Data & Analytics · FullStory + Claude
FullStory MCP with Claude: Faster Digital Experience Insight for Product and Support Teams
The short answer
Claude works with FullStory through the Model Context Protocol, a secure connection that lets Claude read session and event data and perform permitted actions. Teams ask questions in plain English, such as which checkout steps cause the most drop-off, and Claude retrieves and summarises the relevant FullStory information under the access controls the organisation sets.
What is FullStory?
FullStory is a digital experience analytics platform. It records how users move through websites and apps, tracking sessions, events and recordings so teams can see where customers hesitate or get stuck. It also manages privacy rules that control what data is captured and organisation-level settings. Product managers, UX researchers, support leaders, engineers and growth teams typically use it to understand customer behaviour and improve product experiences faster.
How Claude connects to FullStory through MCP
The Model Context Protocol, or MCP, is an open standard that lets Claude securely use other software. Think of it as a universal adapter between Claude and a tool like FullStory. The organisation decides what Claude can access, and the connection follows that agreed scope.
Once connected through FullStory's MCP server or a direct API connection, Claude can inspect sessions, analyse events, manage exports and review recording settings. A product manager might ask for the most common errors on a sign-up page over the last two weeks, and Claude gathers the data and explains the pattern in plain language.
Permissions and approvals keep people in charge. Access uses an API key with least-privilege settings, so Claude sees only what it needs. Consequential changes, such as altering privacy rules or export configurations, can be set to require a named person's approval before they take effect, and every action is logged for review.
What you can automate
Diagnosing checkout drop-off
An e-commerce team asks Claude which steps in the checkout flow lose the most users, and on which devices. Claude reviews session and event data, highlights the friction points and summarises likely causes. The team then watches the flagged recordings to confirm what customers experienced before changing the page.
Triaging customer complaints
A support lead receives reports that a feature is not working. Claude searches recent sessions for the error events linked to those reports, groups them by browser and screen, and gives a short summary. Engineers receive a clear starting point rather than hours of manual searching.
Supporting product launch reviews
After a release, a product team wants to know whether new features are being adopted. Claude compares event counts before and after launch and flags unexpected changes. The findings feed into the next sprint planning meeting, so decisions rest on observed behaviour.
Reviewing privacy and recording settings
A compliance officer needs to confirm which fields are masked and which pages are excluded from recording. Claude reviews the current recording settings and privacy rules and lists them in plain language. Any proposed change goes to the officer for approval before it is applied.
Preparing data exports for analysts
A data team needs a regular export of specific event data for reporting. Claude helps set up and check the export parameters through natural language, and a staff member reviews the configuration before the export runs. This reduces back-and-forth between teams and cuts errors in the request.
An end-to-end workflow: Weekly friction report for the product and support teams
TriggerEvery Monday at 8:00 am, a scheduled request starts the workflow.
Claude queries FullStory for sessions and events from the previous week on the key onboarding and checkout pages.
Claude identifies pages and events with unusual error rates or drop-off compared with the prior four weeks.
Claude matches the flagged issues against open support tickets in the helpdesk system to see which problems customers are already reporting.
Claude drafts a short report with the top five friction points, linked session examples and suggested owners.
A product manager reviews and approves the report before it is posted to the team's Microsoft 365 channel and added to the sprint backlog.
OutcomeProduct and support teams start each week with a shared, evidence-based list of friction points. Issues reach the right owner sooner, and fewer problems go unnoticed between reviews. Results vary by business, and outcomes are typical rather than guaranteed.
How we set it up
Free automation audit
We review your current FullStory use, your support and product workflows, and the systems they connect to. We identify the workflows where Claude will save the most time and flag any privacy considerations early.
Secure connection
We connect Claude to FullStory using an API key or FullStory's official MCP server, with least-privilege access. Credentials are stored securely and scoped to the minimum permissions each workflow needs.
Workflow design
We design the end-to-end workflow across FullStory and your other systems, such as Microsoft 365, your CRM or ticketing tool. We define which actions run automatically and which need a named person's approval.
Testing against real cases
We test the workflow against past sessions and known issues to confirm that Claude's findings match what your team already knows. We adjust prompts, filters and approval steps until the results are reliable.
Launch, monitoring and training
We launch with monitoring and audit logs, then train your product, support and compliance teams on how to ask questions, review outputs and manage approvals. Support continues after launch as needs change.
Who benefits
- Product managers
- Understand how customers actually use new and existing features, and prioritise fixes based on observed behaviour.
- Support leaders
- Connect customer complaints to specific sessions and errors, so issues are triaged faster.
- UX researchers
- Ask questions of session data in plain English and move from hypotheses to evidence more quickly.
- Compliance and privacy officers
- Review recording and privacy settings in clear language, with changes approved before they take effect.
Security and control
- Least-privilege API access, so Claude sees only the data each workflow requires.
- Named human approval for consequential actions such as changing privacy rules or export settings.
- Masking and exclusion rules reviewed regularly against your data protection obligations.
- Full audit logs of every query and action taken through the connection.
- Regular testing to check that summaries remain accurate as your product and data change.
For teams in the US, UK, India and the Middle East
Organisations in the United States and the United Kingdom can use this connection within their existing data governance frameworks, with access limited to what each team needs. In India, deployments can be designed to meet the Digital Personal Data Protection Act, 2023, including consent and data minimisation requirements. In the UAE and Saudi Arabia, we configure workflows to respect local data protection laws. Hosting region for any custom application is chosen to meet your legal and contractual requirements.
Learn more about Claude and MCP
Anthropic's AI model and assistant.
Secure links between Claude and business tools.
How engineers build and change software with Claude.
Hosted agents that run multi-step work.
The open standard Claude uses to connect to tools.
Frequently asked questions
What does the FullStory MCP server do?
The FullStory MCP server acts as a secure bridge between AI tools like Claude and your FullStory account. It lets Claude inspect sessions, analyse events, manage exports and review recording settings through natural language requests. The server only exposes the capabilities your connection permits, so your team keeps control over what is accessed.
Is connecting FullStory to Claude secure?
Security depends on how the connection is set up. We use an API key with least-privilege permissions, store credentials securely, and log every action. Sensitive changes can require human approval. We also review privacy and masking rules as part of setup to protect end-user data.
What can Claude do with FullStory?
Typically, Claude can search sessions, summarise event patterns, explain where users struggle, help prepare exports and check recording configurations. It presents findings in plain language and can point to supporting sessions. Which actions are available depends on the permissions your organisation grants.
How long does setup take?
Timelines vary with the number of workflows and the systems involved. A focused single-workflow setup is often completed within a few weeks, including testing and training. Larger programmes covering several teams and systems take longer. The free automation audit gives a realistic estimate for your situation.
Which plan or permissions are needed?
Generally, you need a FullStory account with an API key and permissions that cover the data and settings your workflows will use. The exact plan and access requirements depend on your FullStory agreement and your internal policies. We confirm these during the free automation audit so there are no surprises.