# Optimizely MCP for AI Agents AI Agent Connect > Optimizely MCP lets you manage A/B tests and feature flags directly through your AI agent. Instead of clicking through the Optimizely dashboard to check experiment statuses or toggle features, you can just ask your agent to do it. It handles listing projects, tracking live experiments, and auditing audience definitions to keep your growth workflows moving without the constant tab switching. ## Overview - **Category:** data-analytics - **Price:** Free - **Endpoint:** https://edge.vinkius.com/vk_preview_bvFb0C3kWGnKUOKniHIrp2EkQUMOnHphRVl70b9H/ai-agent-connect - **Tags:** ab-testing, feature-flags, experimentation, digital-experience, product-analytics ## Description Stop jumping between browser tabs just to see if a feature flag is live or if a specific experiment is still running. This Connector lets you talk to your Optimizely account as if it were a shared teammate. You can ask your agent to pull a summary of all active projects or dig into the specific configuration of a conversion event without ever opening the dashboard. It's built for people who need to move fast and want to keep their focus on the strategy rather than the manual clicking. By connecting this through Vinkius, you get a direct line to your experimentation data. You can audit your audience targeting, check the metadata for your latest tests, and even push live updates like starting or pausing an experiment on the fly. It turns a manual, multi-click process into a simple conversation, making it much easier to keep your product's growth engine running smoothly. Instead of digging through nested menus to find a specific flag, you just ask for it and get the answer immediately. This helps you stay in your flow while keeping your production environment stable and your growth targets on track. You can also verify that your conversion events are correctly mapped across different projects, ensuring your data remains clean and your reporting stays accurate. ## Tools ### list_feature_flags List every feature flag associated with a project. Use this to see what's currently toggled. ### get_experiment Get specific details for a single experiment. Use this to check the exact configuration of a test. ### get_feature_flag Pull the definition and status of a specific feature flag. This helps you verify if a flag is active. ### get_project Retrieve detailed metadata for a specific Optimizely project. Use it to see project-level settings. ### list_audiences Show all defined audiences within a specific project. This is useful for auditing your targeting rules. ### list_events List all conversion events tied to a project. Use this to verify your tracking setup. ### list_experiments Show all experiments currently in a project. This gives you a quick overview of your active tests. ### list_projects Show a complete list of all Optimizely projects in your account. This helps you see your whole workspace. ### pause_experiment Set an experiment's status to paused immediately. Use this to stop a test if you notice an issue. ### start_experiment Set an experiment's status to running. This lets you launch a test through a simple command. ## Prompt Examples **Prompt:** ``` List all Optimizely projects in my account. ``` **Response:** ``` I've retrieved 4 projects: **Main Website**, **Mobile App iOS**, **Checkout Flow**, and **New Product Beta**. Which one would you like to explore? ``` **Prompt:** ``` Check the status of all experiments in project 12345. ``` **Response:** ``` There are 5 experiments in project 12345: * **Hero Banner v2**: Running * **Free Shipping Prompt**: Running * **Summer Sale**: Paused * **Login Redirect**: Paused * **New Checkout**: Draft ``` **Prompt:** ``` Pause experiment 67890 in project 12345. ``` **Response:** ``` Experiment 67890 (**Hero Banner v2**) has been successfully paused. ``` ## Capabilities ### List active projects See your entire workspace of projects in one conversation. ### Check experiment status Find out which tests are running, paused, or in draft mode. ### Toggle experiment states Start or pause experiments with a single command. ### Audit feature flags Inspect the definitions and statuses of flags across your projects. ### Verify audience targeting List defined audiences and conversion events to check your setup. ### Retrieve experiment metadata Get the full configuration details for any specific experiment. ## Use Cases ### Emergency test shutdown A growth engineer notices a bug in a live test and asks the agent to use pause_experiment to stop the test immediately. ### Feature flag audit A PM wants to ensure a new feature flag is correctly scoped and uses get_feature_flag to check the definition before a release. ### New team onboarding A new team member joins and asks the agent to list_projects to see the history of experiments and projects in the account. ### Data verification A data scientist uses list_events to confirm that all required conversion triggers are active for a new campaign. ## Benefits - Stop clicking through nested menus by using list_projects to see your entire workspace in one view. - React faster to production issues by using pause_experiment to stop a failing test instantly. - Verify your tracking setup quickly by using list_events to see all conversion triggers in a project. - Audit your audience targeting without opening a browser by using list_audiences to check definitions. - Ensure feature flags are configured correctly by using get_feature_flag to pull definitions on the fly. - Get a clear picture of your testing roadmap by using list_experiments to see what's running or paused. ## How It Works The bottom line is you get instant, conversational control over your experimentation and feature management. 1. Subscribe to this Connector on the Vinkius Marketplace. 2. Enter your Optimizely Personal Access Token in your agent's configuration. 3. Start managing your experiments from Claude, Cursor, or any Connector client. ## Frequently Asked Questions **How can the Optimizely MCP help my growth team?** It gives your team a way to check experiment statuses and toggle features using natural language. This means you can get answers faster without constantly switching between your AI client and the Optimizely dashboard. **Can I use the Optimizely MCP to stop a live test?** Yes, you can ask your agent to pause an experiment immediately. This is helpful for quickly responding to issues during a live rollout. **Does the Optimizely MCP show me my audience targeting?** Yes, you can use the Connector to list the defined audiences in any project. This helps you verify your targeting rules quickly. **How do I connect Optimizely to my AI agent?** You just need to subscribe to the Connector on Vinkius and add your Optimizely Personal Access Token to your agent's configuration. **Can the Optimizely MCP list all my active projects?** Yes, your agent can pull a full list of all projects in your account so you can see your entire workspace at a glance. **Will the Optimizely MCP help me audit feature flags?** Absolutely. You can ask your agent to pull the definitions and statuses of flags across different projects to ensure everything is set up correctly. **Where do I find my Personal Access Token?** In Optimizely, go to **Profile Settings** > **API Access** and generate a new Personal Access Token. Ensure it has the necessary permissions for the projects you want to manage. **Can I start an experiment that is in draft mode?** Yes, using the `start_experiment` tool will attempt to set the status to 'running'. However, Optimizely requires the experiment to be valid and fully configured before it can transition from draft to running. **How do I find my Project ID?** You can use the `list_projects` tool to see all projects associated with your account along with their IDs. You can also find it in the URL when viewing a project in the Optimizely dashboard.