agentseal

getagentseal/agentseal

★ 199 stars Python 🔒 Security Updated today

Security toolkit for AI agents. Scan your machine for dangerous skills and MCP configs, monitor for supply chain attacks, test prompt injection resistance, and audit live MCP servers for tool poisoning.

View on GitHub →

Quick Install

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

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "agentseal": {
      "command": "uvx",
      "args": [
        "agentseal"
      ]
    }
  }
}

Or install with pip: pip install agentseal

README Excerpt

<p align="center"> <a href="https://agentseal.org"> <img src="assets/logo-white.png" height="96" alt="AgentSeal" /> </a> </p> <h3 align="center">Security toolkit for AI agents. Red-team prompts, detect MCP poisoning,<br>scan skill files, trace toxic data flows. 225+ tests across 28 agents.</h3> <p align="center">

Tools (3)

ANTHROPIC_API_KEYMINIMAX_API_KEYOPENAI_API_KEY

Topics

agent-securityai-agentai-agentsai-securityclillmllm-securitymcpmcp-securitymodelcontextprotocolpentestingprompt-injectionred-teamred-teamingsecurity

agentseal

Quick Install

README Excerpt

Tools (3)

Topics

Related Security Servers