# MCP Agent Architecture

### Requirements & Usage

| Python Library                                                                                           | Usage / Role                                                                                                         |
| -------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------- |
| `livekit`                                                                                                | Handles the Text-to-Speech (TTS), Speech-to-Text (STT) for user interactions.                                        |
| [`mcp-agent-servers`](https://github.com/punkpeye/awesome-mcp-servers?tab=readme-ov-file#text-to-speech) | Equipping Gaby with function tools via API Routes to External Platforms (i.e. in more modern-like terms, AI Agents). |
| `huggingface-cli`                                                                                        | Huggingface CLI contains open-sourced Machine learning models and these can be used for inferencing.                 |

### Main Challenge

The main objective is to control the responses of the agent over time so the websocket wrappers / handler functions must adapt to `livekit` build framework.

### Database Selection

For the sake of prototyping Gaby as an application for the Google BigQuery competition, Google Storage was used. 

### MCP Servers & Usage in Gaby

| MCP Agent (Source Link)                                                              | Usage                                                                   |
| ------------------------------------------------------------------------------------ | ----------------------------------------------------------------------- |
| Data Visualization -<https://github.com/antvis/mcp-server-chart?tab=readme-ov-file>. | For visualizing data insights upon users' request.                      |
| Jira Integration - <https://github.com/tom28881/mcp-jira-server>                     | Monitor Team members' workflow for teams running on Jira.               |
| Notion Integration                                                                   | Used as Agent's Workspace to document and report data findings to user. |


---

# 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://whoamimi.gitbook.io/blog/projects/readme-1/ai-agent-mcp-servers/mcp-agent-architecture.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.