agent-scan MCP Server
snyk/agent-scan
[](https://agentrank-ai.com/tool/snyk--agent-scan/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge) Security scanner for AI agents, MCP servers and agent skills.
claude mcp add agentrank -- npx -y agentrank-mcp-server Overview
snyk/agent-scan is a Python MCP server licensed under Apache-2.0. Security scanner for AI agents, MCP servers and agent skills. Topics: agent, ai, mcp, modelcontextprotocol, security.
Ranked #275 out of 24846 indexed tools.
In the top 2% of all indexed tools.
Has 3,132 GitHub stars.
Has 22 contributors.
Ecosystem
Score Breakdown
3,132 stars → well-known project
Last commit 18d ago → recently updated
67/87 issues closed → decent issue management
22 contributors → active community
No dependents → no downstream usage
Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →
Matched Queries
From the README
<p align="center"> <h1 align="center"> Snyk Agent Scan </h1> </p> <p align="center"> Discover and scan agent components on your machine for prompt injections<br/> and vulnerabilities (including agents, MCP servers, skills). </p> > **Note:** We don't publish an npm package for Agent Scan. Install it via [`uvx`](#run-with-uvx) or as a [standalone binary](#run-with-a-standalone-binary). > **Note: CLI output is experimental and subject to change** > > **Agent Scan v0.5.x (planned for deprecation)** > > The raw output of this CLI — including issue codes, field names, severity labels, and response structure — is experimental and may change without notice between releases. We do not recommend building production workflows that depend on specific CLI output fields or issue codes. > > **Agent Scan v0.6 and later** > > The raw output of this CLI — including risk indicator names, scores, field names, and response structure — is experimental and may change without notice between releaRead full README on GitHub →
Get the weekly AgentRank digest
Top movers, new tools, ecosystem insights — straight to your inbox.