Set up Gemini CLI
Google’s open-source CLI coding agent. Add Agentcy so Gemini can query your marketing data from the terminal. Free tier supports MCP.
- 01
Sign up at app.goagentcy.com and create an API key
- 02
Install Gemini CLI: npm install -g @google/gemini-cli
- 03
Create or edit ~/.gemini/settings.json (global) or .gemini/settings.json (project)
- 04
Paste the config snippet below, replacing YOUR_AGENTCY_API_KEY with your actual key
- 05
Save the file and start a new Gemini CLI session: gemini
- 06
Verify with /mcp list — Agentcy should appear as a connected server
path: ~/.gemini/settings.json
{
"mcpServers": {
"agentcy": {
"httpUrl": "https://data.goagentcy.com/mcp",
"headers": {
"Authorization": "Bearer YOUR_AGENTCY_API_KEY"
}
}
}
}Gemini CLI uses httpUrl (NOT url) for remote MCP servers — transport is inferred from the field name (httpUrl = streamable HTTP, url = SSE, command = stdio). No type field needed. Shares its config format AND file with Gemini Code Assist — configuring once enables Agentcy in both. Free tier with personal Google account: 1,000 requests/day, 60 RPM (paid Google AI Pro/Ultra raises this to 1,500–2,000/day). Interactive commands available in-session: /mcp (status), /mcp list, /mcp auth, /mcp enable <name>, /mcp disable <name>. SECURITY NOTE: Gemini CLI redacts sensitive env vars (*TOKEN*, *SECRET*, *KEY*, etc.) ONLY from environment passed to spawned stdio subprocess servers — it does NOT redact HTTP request headers. Inline Bearer tokens in headers are safe. Quickest install via CLI: gemini mcp add --transport http --header "Authorization: Bearer YOUR_KEY" agentcy https://data.goagentcy.com/mcp
Stuck or want to verify these instructions yourself? These are the documentation sources we used. If something here doesn't match what you see in your client, the vendor may have updated their UI — and we'll get this page updated.
After connecting Gemini CLI and configuring your data sources in the portal, ask questions about any of them in natural language: