> ## Documentation Index
> Fetch the complete documentation index at: https://docs.deepblocker.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Test modes

> Connect our test tools or test the agent as it is, and what each choice means for how deep a finding can go.

When you add an agent you choose how we test it. The choice sets how much we can see, and so how strong a finding can be.

## The two choices in the console

| Choice | What it means | Strongest finding |
| - | - | - |
| **Connect our test tools (recommended)** | Your test copy of the agent gets our fake tools through one MCP server entry. We see every tool call and can prove what the agent did | Critical |
| **Test it as it is** | We only talk to the agent. We cannot see what its tools do. Findings come from the conversation alone | Moderate |

> [!NOTE]
>
> A third mode, your own sandbox, exists for agents DeepBlocker set up with you. You cannot pick it in the add form.

## Connect our test tools

You make a test copy of your agent. In that copy you swap its real tools for ours. Our tools answer with safe, made-up data and record every call. Your live agent is never touched.

With this mode we can show a finding at any level, because the proof is a tool call we served ourselves. See [Connect our test tools](https://docs.deepblocker.ai/agent-assurance/connect/sandbox-mcp.md).

### Real tools still connected

The add form has a box: **I removed my agent's own real tools from the test copy**. Until you tick it, we treat the real tools as still connected. We then use only attacks that ask your agent for words, never for actions, so nothing real can happen. Tick the box once the test copy has only our tools.

## Test it as it is

We reach the agent on its real channel and judge each reply from the words alone. This is the mode for a Telegram bot, or for a web agent you cannot copy.

A finding from words alone is capped at Moderate. The agent may have said it would do something; we did not see it happen.

## Activity logs

Whichever mode you pick, your agent can send us its own activity logs over OpenTelemetry. A tool call seen in your logs grades higher than words alone and lower than our own tools: capped at High. See [Send activity logs](https://docs.deepblocker.ai/agent-assurance/connect/traces.md).

## Changing the mode

Open the agent's **Connection** tab, find **Change this agent**, pick the other mode and press **Save changes**. The mode cannot change while a test of the agent is scheduled, running or paused. Stop the test first.

## Where to go next

> [card] [Connect our test tools](https://docs.deepblocker.ai/agent-assurance/connect/sandbox-mcp.md)
>
> The MCP address, the key and the set-up per framework.

> [card] [Send activity logs](https://docs.deepblocker.ai/agent-assurance/connect/traces.md)
>
> OpenTelemetry endpoints and settings.

> [card] [Reports](https://docs.deepblocker.ai/agent-assurance/reports.md)
>
> How levels and caps become a band.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.