Give Gemini CLI access to skill discovery through one MCP connection. Describe your task, and your agent can find and load relevant instructions without installing each skill separately.

Before you start

Install a current Gemini CLI release with HTTP MCP and OAuth support.

You need a 9octopus account to approve access. You can sign in or create one during connection. Use the account for this environment; staging and production accounts are separate.

1. Add 9octopus to Gemini CLI

Use this server URL with remote MCP over Streamable HTTP and OAuth:

https://app.9octopus.work/mcp
  1. Add the HTTP server. Run this in your terminal. User scope stores the entry in your user settings; use project scope instead if you only want it in this project.
    gemini mcp add --transport http --scope user 9octopus https://app.9octopus.work/mcp

The examples name the connection 9octopus. If you choose another name, use that name in commands and prompts. If you already have a connection, inspect it before adding another.

2. Sign in and approve access

Start an interactive Gemini CLI session and enter the slash command below. Complete the browser authorization flow.

/mcp auth 9octopus

On the 9octopus consent page, check the client name, sign in, and approve access. Keep the agent open until it finishes connecting. You do not need to paste a bearer token into your configuration.

3. Check the connection and try a task

In the interactive session, use /mcp list to inspect the server. From your terminal, gemini mcp list also shows connection errors.

You can also open Connected agents in 9octopus to confirm that the connection is active. Then send this prompt to Gemini CLI:

Use the 9octopus MCP connection to find public skills for reviewing a landing page’s accessibility. Show me the relevant descriptions and sources. Load the best fit, confirm its exact version, and explain what access you need before starting the review.

Your agent should discover skills, load the selected release, and read its instructions. It still needs the tools and permissions required to perform the task. If no suitable skill exists, refine the task or browse public skills.

Public task recommendations may send your task description to OpenAI. Keep secrets and private repository contents out of discovery prompts.

Optional: help your agent discover skills as you work

Open Connections and select Agent instructions. Copy the guidance into your client’s persistent instructions, or merge the downloaded AGENTS.md into a supported instruction file. Keep existing rules; supported filenames and settings vary by agent.

Troubleshooting

  • For expired credentials, repeat /mcp auth 9octopus inside Gemini CLI. If the server is disabled, use /mcp enable 9octopus before retrying.
  • Expired consent or HTTP 401: restart authentication from the agent and complete the new browser flow. An old consent URL cannot be reused.
  • Pending in Connected agents: the agent has not finished the token exchange. Retry sign-in, then revoke any abandoned pending entry.
  • Need to disconnect? Revoke this connection in Connected agents. To reconnect later, clear its saved authentication in the client and sign in again.

Setup reference: Gemini CLI MCP documentation. Instructions reviewed October 27, 2026; client menus and plan availability can change.

Using a different agent? Choose another setup guide or follow the general MCP connection instructions.