> ## 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.

# Gemini

> Connect Spyro AI to the Gemini app in Developer Mode, or to Gemini Enterprise with your own OAuth client.



Let your AI agent configure this for you

        Copy configuration prompt


      \<details><summary>Preview the prompt</summary>
        \<pre /></details>

There are two ways to use Spyro AI in Gemini. Individuals use **Developer Mode** in the Gemini app. Organizations use **Gemini Enterprise**, where an admin sets up a connected app.## Gemini app (Developer Mode)**1. Open Developer Mode**Go to **gemini.google.com/devmode**. You can also find it in **Settings → Gemini Apps Developer Mode**.**2. Create the server**Click **+ Create new** and paste the address as the **MCP Server URL**:```text theme={null}
https://mcp.spyro.app/mcp
```Leave the client settings empty.**3. Connect and sign in**Accept the confirmation, click **Connect**, name the app **Spyro AI** and sign in. Tick your workspaces, choose the access level and click **Allow**.Then ask: *"Use Spyro AI to give me an overview of my workspace."*## Gemini Enterprise (admins)Gemini Enterprise needs a client ID and secret, so you create an OAuth client in Spyro AI first.**1. Create an OAuth client in Spyro AI**Open **Settings → MCP → OAuth clients → Create OAuth client**. Use this redirect URI, then copy the client ID and secret (the secret is shown once):```text theme={null}
https://vertexaisearch.cloud.google.com/oauth-redirect
```**2. Add the MCP server in Gemini Enterprise**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. Enter the OAuth settings**Choose **OAuth 2.0**, enter these values with your client ID and secret, and turn on **Enable PKCE Support**. Spyro AI requires PKCE, so sign-in fails without 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 and turn it on**Finish the steps, sign in and turn the connector on. If the **Custom MCP Server** option is missing, a Google Cloud organization policy may block it.## Try these prompts- *"Use Spyro AI to find my biggest SEO issues and rank them by impact."*
- *"Which queries have many impressions but few clicks in Google Search Console?"*
- *"Compare my AI visibility against my competitors."*## Tips- Gemini asks before it calls a tool. Read the request before you approve it.
- To let Gemini make changes, approve **Read and take actions** on the Spyro AI screen. Use **Read** otherwise. You still confirm each change in Spyro AI.
- For Gemini Enterprise, scope `spyro.read` gives read access. Use `spyro.read spyro.actions` only if the team needs to make changes.
- The Spyro AI sign-in screen marks Gemini as **Unverified**. That is expected.## If it fails- **Developer Mode is missing:** it depends on your Google account and region. Check Google's own help.
- **Sign-in fails in Gemini Enterprise:** check that **Enable PKCE Support** is on, the redirect URI, the client ID and the secret, and that the three URLs match exactly.
- More: [Troubleshooting](https://spyro.app/docs/product/mcp-troubleshooting.md).## Related- [Gemini CLI](https://spyro.app/docs/product/mcp-gemini-cli.md)
- [Manage keys and apps](https://spyro.app/docs/product/mcp-manage-access.md)


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