Visual Studio Code

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 Visual Studio Code so you can query your product data from Chat using the Fullstory agent plugin and MCP server.

Prerequisites

• Visual Studio Code with GitHub Copilot and current Chat / agent extension support (the commands below require a build that includes Chat: Install Plugin from Source and MCP: List Servers)

---

Setup

1. Install the plugin from source

Open the Command Palette (Ctrl+Shift+P on Windows and Linux, Cmd+Shift+P on macOS), run Chat: Install Plugin from Source, and choose that command when it appears.

2. Enter the Fullstory skills repository URL

When prompted, enter:

https://github.com/fullstorydev/fullstory-skills

3. Open MCP server list

Open the Command Palette again and run MCP: List Servers.

4. Select the Fullstory agent plugin entry

In the list, choose fullstory (Agent Plugin).

5. Start the MCP server

Select Start Server. VS Code may prompt you to Allow authentication or related permissions—approve those prompts so the OAuth flow can proceed.

6. Complete sign-in

When prompted, choose Sign in to another account (or the equivalent option) so you can authenticate with the Fullstory account you want to use. You may see a confirmation dialog before the browser opens the sign-in URL—confirm to continue.

What the plugin includes

Component	What it does
MCP server	Connects VS Code Chat 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.