Is Your MCP Server Safe?

Free security grades for MCP servers. Search by name or paste a URL.

Try a name like "filesystem" or paste a URL like https://mcp.example.com

84,504 MCP Servers Tracked
6,477 Security Graded
71% No Authentication
Daily Scan Frequency
This week: 2866 new agents scanned

Grade Distribution

Full report
B (930) C (4213) D (414)
A: 181 B: 930 C: 4213 D: 414 F: 1

Recently Scanned

N/A
nonnname/T-Invest MCP Server
mcp Offline
N/A
VelimirMueller/code-context-mcp
mcp Offline
N/A
stoichodimov/Supabase MCP Server
mcp Offline
N/A
Habib0x0/Basic MCP Server
mcp Offline
N/A
jxnxts/mcp-brasil
mcp Offline
B
SaharshPatel24/splitwise-mcp
mcp Offline
B
AbbottDevelopments/Shopmonkey MCP Server
mcp Offline
B
nicosaporiti/Gym Coach MCP Server
mcp Offline

Needs Improvement

View all
D
io.github.bch1212/injectshield
mcp Online
D
ai.compeller/compel
mcp Online
D
io.github.myrouteonline/myrouteonline
mcp Online
D
io.github.atmflow55/datafood-mcp
mcp Online
D
io.github.juanisidoro/securecode
mcp Offline
D
com.cyclingcoachai/cycling-coach-ai
mcp Online
D
io.github.yolstudio26-oss/saroday-mcp-server
mcp Online
D
xyz.trusteed/mcp-gateway
mcp Online

Stay informed on MCP security

Get weekly security alerts, grade changes, and new agent discoveries.

How AgentGrade Works

AgentGrade scans MCP servers and AI agent endpoints with passive HTTP checks — no authentication attempts, no exploitation. Every agent gets a letter grade from A to F based on 14 security criteria including HTTPS, authentication, CORS configuration, credential exposure, and security headers.

Why MCP Server Security Matters

The Model Context Protocol (MCP) connects AI assistants to external tools and data. A misconfigured MCP server can expose credentials, leak data through CORS misconfigurations, or allow unauthorized access. AgentGrade helps developers and teams verify their agent’s security posture before deployment.