Fullstory
@Fullstory
About Fullstory
Product analytics with receipts. Claude builds segments, computes metrics, and analyzes conversion from your Fullstory behavioral data, then pulls the real sessions behind every number. Requires a Fullstory account on an
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"fullstory": {
"type": "http",
"url": "https://api.fullstory.com/mcp/fullstory"
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is Fullstory MCP?
Fullstory MCP connects Claude (or any MCP client) to your product's behavioral data. Ask how many users adopted a feature, where checkout is leaking, or whether yesterday's release broke something, and the agent builds the segment, computes the metric, and explains the result with a link back to Fullstory.
Analytics connectors can give you numbers. Fullstory shows you what happened. Every metric unpacks into real session replay, so "conversion dropped 12%" becomes "the coupon field errors for logged-out users."
And because Fullstory autocaptures clicks, page views, errors, and frustration signals, many questions need no instrumentation at all.
Key features
- Build and save segments and metrics. Describe the users or behavior you care about in your own words; the agent creates the segment or metric in Fullstory where your whole team can reuse it.
- Compute on demand. Counts, rates, trends, and breakdowns by device, browser, geography, or user property, over any time window.
- Speak your product's language. The agent discovers your pages, named elements, and defined events, so questions map to your real product vocabulary instead of guessed selectors.
- Analyze conversion. Read your saved funnels and measure where users drop and why.
- Back every number with sessions. Retrieve the sessions and events behind any metric, including frustration signals like rage clicks and dead clicks.
- Read sessions at scale. Review dozens of sessions behind a drop-off or an alert and report the patterns, including failures that never reached your error tracker.
Example prompts
- "How many users tried the new export feature last week, and is adoption growing week over week?"
- "Signups fell after Tuesday's release. Break conversion down by browser and tell me where the drop is."
- "Pull sessions from users who abandoned checkout after an error and summarize what actually happened."
- "Review 20 sessions from users who dropped at step 3 of onboarding and give me the top three reasons they gave up."
- "I watched a user rage click the pricing toggle. How many users did that this month, and is it trending up?"
Requirements
Requires a Fullstory account on an org that is capturing sessions, with MCP access enabled (available on paid plans; not included in free plans). Sign in with your Fullstory credentials via OAuth; the agent acts with your permissions and sees only what your account can see.
Setup
Add the remote server to your MCP client:
{
"mcpServers": {
"fullstory": {
"type": "http",
"url": "https://api.fullstory.com/mcp/fullstory"
}
}
}
Full client setup guides (Claude, Cursor, VS Code, and more): https://developer.fullstory.com/mcp/introduction/
Basic information
More Data & Analytics MCP servers
dbt MCP Server
dbt-labsA MCP (Model Context Protocol) server for interacting with dbt.
mcp-simple-arxiv
andybrandtTool to work with arXiv, provide LLM with ability to search and read papers from there
Linkly Link Shortener
LinklyLinkly is an URL shortener with geo redirects, click & conversion tracking, link rotators, mobile deep links and an URL shortening API.
Google Ads MCP
cohnenAn MCP tool that connects Google Ads with Claude AI/Cursor and others, allowing you to analyze your advertising data through natural language conversations. This integration gives you access to campaign information, performance metrics, keyword analytics, and ad management—all th
PubMed Analysis MCP Server
DarkroasterA PubMed MCP server.
Comments