First MCP-specific security scanner

Secure Your MCP Servers

Detect tool poisoning, over-permissioned access, prompt injection vectors, and supply chain risks in Model Context Protocol servers.

Free security analysis · No signup required · Results in seconds

1,000+
Exposed MCP servers detected
RCE
Found in official Anthropic server
Tool Poisoning
#1 attack vector in MCP

What We Detect

Tool Poisoning

Malicious instructions hidden in tool descriptions that trick LLMs into harmful actions.

Over-Permissioned

Servers requesting full filesystem, network, or command execution access without justification.

Prompt Injection

Vulnerabilities allowing attackers to override instructions via crafted tool inputs.

Supply Chain

Dependency risks, typosquatting, and compromised packages in the MCP ecosystem.

Recent Scans

Loading...