> ## Documentation Index
> Fetch the complete documentation index at: https://docs.qwairy.co/llms.txt
> Use this file to discover all available pages before exploring further.
# Getting Started
> Connect your AI assistant to Qwairy in 2 minutes. Works with Claude, ChatGPT, Cursor, VS Code, Windsurf, and any MCP-compatible client.
Connect your favorite AI assistant to your Qwairy GEO monitoring data. All you need is the server URL:
```
https://mcp.qwairy.co
```
Authentication is handled automatically via OAuth — a browser window opens, you sign in, and you're connected.
MCP is an open protocol that is still evolving. Some clients may update their setup flow over time. If the steps below don't match exactly what you see, refer to your client's documentation — the server URL remains the same.
## Prerequisites
* A **Qwairy Starter plan** or higher
* At least one **active brand** with monitoring data
* An MCP-compatible AI client (see options below)
## Choose Your Client
1. Go to **Settings** → **Connectors**
2. Click **Add custom connector**
3. Enter a name (e.g. `Qwairy`) and the server URL:
```
https://mcp.qwairy.co
```
4. Click **Add**, then authorize the connection when prompted
This works the same way on Claude Desktop (macOS/Windows) and Claude.ai (web).
Requires a **ChatGPT Pro, Team, Enterprise, or Edu** plan.
1. Go to **Settings** → **Advanced** → Enable **Developer Mode**
2. Go to **Settings** → **Connectors** → **Create**
3. Enter a name (e.g. `Qwairy`) and the server URL:
```
https://mcp.qwairy.co
```
4. Set authentication to **OAuth**
5. Save, then authorize the connection when prompted
1. Open **Cursor Settings** → **MCP**
2. Click **+ Add new MCP server**
3. Set type to **HTTP** and enter the URL:
```
https://mcp.qwairy.co
```
Or add it manually to your project's `.cursor/mcp.json`:
```json theme={null}
{
"mcpServers": {
"qwairy": {
"url": "https://mcp.qwairy.co"
}
}
}
```
Run this single command in your terminal:
```bash theme={null}
claude mcp add qwairy --transport http https://mcp.qwairy.co
```
Claude Code will handle OAuth authentication automatically on first use.
Open the Command Palette (`Cmd+Shift+P`) and run **MCP: Add Server**, then enter:
```
https://mcp.qwairy.co
```
Or add it to your `.vscode/mcp.json`:
```json theme={null}
{
"servers": {
"qwairy": {
"type": "http",
"url": "https://mcp.qwairy.co"
}
}
}
```
1. Open **Cascade** (`Cmd+L`)
2. Click the **MCP** icon → **Configure**
3. Add a new server with the URL:
```
https://mcp.qwairy.co
```
Or add it to your Windsurf MCP config (`~/.codeium/windsurf/mcp_config.json`):
```json theme={null}
{
"mcpServers": {
"qwairy": {
"serverUrl": "https://mcp.qwairy.co"
}
}
}
```
Windsurf uses `serverUrl` (not `url`) for remote HTTP servers.
For clients that support **remote MCP servers** natively, use the URL:
```
https://mcp.qwairy.co
```
For clients that only support **stdio transport**, use the `mcp-remote` bridge:
```json theme={null}
{
"mcpServers": {
"qwairy": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://mcp.qwairy.co"]
}
}
}
```
This works with Zed, Cline, and any other MCP-compatible client.
## Authorize the Connection
After adding the server, your client will initiate the OAuth flow:
1. A browser window opens with the Qwairy sign-in page
2. Sign in with your Qwairy account
3. Authorize the connection
4. You're redirected back — the connection is active
Your credentials are never shared with the AI client. Authentication uses OAuth 2.1 with PKCE — only a secure, scoped access token is exchanged. [Learn more about OAuth](/mcp/oauth).
## Start Querying Your Data
Try these example prompts:
```
What brands am I monitoring?
```
```
Show me my GEO performance for the last 30 days
```
```
Who are my top competitors in AI responses?
```
```
Which sources cite my brand most often?
```
```
What are the top content opportunities for my brand right now?
```
```
Compare my brand's sentiment across different AI providers
```
```
Which prompts are driving the most visibility for my competitors?
```
## Troubleshooting
### "Server not found" error
* Ensure the URL is exactly `https://mcp.qwairy.co` (no trailing slash)
* Check that your config file is valid JSON
* Restart your AI client after editing the config
### "Authentication failed" error
1. Check that you have a **Starter plan** or higher
2. Ensure you're signing in with the correct Qwairy account
3. Try disconnecting and reconnecting
### "No data returned"
Make sure you have:
* At least one brand with status **"Live"**
* Monitoring enabled with generated responses
* Recent data (within the last 30 days by default)
### Client doesn't support remote MCP?
Use the `mcp-remote` bridge — see the **Other Clients** tab above.
## Rate Limits
The MCP server allows **300 requests per minute** and **3,000 requests per day** per connection. This is more than enough for interactive use, but automated scripts should implement appropriate delays.
## Measure Tools and Scopes
Tools that read off-AI analytics (Search Console, Bing, referrer traffic, AI revenue, crawler activity) live under the **Measure** category and require the `read:measure` scope. If you connected before this scope existed, disconnect and reconnect to pick it up — scopes are never expanded silently on an already-issued token. See [Measure Tools](/mcp/tools/measure).
## Next Steps
Learn what each tool does and its parameters
See real-world usage examples
Connect Qwairy with your SEO, CMS, and project management tools
How authentication works under the hood