***

title: AI Integrations
description: >-
Connect MeetStream to AI coding assistants and chat tools using our MCP server
and Claude Skill.
icon: brain-circuit
subtitle: >-
MeetStream provides two ways to bring its documentation and API directly into
your AI workflow: a **Claude Skill** that pre-loads Claude with deep
MeetStream knowledge and an **MCP Server** for real-time doc search inside
your coding tools.
------------------

<Note>
  Every page in these docs also has quick-access buttons below each heading —**Open in Claude**, **Open in ChatGPT**, and **Connect to Cursor** so you can jump straight into prompting the LLM based on that page's content.
</Note>

## Claude Skill

The MeetStream Claude Skill is a pre-packaged knowledge file that teaches Claude everything about the MeetStream API such as authentication, bot lifecycle, webhooks, live transcription, WebSocket control, and Google Calendar integration without needing to search every time.

<Card title="Meetstream Claude Skill" href="https://drive.google.com/uc?export=download&id=1NgicxHwUzrGTR50r81iI_YyI87MNxniP" icon="external-link">
  Click this card to download our Claude skill
</Card>

### What's included

* Full bot lifecycle walkthrough
* All callback event types and payload formats
* Live transcription and audio streaming setup
* WebSocket bot control commands
* Google Calendar auto-scheduling integration
* Data retention configuration
* Ready-to-use `curl` examples for common workflows

### Installation

1. **Download** the ZIP file above and unzip it — you'll get a `meetstream-skill/` folder containing `SKILL.md` and `references/api-quickstart.md`
2. Open **Claude.ai** → Profile → **Settings** → **Capabilities**
3. Click **Upload Skill** and select the `meetstream-skill/` folder (or the `SKILL.md` file directly)
4. Enable the skill — Claude will now apply MeetStream context automatically when relevant

<Note>
  The skill pairs with the MCP server for the most comprehensive experience: the skill handles common patterns and context, while the MCP server handles live doc lookups for edge cases.
</Note>

***

## MCP Server

The MeetStream MCP (Model Context Protocol) server lets AI tools like Cursor, VS Code, Claude Code, and Claude.ai query our live documentation on demand.

**MCP Server URL:**

```
https://docs.meetstream.ai/_mcp/server
```

### Setup Instructions

<Tabs>
  <Tab title="Cursor">
    1. Open **Cursor Settings** → **Features** → **MCP Servers**
    2. Click **Add new MCP server**
    3. Set **Name** to `meetstream-docs`
    4. Set **Type** to `SSE`
    5. Set **URL** to `https://docs.meetstream.ai/_mcp/server`
    6. Click **Save** and restart Cursor
  </Tab>

  <Tab title="VS Code (Copilot)">
    Add to your `.vscode/mcp.json` or user settings:

    ```json
    {
      "servers": {
        "meetstream-docs": {
          "type": "sse",
          "url": "https://docs.meetstream.ai/_mcp/server"
        }
      }
    }
    ```
  </Tab>

  <Tab title="Claude Code">
    Run in your terminal:

    ```bash
    claude mcp add meetstream-docs --transport sse https://docs.meetstream.ai/_mcp/server
    ```
  </Tab>

  <Tab title="Claude.ai">
    1. Go to **claude.ai** → Click your profile → **Settings**
    2. Navigate to **Integrations** → **Add integration**
    3. Enter the MCP URL: `https://docs.meetstream.ai/_mcp/server`
    4. Save and enable the integration
  </Tab>
</Tabs>

Once connected, your AI assistant can search and reference MeetStream documentation in real time during your sessions.

***

## Recommended Setup

For the best developer experience, use **both together**:

| Tool             | Purpose                                              |
| ---------------- | ---------------------------------------------------- |
| **MCP Server**   | Real-time doc search in Cursor, VS Code, Claude Code |
| **Claude Skill** | Pre-loaded MeetStream context in Claude.ai chat      |

With both enabled, LLMs can answer questions about any MeetStream endpoint, generate working API calls, debug webhook payloads, and help architect integrations all grounded in accurate, up-to-date documentation.