stevenkozeniesky02/agentsid-scanner
Security scanner for MCP servers. Grades auth, permissions, injection risks, and tool safety. The Lighthouse of agent security.
This tool helps ensure the security of your Model Context Protocol (MCP) server, which exposes tools to AI agents. It takes your running MCP server (local or remote) as input and produces a detailed security report card, grading your server's resilience against common vulnerabilities like prompt injection, missing authentication, and weak permissions. Anyone responsible for deploying or managing AI agent infrastructure would use this to understand and improve their server's security posture.
Use this if you are running an MCP server and need to quickly assess its security risks, get a clear grade, and receive actionable recommendations to protect your AI agent tools.
Not ideal if you are looking for a general-purpose security scanner for traditional web applications or network infrastructure, as this tool is specifically designed for MCP server security.
Stars
14
Forks
—
Language
JavaScript
License
MIT
Category
Last pushed
Apr 03, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/stevenkozeniesky02/agentsid-scanner"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ghostwright/phantom
An AI co-worker with its own computer. Self-evolving, persistent memory, MCP server, secure...
dograh-hq/dograh
Open Source Voice Agent Platform
gmickel/flow-next
Plan-first AI workflow plugin for Claude Code, OpenAI Codex, and Factory Droid. Zero-dep task...
joseairosa/recall
Persistent cross-session memory for Claude & AI agents. Self-host on Redis/Valkey, or use the...
lintsinghua/claude-code-book
《御舆：解码 Agent Harness》42万字拆解 AI Agent 的Harness骨架与神经 —— Claude Code 架构深度剖析，15 章从对话循环到构建你自己的 Agent...