Cursor
Connect the Fullstory MCP server to Cursor to query your product data directly from the editor.
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).
- Cursor installed
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
-
In Cursor, go to Settings → Settings... → Cursor Setings
-
Select Plugins in the left-hand settings menu.
-
In the text box labelled Search or Paste Link, paste https://github.com/fullstorydev/fullstory-skills and hit Enter.
noteIn some versions of Cursor, the Search or Paste Link box only appears once at least one plugin is already installed. If you don't see it, install any plugin from the Plugins page first, then return here and the box should be available.
-
A plugin titled fullstory should appear, click on it and select Add to Cursor
-
Select Add for Myself and click the Add Plugin button.
-
Select Tools & MCPs from the left-hand settings menu (just below Plugins).
-
Click the Connect button beside the Fullstory MCP server.
As a part of the plugin, the general-analysis skill should be installed. This skill guides Cursor through a structured analytics workflow — building segments and metrics, computing results, validating them, and investigating sessions to explain the "why."
Verify the connection
In the Cursor chat, ask:
What Fullstory tools are available?
Cursor will list the available tools if the connection is working.
Using the tools
Once connected, you can ask Cursor questions about your product data in natural language. For example:
- "What are the biggest frustrations on my checkout page?"
- "How many users hit a network error last week? Show me as a trend."
- "Find sessions where users rage clicked on the signup button."
See Example Workflows for more patterns.