> For the complete documentation index, see [llms.txt](https://ai-security-docs.akto.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://ai-security-docs.akto.io/akto-argus-agentic-ai-security-for-homegrown-ai/agentic-red-teaming/get-started/red-team-existing-agentic-asset.md).

# Red team existing Agentic Asset

Run comprehensive security probes on your already discovered AI agents, MCP servers, and models to identify vulnerabilities before attackers do.

## Run Security Probes

Once your agentic assets are discovered and inventoried in Akto, you can immediately start probing them with [4000+ specialized security probes](/akto-argus-agentic-ai-security-for-homegrown-ai/probe-library.md) designed for AI agents and MCP servers.

### Quick Steps

1. Navigate to [**AI Red Teaming**](/akto-argus-agentic-ai-security-for-homegrown-ai/agentic-red-teaming/concepts/ai-agent-security.md) in your Akto dashboard
2. Select the assets you want to probe from your inventory
3. Choose from available probe categories (prompt injection, tool abuse, data leakage, etc.)
4. Click [**Run Scans**](/akto-argus-agentic-ai-security-for-homegrown-ai/agentic-red-teaming/how-to/run-test.md) to start probing
5. Review results and remediation guidance

## After Probing

Once probes complete:

1. **Review Results** - See all identified vulnerabilities with severity levels
2. **Get Remediation Guidance** - Follow step-by-step fixes for each issue
3. **Export Reports** - Share findings with your team
4. **Enable Guardrails** - Deploy [real-time protection](/agentic-guardrails/overview.md) to block threats in production

Need help? Contact <support@akto.io> or use in-app Intercom.