> ## Documentation Index
> Fetch the complete documentation index at: https://spyro.app/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Connect your AI app

> Step-by-step setup for Spyro AI MCP in Claude, Claude Code, ChatGPT, Gemini, Gemini CLI, Codex, Cursor and VS Code, plus a quick table for other apps.

> [!TIP]
>
> Want your AI agent to set it up? Copy one prompt or install the Spyro AI skill: [Set up with your AI agent](https://spyro.app/docs/product/mcp-agent-setup.md).

Every app uses the same server address:

```text theme={null}
https://mcp.spyro.app/mcp
```

Choose how to sign in:

* **Sign in** - the app opens a Spyro AI page where you approve access. Use this whenever the app supports it.
* **Key** - you create an MCP key and the app sends it in a header. See [Manage keys and apps](https://spyro.app/docs/product/mcp-manage-access.md) to create one.

Each of the eight main apps has a full guide with tips and troubleshooting:

> [card] [Claude](https://spyro.app/docs/product/mcp-claude.md)

> [card] [Claude Code](https://spyro.app/docs/product/mcp-claude-code.md)

> [card] [ChatGPT](https://spyro.app/docs/product/mcp-chatgpt.md)

> [card] [Gemini](https://spyro.app/docs/product/mcp-gemini.md)

> [card] [Gemini CLI](https://spyro.app/docs/product/mcp-gemini-cli.md)

> [card] [Codex](https://spyro.app/docs/product/mcp-codex.md)

> [card] [Cursor](https://spyro.app/docs/product/mcp-cursor.md)

> [card] [VS Code](https://spyro.app/docs/product/mcp-vscode.md)

> [!NOTE]
>
> AI apps change their menus often. If a button has moved, search your app's settings for "connectors", "MCP" or "custom connector", or check the app's own documentation.

## Claude (claude.ai and Claude Desktop)

**1. Add a custom connector**

Open **Customize → Connectors**, click **+ Add**, then **Add custom connector**.

**2. Enter the address**

Name it **Spyro AI** and paste the server address. Leave the advanced OAuth fields empty.

**3. Connect**

Click **Add**, then **Connect**. Sign in to Spyro AI, pick your workspaces and click **Allow**.

> [!NOTE]
>
> On Team and Enterprise plans an owner adds the connector first in **Organization settings → Connectors** (**Add → Custom → Web**). Members then click **Connect**.

## Claude Code

> [tab] Sign in
>
> ```bash theme={null}
> claude mcp add --transport http spyro-ai https://mcp.spyro.app/mcp
> ```
>
> Then run `/mcp` inside Claude Code, pick **spyro-ai**, and sign in in your browser.

> [tab] Key
>
> Set the key in your shell, then add this to `.mcp.json`:
>
> ```bash theme={null}
> export SPYRO_AI_MCP_KEY="sk_mcp_..."
> ```
>
> ```json .mcp.json theme={null}
> {
>   "mcpServers": {
>     "spyro-ai": {
>       "type": "http",
>       "url": "https://mcp.spyro.app/mcp",
>       "headers": {
>         "Authorization": "Bearer ${SPYRO_AI_MCP_KEY}"
>       }
>     }
>   }
> }
> ```

## ChatGPT

**1. Open the connector settings**

Go to **chatgpt.com/plugins**, click the plus button, then **Add custom MCP server**.

**2. Enter the address**

Name it **Spyro AI**, paste the server address under **Connection** and choose **OAuth**.

**3. Accept and sign in**

Read the risk notice, click **I understand and want to continue**, then **Create as a plugin**.

**4. Install and sign in**

Install the plugin from your plugins list and sign in to Spyro AI.

> [!NOTE]
>
> Custom MCP servers in ChatGPT depend on your plan and workspace settings. On Business, Enterprise and Education workspaces an admin may need to allow them first.

## Gemini

**1. Open Developer Mode**

Go to **gemini.google.com/devmode** (also in **Settings → Gemini Apps Developer Mode**).

**2. Create the server**

Click **+ Create new** and paste the server address as the **MCP Server URL**. Leave the client settings empty.

**3. Connect**

Accept the confirmation, click **Connect**, name the app **Spyro AI** and sign in.

> [accordion] Gemini Enterprise (admins)
>
> Gemini Enterprise needs its own OAuth client.
>
> 1. In Spyro AI open **Settings → MCP → OAuth clients** and create a client with this redirect URI: `https://vertexaisearch.cloud.google.com/oauth-redirect`. Copy the client ID and secret.
> 2. In the Google Cloud console open **Gemini Enterprise → Apps → your app → Connected data stores → New data store**, search for **Custom MCP Server** and click **Add MCP server**.
> 3. Choose **OAuth 2.0**, enter these values plus your client ID and secret, and turn on **Enable PKCE Support** (Spyro AI requires it):
>
> ```text theme={null}
> Server URL:         https://mcp.spyro.app/mcp
> Authorization URL:  https://spyro.app/mcp/authorize
> Token URL:          https://mcp.spyro.app/oauth/token
> Scopes:             spyro.read
> Enable PKCE:        on
> ```
>
> 4. Finish the steps and turn the connector on. For **Read and take actions**, use the scopes `spyro.read spyro.actions`. If the **Custom MCP Server** option is missing, a Google Cloud organization policy may block it.

## Gemini CLI

Add the server to `~/.gemini/settings.json`. The `httpUrl` field selects the streamable HTTP transport:

```json ~/.gemini/settings.json theme={null}
{
  "mcpServers": {
    "spyro-ai": {
      "httpUrl": "https://mcp.spyro.app/mcp"
    }
  }
}
```

Then run `/mcp auth spyro-ai` inside Gemini CLI and sign in in your browser.

## Codex

> [tab] Sign in
>
> Add the server to `~/.codex/config.toml`:
>
> ```toml ~/.codex/config.toml theme={null}
> [mcp_servers.spyro-ai]
> url = "https://mcp.spyro.app/mcp"
> ```
>
> Then sign in:
>
> ```bash theme={null}
> codex mcp login spyro-ai
> ```

> [tab] Key
>
> Set the key in your shell, and point Codex at the variable name (not the key itself):
>
> ```bash theme={null}
> export SPYRO_AI_MCP_KEY="sk_mcp_..."
> ```
>
> ```toml ~/.codex/config.toml theme={null}
> [mcp_servers.spyro-ai]
> url = "https://mcp.spyro.app/mcp"
> bearer_token_env_var = "SPYRO_AI_MCP_KEY"
> ```

## Cursor

> [tab] Sign in
>
> Add the server to `mcp.json` (project `.cursor/mcp.json` or global `~/.cursor/mcp.json`). Cursor asks you to sign in on first use.
>
> ```json mcp.json theme={null}
> {
>   "mcpServers": {
>     "spyro-ai": {
>       "url": "https://mcp.spyro.app/mcp"
>     }
>   }
> }
> ```

> [tab] Key
>
> ```json mcp.json theme={null}
> {
>   "mcpServers": {
>     "spyro-ai": {
>       "url": "https://mcp.spyro.app/mcp",
>       "headers": {
>         "Authorization": "Bearer ${env:SPYRO_AI_MCP_KEY}"
>       }
>     }
>   }
> }
> ```
>
> Set `SPYRO_AI_MCP_KEY` in your environment and restart Cursor.

## VS Code (GitHub Copilot)

> [tab] Sign in
>
> Add the server to `.vscode/mcp.json`. VS Code asks you to sign in.
>
> ```json .vscode/mcp.json theme={null}
> {
>   "servers": {
>     "spyro-ai": {
>       "type": "http",
>       "url": "https://mcp.spyro.app/mcp"
>     }
>   }
> }
> ```

> [tab] Key
>
> VS Code asks for the key once and stores it securely.
>
> ```json .vscode/mcp.json theme={null}
> {
>   "inputs": [
>     {
>       "type": "promptString",
>       "id": "spyro-ai-key",
>       "description": "Spyro AI MCP key",
>       "password": true
>     }
>   ],
>   "servers": {
>     "spyro-ai": {
>       "type": "http",
>       "url": "https://mcp.spyro.app/mcp",
>       "headers": {
>         "Authorization": "Bearer ${input:spyro-ai-key}"
>       }
>     }
>   }
> }
> ```

## Other apps

| App | How to connect |
| - | - |
| Windsurf | Add `{"mcpServers":{"spyro-ai":{"serverUrl":"https://mcp.spyro.app/mcp"}}}` to `~/.config/devin/mcp_config.json` (Windows: `%AppData%\devin\mcp_config.json`), then sign in on first use. |
| Zed | Add `{"context_servers":{"spyro-ai":{"url":"https://mcp.spyro.app/mcp"}}}` to your Zed `settings.json`, with no Authorization header. Zed asks you to sign in. |
| Cline | Key only. Add the server to `cline_mcp_settings.json` with `"type": "streamableHttp"` and an `Authorization` header. Without that type, Cline uses the old SSE transport and cannot connect. |
| Kiro | Add the server to `mcp.json` and sign in. In Kiro web and mobile, use a key header instead. |
| JetBrains AI Assistant | Add a command server: `npx -y mcp-remote https://mcp.spyro.app/mcp`. Needs Node.js. Your browser opens to sign in. |
| Mistral Le Chat | Admins: **Connectors → + Add Connector → Custom MCP Connector**. Name it `SpyroAI` (no spaces), paste the address and click **Connect**. |
| Microsoft Copilot Studio | **Tools → Add a tool → New tool → Model Context Protocol**. Choose **OAuth 2.0** with **Dynamic discovery**. For a key, choose **API key**, type **Header**, name `X-API-Key`. Never choose Query. |
| Perplexity | **Plugins → Add custom → Add MCP connector → Remote**. Paste the address, and under **Advanced** choose **OAuth** and **Streamable HTTP**. |
| n8n | **MCP Client Tool** node: paste the address as the endpoint and choose **HTTP Streamable**. For sign-in, create an **MCP OAuth2 API** credential and keep dynamic client registration on. |

### Any other app

Apps that speak MCP over streamable HTTP: paste the address and sign in. Apps without sign-in can send a key as `Authorization: Bearer sk_mcp_...` or `X-API-Key: sk_mcp_...`.

Apps that only run local (stdio) servers can use `mcp-remote`, which opens your browser to sign in:

```bash theme={null}
npx -y mcp-remote https://mcp.spyro.app/mcp
```

> [!WARNING]
>
> Never put a key in the server address or a query string. Spyro AI only reads keys from the `Authorization` or `X-API-Key` header. Keep keys in an environment variable, not in a file you commit.

## Check that it works

Ask your app: *"List the Spyro AI tools you can use."* then *"Use Spyro AI to give me an overview of my workspace."* If you connected more than one workspace, the app first asks which one to use.

If something fails, see [Troubleshooting](https://spyro.app/docs/product/mcp-troubleshooting.md).

Building your own client or agent? See the [Developer guide](https://spyro.app/docs/product/mcp-developers.md).

## Related

* [MCP server overview](https://spyro.app/docs/product/mcp-overview.md)
* [Manage keys and apps](https://spyro.app/docs/product/mcp-manage-access.md)
* [Tools reference](https://spyro.app/docs/product/mcp-tools.md)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.