OWASP Top 10 for Agentic AI security MCP server — prompt injection detection, tool poisoning, excessive agency, data leakage assessment
OWASP Top 10 for Agentic AI security MCP server — prompt injection detection, tool poisoning, excessive agency, data leakage assessment
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| full_agent_scan | Full OWASP Agentic Top 10 security scan |
| assess_agentic_security | Assess against specific OWASP Agentic categories |
| check_prompt_injection | Test for prompt injection vulnerabilities |
| check_tool_poisoning | Check for tool poisoning risks |
| check_excessive_agency | Assess agency level vs minimum required |
{
"mcpServers": {
"owasp-agentic": {
"command": "python",
"args": [
"path/to/server.py"
]
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
Give your coding agent the full DevTools toolbox: traces, network, console, heap snapshots and Lighthouse.
Workers, KV, R2 and D1 by conversation — Cloudflare's official remote servers for building and observability.
Premium agentic endpoint for ai-safety-incident-logger-mcp.
Austria RIS: federal & state law, case law, gazettes, change monitoring (Bundesrecht, Judikatur).
Secure, self-hosted New Relic observability and administration tools for MCP clients
Model Context Protocol server for Sentry integration