--- title: "MCP write tools: create flows, segments, and charts from your AI tool" slug: "mcp-write-tools" updated: 2026-11-13T16:29:34Z published: 2026-11-13T16:29:34Z canonical: "help.userflow.com/mcp-write-tools" --- > ## Documentation Index > Fetch the complete documentation index at: https://help.userflow.com/llms.txt > Use this file to discover all available pages before exploring further. # MCP write tools: create flows, segments, and charts from your AI tool MCP write tools let Claude, ChatGPT, and other AI tools connected through the Userflow MCP create things in your Userflow account: flows, segments, charts, and dashboards. Flows come back as unpublished drafts, and nothing is published until you confirm it. If you haven't connected the Userflow MCP yet, start with [Connect Userflow to Claude, ChatGPT, and other AI tools with the Userflow MCP](https://help.userflow.com/docs/mcp). If you're already connected, the write tools are there already. There's nothing to reconnect or reconfigure. For the background on why writes work this way, see [Introducing MCP Write Tools](https://www.userflow.com/blog/blog-introducing-mcp-write-tools?utm_source=help.userflow.com&utm_medium=referral&utm_campaign=mcp-write-tools&utm_content=kb-mcp-write-tools) on the blog. ## How MCP write tools create drafts Every MCP write follows the same shape: you describe what you want, and your AI tool builds it and hands back a link so you can open it in Userflow and check it. For flows, what comes back is an unpublished draft. It isn't live, and nobody in your product sees it until you publish it. Publishing is its own separate step that asks for your confirmation every time—it's never bundled into the instruction that created the draft. Segments, charts, and dashboards work a little differently, because they don't have a draft state in Userflow. When your AI tool creates one, it exists in your account right away, the same as if you'd built it in the app yourself. Nothing about that reaches your end users on its own—a segment doesn't show anyone anything until a live flow targets it—but it's worth knowing the difference. ## What you can create with MCP write tools ### Flows, guides, and campaigns Describe a tour, tooltip, modal, announcement, or banner and your AI tool creates it as an unpublished draft, with its content and audience built from what you asked for. Surveys and NPS work the same way, created as flows with question steps. Checklists, launchers, and resource centers are created as an unpublished draft too, with their name, theme, audience, and start settings. You add their content in the Builder, including the element a launcher attaches to. When a step needs to point at something on the page that's easier to click than to describe, your AI tool starts a Smartflow Builder draft instead and gives you a link to finish it by clicking through your own app. You can also duplicate an existing flow into a new draft, which is a quick way to start a variant without rebuilding it. ### Segments Describe who you're targeting in plain language—"companies on the free plan who haven't upgraded after 14 days," "users who saw the onboarding flow but didn't complete it"—and get a real user or company segment built from Userflow's condition logic. You can reuse it in the same conversation to target an announcement, a banner, or a chart. ### Charts and dashboards Ask an analytical question and get a usage or funnel chart back, with the metrics, time period, and filters set up for you. Group related charts into a dashboard the same way. ## Publishing a flow through the Userflow MCP Publishing and unpublishing a flow is a separate tool from creating or editing one. That's deliberate: it's the one write action that reaches your end users directly, so it always asks for its own explicit yes. In practice this means a two-step exchange. You ask your AI tool to publish a flow, it comes back describing exactly what it's about to publish, and you confirm. If you'd rather publish from the Userflow app after reviewing the draft, that works too—the draft is a normal flow draft, and nothing about it is specific to the MCP. ## Who can use MCP write tools MCP write tools run under your own Userflow permissions, using the same sign-in and role-based access as the rest of the product. If you can't publish a flow inside Userflow, your AI tool can't publish it for you either. Every write is attributed to the teammate who triggered it. Nothing happens anonymously, and nothing crosses between accounts. Because permissions come from your Userflow role, the way to change what someone can do through the MCP is to change their role in Userflow itself (see [Managing Teams in Userflow](https://help.userflow.com/docs/team-management)), or to revoke their connection. The steps to revoke are in [Managing your connections](https://help.userflow.com/docs/mcp#managing-your-connections). ## Turn MCP write tools on or off Your AI platform controls which Userflow MCP tools it can call, not Userflow. In most tools you can open the connector's settings and switch individual tools on or off, or set them to ask you before running. To keep the Userflow MCP read-only, turn the write tools off there and leave the read tools on. ## What write tools can't do yet ### Can my AI tool add images? Only from a public URL. The write tools can't upload an image file from your AI tool, so an image you attached or created in the conversation won't come through. Give your AI tool a public image URL instead, or add the image in the Userflow builder after the draft is created. ### Can the MCP select page elements for me? No. The MCP can't pick elements on your page by itself, even if you describe them clearly. When a step needs to point at an element, your AI tool gives you a link to finish the draft in the Builder, and you select the element there. This includes elements inside nested Shadow DOM. Selecting them by hand in the Builder works as usual. ### Can my AI tool build a checklist, launcher, or resource center? Partly. Your AI tool can create the draft and set its name, theme, audience, and start settings. It can't add the content yet: checklist tasks, the launcher's icon, beacon, or tooltip, or the items in a resource center. Open the draft from the link your AI tool gives you and add the content in the Builder. For a launcher, that's also where you pick the element it attaches to. ## Using MCP write tools safely ### Editing a segment that's already in use A flow draft is versioned—when you edit one, the previous version is kept and you can get back to it from the Builder's version history. A segment isn't. If you ask your AI tool to change a segment's conditions, the change applies immediately, including to anything already using that segment. Before changing a segment, it's worth asking what's currently targeting it. Creating a new segment is often safer than editing an existing one. ### Making a lot of changes at once A single open-ended instruction to change many things at once isn't a good use of these tools yet. Your AI tool carries out that kind of request as a long series of individual actions, and it's hard to review. If you need to make the same change across many flows, break it into small batches, name the specific flows, and confirm each batch. If it's something you do regularly, a purpose-built skill is a better fit than a freeform prompt—talk to your Userflow contact. ## Example prompts for MCP write tools - "Which users signed up in the last 30 days and haven't finished onboarding? Create a segment for them, then draft an announcement about our new onboarding flow targeted to it." - "Show me the drop-off point in our Setup flow, then update that step to skip SSO users." - "Build a funnel chart for activation over the last 30 days and add it to my activation dashboard." - "Duplicate the Welcome Tour and call it Welcome Tour — Enterprise." - "Create an NPS survey for companies who've been customers for more than six months." For more ideas, see [7 Ways to Put Userflow MCP Write Tools to Work This Week](https://www.userflow.com/blog/mcp-write-tools-use-cases?utm_source=help.userflow.com&utm_medium=referral&utm_campaign=mcp-write-tools&utm_content=kb-example-prompts) on the blog. ## Common questions about MCP write tools ### Will my AI tool publish something without me approving it? No. Creating or editing a flow with MCP write tools always produces a draft. Publishing is a separate action that needs its own confirmation every time. ### Do I need to reconnect to use MCP write tools? No. MCP write tools appear inside your existing Userflow MCP connection. ### Who gets credited for something built through my AI tool? You do. Every MCP write runs under your own Userflow permissions and is attributed to you. ### Can I keep using the Userflow MCP read-only? Yes. Turn the write tools off in your AI platform's connector settings. ### Do MCP write tools use up my AI platform's credits or tokens? That's determined by your AI platform, not Userflow. From Userflow's side an MCP call looks like any other API call. To cap how much a job uses, set that in your AI tool. ### What happens if I hit Userflow's API rate limit partway through? You'll get a message telling you the limit was reached and, where possible, when the action can be retried. ### Can I change many trackers or flows at once? Userflow doesn't have a bulk edit in the dashboard. To make the same change to many trackers, flows or other content, ask your AI tool to do it with MCP write tools. For example, to stop counting your own team's usage in every tracker: "For every tracker in my Userflow account, add an audience rule that excludes users whose email contains 'yourcompany'. Keep any existing audience rules. Start with one tracker so I can check it, then do the rest and publish them." Before you run a change like this: - **Ask it to keep existing audience rules.** Some trackers may already have conditions, and those should stay in place. - **Check the first one before it changes the rest.** Open it in Userflow and make sure the rule is what you wanted. - **An audience rule only affects new tracking.** Usage already recorded stays in your reports. ### Can I use MCP write tools to delete things in bulk? It isn't a good fit for an open-ended chat instruction. Anything that can't be undone is safer done in small, named batches you can check as you go, or through a skill built for it. ## Still need help with MCP write tools? If something you built through your AI tool doesn't look right, or a write doesn't behave the way this article describes, reach out to your Userflow contact or post in the in-app help. ## Related articles - [Connect Userflow to Claude, ChatGPT, and other AI tools with the Userflow MCP](https://help.userflow.com/docs/mcp) - [AI Skills Library](https://help.userflow.com/docs/ai-skills-library): skills that build segments, banners, and announcements through the Userflow MCP - [Managing Teams in Userflow](https://help.userflow.com/docs/team-management)