIO transport RCE

Core design flaw enabling authenticated RCE. Affected 150M+ downloads across Letta AI, LangFlow, Windsurf.

AgentSeal scanned 1,808 MCP servers in 2025. 66% had security findings.