MCP.so
ログイン

Fullstory

@Fullstory

Fullstory について

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

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "fullstory": {
      "type": "http",
      "url": "https://api.fullstory.com/mcp/fullstory"
    }
  }
}

ツール

ツールは検出されませんでした

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

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/

コメント

「データと分析」の他のコンテンツ