How to Use the Formbricks MCP in Claude Code
Claude Code automates Formbricks surveys and response extraction directly from your terminal.
Works with every AI agent you already use
…and any MCP-compatible client
Connect Formbricks MCP to Claude Code
Create your Vinkius account to connect Formbricks to Claude Code and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.
Terminal-Driven Survey Deployment
Running `create_survey` through the Claude Code MCP Server integration lets you spin up new user prompts as part of your deployment scripts. You just pipe a JSON schema into the terminal, and Claude executes the command to push the survey live. It fits perfectly into a CI/CD pipeline where a new feature release automatically triggers a feedback module. If a release rolls back, Claude Code hits `delete_survey` to instantly pull the associated prompt. You can also run `list_surveys` to audit your active modules or use `get_survey` to dump a specific configuration to standard output. It strips away the GUI and gives you raw command-line control.
Formbricks MCP Server Data Pipelines
Invoking `list_responses` allows Claude Code to pull batch feedback data and pipe it into your analytics scripts. A cron job can wake up, grab the last 24 hours of responses, filter by survey ID, and push the results to your data warehouse. You get automated insight extraction without touching a dashboard. When a specific submission triggers an alert, Claude calls `get_response` to fetch the exact payload. It can also run `list_people` and `get_person` to append user identity details to your log files. This gives your DevOps team immediate context when users complain about a broken feature.
Audit Actions and Webhooks
Calling `list_action_classes` lets Claude Code verify that your application's trigger events match your infrastructure state. If a deployment changes a button ID, Claude checks the action classes to ensure your surveys will still fire. It prevents silent failures in your feedback loops. To keep your event routing healthy, Claude executes `list_webhooks`. It audits your active MCP endpoints from the terminal, ensuring Formbricks actually sends data to your consumer services. If a webhook drops, you can script Claude to alert your Slack channel immediately.
Set up Formbricks MCP in Claude Code
Prerequisites
- Claude Code CLI installed (
npm install -g @anthropic-ai/claude-code) - Active Vinkius subscription with a valid endpoint token
- 1
Run the add command
Open your terminal and run the command shown on the right. Replace
[YOUR_TOKEN_HERE]with your endpoint token from cloud.vinkius.com. Use--scope userto make it available across all projects. - 2
Verify the connection
Start a Claude Code session and type
/mcpto list connected servers. You should seeformbricks-alternative-mcpwith a green status indicator. - 3
Start using tools
Ask Claude Code something like "Check my latest Formbricks transactions." It will automatically discover and invoke the available Formbricks tools.
claude mcp add --transport http formbricks-alternative-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Why Choose Vinkius
Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.
Real-time monitoring
Live
visibility into every interaction
Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.
Built-in savings
60%
lower AI costs
Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.
Single dashboard
One
place for every integration
Every tool your AI connects to, managed from a single screen. One account, complete control.
Common questions about Formbricks MCP in Claude Code
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
Start using the Formbricks MCP today
We host it, we monitor it, we maintain it. You just paste one token.