> For the complete documentation index, see [llms.txt](https://docs.bluerock.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.bluerock.io/bluerock-documentation-2.7.0-beta/bluerock-dashboard/event-viewer.md).
# Event Viewer
### Overview
The **Event Viewer** provides visibility into observed agents, MCP servers, and language models in the BlueRock environment. Use it to review activity, inspect available metrics, and identify entities that may require further investigation.
The Event Viewer includes three views:
* **Agents** — Displays observed agent instances and their activity.
* **MCP Servers** — Displays observed MCP servers and their request activity.
* **Models** — Displays observed language models, provider information, call counts, and token usage.
Use the time-range selector in the upper-right corner to change the reporting period. The available data and counts depend on the selected period and the activity observed by BlueRock.
***
### Agents
Select the **Agents** tab to view observed agent instances.
The table provides the following information:
| Column | Description |
| --------------- | -------------------------------------------------------------------------- |
| **Name** | Agent name and associated user or host information, when available. |
| **User** | User associated with the agent. |
| **Agent type** | Type of agent, such as Claude Code. |
| **Activity** | Current activity status displayed for the agent, such as Dormant or Ended. |
| **Triggers** | Trigger information associated with the agent, when available. |
| **Approval** | Approval-related status or information, when available. |
| **Alerts** | Alert indicators associated with the agent. |
| **Host** | Host associated with the agent, when available. |
| **Last active** | Time when the agent was last active. |
| **Runs** | Number of runs displayed for the agent. |
| **Prompts** | Number of prompts displayed for the agent. |
| **Subagents** | Number of subagents displayed for the agent. |
| **Events** | Number of events displayed for the agent. |
| **Actions** | Actions available for the agent. |
Use the search field to search by name, host, or run. Use **All agent types** to filter the list by agent type.
The table may display a notice indicating when activity counting began. Activity before the stated start time may not be included in the displayed counts.
**Filter by Agent Type**
Use the **All agent types** filter to narrow the Agents table by agent type. The available options depend on the agent types observed by BlueRock.
***
### MCP Servers
Select the **MCP Servers** tab to view observed MCP servers and their request activity.
| Column | Description |
| ---------------- | ------------------------------------------------------------------------------------- |
| **Name** | Name of the MCP server. An External label may appear for externally observed servers. |
| **Called by** | Calling agent or application, when available. |
| **Called from** | Source entity associated with the server activity. |
| **Host** | Host associated with the server, when available. |
| **State** | State displayed for the server, such as Inactive. |
| **Requests** | Number of requests displayed for the server. |
| **Errors** | Number of errors displayed, when available. |
| **Failure rate** | Failure rate displayed for the server, when available. |
| **Alerts** | Alert information associated with the server. |
| **Last seen** | Time when the server was last observed. |
| **Actions** | Actions available for the server. |
Use the search field to search by name, agent, or host.
The table may display a notice indicating when activity counting began. Review this notice when interpreting request and error counts for the selected time period.
***
### Models
Select the **Models** tab to view observed language models and their usage information.
| Column | Description |
| ------------------- | ----------------------------------------------------------- |
| **Model** | Name of the language model. |
| **Provider** | Provider associated with the model. |
| **Framework** | Framework associated with the model. |
| **Calls** | Number of calls displayed for the model. |
| **Tokens in / out** | Input and output token counts displayed for the model. |
| **Hosts** | Host information associated with the model, when available. |
| **Last seen** | Time when the model was last observed. |
| **Actions** | Actions available for the model. |
Use the search field to search by model, provider, or host.
***
### Interpreting Event Viewer Data
* Counts and activity information reflect the data available for the selected time period.
* Some fields may be unavailable when corresponding information has not been observed or loaded.
* A displayed state such as Inactive or Ended should be interpreted according to the state shown in the UI.
* Where the interface displays a counting start time, account for that time when interpreting the reported activity.
***
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.
Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:
```
GET https://docs.bluerock.io/bluerock-documentation-2.7.0-beta/bluerock-dashboard/event-viewer.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.
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.
