Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "mcp-agent-security-k": {
      "command": "uvx",
      "args": [
        "mcp-agent-security-kit"
      ]
    }
  }
}

Or install with pip: pip install mcp-agent-security-kit

README Excerpt

Practical audit tools, threat models, and control templates for securing Model Context Protocol (MCP) servers and agentic AI tool access. AI agents are moving from chat interfaces into systems that can read files, call APIs, query databases, trigger workflows, and act with user or service credentials. MCP makes that integration easier, but it also turns tool configuration into a security boundary. This project helps teams review that boundary before agents are connected to sensitive systems.

Topics

agentic-aiai-securitycybersecuritygovernancemcpmodel-context-protocolprompt-injectionsecurity-tools

mcp-agent-security-kit

Quick Install

README Excerpt

Topics

Related AI/LLM Servers