> For the complete documentation index, see [llms.txt](https://docs.edgetag.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.edgetag.io/mcp/installation/overview.md).

# Overview

Setting up EdgeTag MCP takes less than 2 minutes in any supported AI application. The process is the same everywhere:

1. Add the EdgeTag MCP server URL to your AI app's configuration
2. Start a conversation - the app will open a browser window for you to log in
3. Authenticate with your EdgeTag account
4. Start asking questions about your data

### Connection details

| Property           | Value                             |
| ------------------ | --------------------------------- |
| **Server URL**     | `https://mcp.edgetag.io/sse`      |
| **Transport**      | Server-Sent Events (SSE)          |
| **Authentication** | OAuth 2.0 (automatic via browser) |

### First connection

When you first use an EdgeTag tool, your AI app will open a browser window where you log in with your EdgeTag account. After authentication, you are connected and all tools become available. Access tokens refresh automatically, so you typically only need to log in once.

### Supported applications

EdgeTag MCP works with any application that supports the MCP protocol. Below are step-by-step guides for the most popular ones, but if your AI app supports MCP with SSE transport, you can connect it using the server URL above.

|                                                           |                                      |
| --------------------------------------------------------- | ------------------------------------ |
| [**Claude Desktop**](/mcp/installation/claude-desktop.md) | Anthropic's desktop app for Claude   |
| [**Claude Code**](/mcp/installation/claude-code.md)       | Anthropic's CLI agent for developers |
| [**Claude Cowork**](/mcp/installation/claude-cowork.md)   | Claude on the web with MCP support   |
| [**ChatGPT**](/mcp/installation/chatgpt.md)               | OpenAI's chat interface              |
| [**Codex**](/mcp/installation/codex.md)                   | OpenAI's coding agent                |
| [**Cursor**](/mcp/installation/cursor.md)                 | AI-powered code editor               |
| [**Windsurf**](/mcp/installation/windsurf.md)             | AI-powered code editor by Codeium    |
| [**Copilot**](/mcp/installation/copilot.md)               | GitHub Copilot in VS Code            |

### Troubleshooting

| Problem                           | Solution                                                                |
| --------------------------------- | ----------------------------------------------------------------------- |
| "Invalid token" error             | Use the `revokeToken` tool, then restart your AI app to re-authenticate |
| Tools not appearing               | Verify the MCP connection is active in your app's MCP settings panel    |
| Browser login window doesn't open | Check that your app has permission to open URLs and try restarting      |


---

# 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 dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.edgetag.io/mcp/installation/overview.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.