The Userflow MCP server lets you query your Userflow data from Claude, ChatGPT, and other AI tools that support MCP. Ask questions in plain language about your flows, users, segments, events, and assistant conversations — without building charts or digging through the dashboard.
This first release is read-only: the AI tool can pull data and answer questions, but can't change anything in your Userflow account.
Availability: the Userflow MCP is available on all plan types. At the initial launch, only account owners and admins can connect and use it. Once sign-in moves to OAuth shortly after, it's available to everyone on your team.
What you can ask
Once connected, you can ask questions in natural language about anything happening in your Userflow account. A few examples:
Your flows
"How many flows do I have published, and which ones are still in draft?"
"When was the 'Welcome Tour' first published, and who's edited it most recently?"
"Which flows are tagged 'Onboarding' and are currently live?"
Performance and analytics
"How many people saw the 'Product Tour' yesterday?"
"What's the completion rate for the 'Trial Signup' flow this month?"
"Compare completion rates between 'Onboarding A' and 'Onboarding B'."
"Summarize the NPS responses we received in the last 30 days."
Your users and companies
"Did jane@acme.com complete the setup flow?"
"Show me all companies in the 'Trial' segment."
"Which users on the Free plan haven't logged in for 10 days?"
Your Adoption Agent
"How many conversations did the Adoption Agent have last week?"
"What are the most common topics customers asked about?"
Your account setup
"List all the events we're tracking."
"What user and company attributes are defined on this account?"
Your help content
"What does our help center say about setting up single sign-on?"
"Find the help article about inviting team members."
"Summarize what our knowledge base covers about billing."
The AI tool will pick the right data to look at based on your question. You can drill in, ask follow-ups, and combine filters the same way you'd talk to a teammate.
What's not in this release
A few things are coming in later waves — calling them out so you know what to expect at launch:
Writing or changing data. This release can read your Userflow data but can't publish flows, create segments, update users, or invite team members. Those actions are planned for a future phase.
Native connector listings. You won't find Userflow by searching the connector directory in Claude or ChatGPT yet. You'll add it as a custom MCP using the steps below. One-click native connections are planned for a later phase.
How to connect
Setup has two parts: adding the Userflow MCP as a custom connector in your AI tool, and signing in to authorize it.
Who can connect: at launch, only account owners and admins can set this up. Once OAuth sign-in arrives shortly after, everyone on your team can connect.
1. Add the Userflow MCP as a custom connector
You'll need the Userflow MCP server URL:
Most accounts:
https://api.userflow.com/mcpEU accounts:
https://api.eu.userflow.com/mcp— use this if your main production environment is in the EU.
In Claude:
Personal account: go to Settings → Connectors, click the + to add a custom connector, enter a name (for example, "Userflow MCP") and the server URL above in the dialog that opens, and click Add. Then complete the sign-in flow to finish connecting.
Team or Enterprise account: an admin adds the connector once using the steps above. After that, anyone on the account can open Settings → Connectors, find the listing the admin created (it has the name they gave it), select it, click Connect, and complete the sign-in flow.
In ChatGPT and other AI tools, add the same server URL wherever the tool lets you add a custom MCP or connector.
2. Sign in to authorize
How you authorize depends on when you connect:
At launch (API key): during the connect flow you'll be asked to choose a Userflow API key from a dropdown — you no longer paste a token in.
If you already have an API key, select it from the dropdown and authorize.
If you don't have one yet, create it first: in Userflow, go to Settings → API and generate a new API key (give it a name you'll recognize, such as "Claude MCP"). Then return to the connect flow and select it from the dropdown.
Once OAuth arrives (shortly after launch): you'll sign in to Userflow directly from the connect flow — no API key needed.
Once authorized, your AI tool can query your Userflow data. Try asking "How many flows do I have published?" to confirm the connection is working.
What to expect at launch
This is the first phase of the Userflow MCP. What to expect:
Structural and analytics questions both work from launch — flow counts, status, ownership, segment membership, event definitions, and attributes, plus completion rates, drop-off, NPS summaries, and comparative analytics. Most data use cases are covered from launch.
A few capabilities arrive just after launch. Tools are rolling out in waves; anything not ready at launch follows shortly after. If a specific question doesn't return data yet, it's likely a capability that's still rolling out.
Complex multi-step queries may need rephrasing. If you don't get the answer you expect, try breaking the question into smaller parts.
What's coming next
The Userflow MCP is rolling out in phases:
At launch — API access (read-only). Connect from Claude, ChatGPT, and other MCP-capable AI tools using a Userflow API key. Available to account owners and admins.
Shortly after — OAuth sign-in. One-step sign-in replaces API keys, and the MCP becomes available to everyone on your team.
Later — native connector listings. One-click connection in Claude, ChatGPT, and other AI platforms, with no custom MCP setup required.
Later — actions in your Userflow account. Publish flows, create segments, update users, manage team members, and more — all from your AI tool.
Need help?
If you run into trouble connecting or have questions about what the MCP can answer, reach out to your Userflow contact or post in the in-app help.