Gemini CLI

Fullstory MCP is in private beta and must be enabled for your Fullstory account before you can connect. If you're interested in being one of the first to try Fullstory MCP, sign up for the waitlist here.

Connect Fullstory to Gemini CLI so you can query your product data directly from the terminal.

Prerequisites

• StoryAI features enabled for your Fullstory org (see the note below — this is a hard requirement; without it your client will connect but show zero tools).
• Gemini CLI installed (see the official installation guide for supported platforms)

StoryAI features must be enabled

Fullstory MCP requires StoryAI features to be enabled for your org. If your org has opted out of StoryAI, your MCP client will appear to connect successfully (OAuth completes, the server shows as "connected") but no tools will be available.

An account Admin can verify or change this at Settings → GenAI Features (/settings/genai-features) in Fullstory. If you don't see that page, you don't have the role needed to change it — ask an Admin in your org.

See FAQ & Troubleshooting if your client is connected but no tools appear.

---

Setup

1. Install the Fullstory extension (from terminal)

gemini extensions install https://github.com/fullstorydev/fullstory-skills

2. Start Gemini CLI (from terminal)

gemini

3. Connect the MCP server (from within Gemini CLI)

/mcp auth fullstory

That starts the OAuth-based authentication flow for the Fullstory MCP server.

What the extension includes

Component	What it does
MCP server	Connects Gemini CLI to your Fullstory data
general-analysis skill	Guides the model through a structured analytics workflow: build a segment or metric, compute results, validate them, then investigate sessions
comparisons skill	Automatically invoked when comparing A vs B — picks the right mechanism (dimensionality vs separate segments)
session-context agent	Reads individual session transcripts in an isolated context so they don't bloat your main conversation

Use the analytics skill with /fullstory:general-analysis.

Using the tools

Once connected, ask questions about your product data in natural language:

• "What are the top frustrations on our product right now?"
• "Build a segment of users who rage clicked on the payment page and summarize 3 sessions for me."
• "What's causing the most drop-off in our checkout funnel, and can you show me what those sessions look like?"

See Example Workflows for more patterns.