# Manual Import

Manual import allows you to directly import your AI agents, MCP servers, and AI models into Akto for AI Red Teaming without setting up continuous discovery agents. This is perfect for quick probing, CI/CD pipelines, or when you only need to probe specific components.

## When to Use Manual Import

Manual import is ideal when you:

* Want to probe specific AI agents or MCP servers without full infrastructure setup
* Need to run security probes in your CI/CD pipeline
* Have standalone AI models or agents to validate
* Prefer a quick start without deploying discovery agents

## Import Options

### Import AI Agents

Import AI agents from AWS Bedrock, Azure AI Foundry, Databricks, Google Vertex AI, IBM Watsonx, or your custom agents directly into Akto for AI Red Teaming.

→ [Import AI Agents](/akto-argus-agentic-ai-security-for-homegrown-ai/agentic-red-teaming/get-started/manual-import/ai-agent-import.md)

### Import MCP Servers

Import MCP servers by connecting to their SSE endpoints. Akto will automatically discover all tools, resources, and prompts for probing.

→ [Import MCP Servers](/akto-argus-agentic-ai-security-for-homegrown-ai/agentic-red-teaming/get-started/manual-import/mcp-import.md)

### Import AI Models

Import large language models and custom AI implementations for comprehensive AI Red Teaming.

→ [Import AI Models](/akto-argus-agentic-ai-security-for-homegrown-ai/agentic-red-teaming/get-started/manual-import/ai-model-import.md)

## What Happens After Import

Once you import your components:

1. They appear in your Akto inventory immediately
2. You can run security probes right away
3. Akto identifies vulnerabilities specific to your agent or model
4. You get detailed remediation guidance for any issues found

For continuous discovery of your infrastructure, consider setting up [homegrown discovery agents](/akto-argus-agentic-ai-security-for-homegrown-ai/connectors.md) or [endpoints discovery agents](/akto-argus-agentic-ai-security-for-homegrown-ai/overview.md).


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://ai-security-docs.akto.io/akto-argus-agentic-ai-security-for-homegrown-ai/connectors/others/manual-import.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.