App

Optimizely integrations

Connect Optimizely to any other app, or use it from your AI client over MCP. The Optimizely platform technology provides A/B testing tools, in which two versions of a web page can be compared for performance, and multivariate testing.

Connects with an API keyoptimizely.com
26 actions

What the catalog holds today. Ask for anything missing and your agent reads the API documentation and adds it.

Build solutions, not workarounds.

What do you want to automate with Optimizely?

Ask the assistant

You'll sign in before anything runs. What you typed comes with you.

Connect your AI client

Give your AI client this address.

https://mcp.apiant.ai

One connection does both: ask your client to act in an app once, or have it build an automation that keeps running. Any client that takes a remote MCP server. Nothing to install. Create your free account, then sign in once in your browser.

Set it up in your client
Claude Code

Run this in the directory you want to work in.

claude mcp add --transport http -s project apiant-ai https://mcp.apiant.ai

Start Claude Code there, approve the server, and sign in in the browser page it opens.

Claude Code guide (opens in a new tab)
Claude, web and desktop

Open Customize, then Connectors, then Add custom connector, and paste the address. On Team and Enterprise an owner adds it first.

Setup guide (opens in a new tab)
Cursor

Add the address to your MCP configuration as a server URL. Cursor signs you in in your browser.

Setup guide (opens in a new tab)
Zed

Open Settings, then AI, then MCP Servers, then Add Server, then Add Remote Server.

Setup guide (opens in a new tab)
Codex and the ChatGPT desktop app

Open Settings, then MCP servers, then Add server, and choose Streamable HTTP. From the terminal, Codex takes the address with its own add command and then signs you in.

Setup guide (opens in a new tab)
Any other MCP client

Paste the address where the client asks for a remote MCP server URL, and name the server apiant-ai where it lets you. APIANT's skills reach the client over the same connection.

Setup guide (opens in a new tab)

Popular

Optimizely with the apps people pair it with most

Pair it

Connect Optimizely with another app

What your agent can do with Optimizely

Triggers and actions 26 actions

  • Action
    Add attribute

    Creates a new attribute in an Optimizely project, which can be used to target audiences.

  • Action
    Add audience

    Adds a new audience to an Optimizely project and returns the id of the audience that was created.

  • Action
    Add campaign

    Creates a new personalization campaign in an Optimizely project and returns its id.

  • Action
    Add experiment

    Creates a new experiment in an Optimizely project and returns its id.

  • Action
    Add feature

    Creates a new feature flag in an Optimizely project. Works only with legacy Full Stack projects, and returns the id of the new feature.

  • Action
    Add page

    Creates a new page in an Optimizely project, defining the URL where experiments and campaigns can run and when it activates. Returns the created page.

  • Action
    Add project

    Creates a new Optimizely project in your account and returns the created project.

  • Action
    Delete experiment

    Archives an Optimizely experiment by its ID. Optimizely keeps archived experiments rather than permanently removing them.

  • Action
    Get audience

    Returns a single Optimizely audience by its ID, including its name, targeting conditions and status. An error occurs if the audience is not found.

  • Action
    Get campaign

    Returns a single Optimizely campaign by its ID, including its status, metrics, targeting and custom field values.

  • Action
    Get experiment

    Returns a single experiment by its ID, including its status, variations, metrics and targeting. Fails if the experiment is not found.

  • Action
    Get experiment results

    Returns the results of an Optimizely experiment, including metric performance per variation, reach and statistical significance, optionally limited to a time range or visitor segment.

  • Action
    Get feature

    Returns a single feature by its ID, including its variables and its rollout rules in each environment. Works only with legacy Full Stack projects.

  • Action
    Get project

    Returns all the properties of a single Optimizely project, including its platform, status and web snippet settings.

  • Action
    List attributes

    Returns all attributes in an Optimizely project, including their keys, names and archived status.

  • Action
    List audiences

    Returns the audiences in an Optimizely project, optionally filtered by archived or journey status.

  • Action
    List campaigns

    Returns all campaigns in an Optimizely project, optionally narrowed by journey or archived status.

  • Action
    List environments

    Returns all of the environments that have been created in an Optimizely project.

  • Action
    List events

    Returns all events in an Optimizely project, including pageview events and, optionally, classic goals.

  • Action
    List experiments

    Returns all experiments in an Optimizely project or campaign.

  • Action
    List features

    Returns all features created in an Optimizely project, including their variables and per-environment rollout rules.

  • Action
    List pages

    Returns the pages defined in an Optimizely project, optionally including single-use pages generated for campaign URL targeting.

  • Action
    List projects

    Returns all the projects in your Optimizely account, with their settings and status.

  • Action
    Update campaign

    Updates an existing Optimizely campaign's details, targeting and metrics, and can publish, start, pause, resume or unarchive it. Returns the updated campaign.

  • Action
    Update experiment

    Updates an Optimizely experiment's settings, such as its name, audiences, metrics, variations and schedule, and can optionally publish, start, pause, resume or unarchive it. Returns the updated experiment.

  • Action
    Update feature

    Updates an existing feature's name, key, description, variables, environment rollout rules or archived state, and returns the updated feature.

Reviews

What our customers say

Questions

Optimizely, answered

Is there a Optimizely MCP server?

APIANT's MCP server at https://mcp.apiant.ai works with Optimizely. Add that address to any AI client that takes a remote MCP server and sign in once in your browser. Your client can then run Optimizely actions on demand, or have APIANT build, test and run automations that use Optimizely. Nothing to install.

What can your agent do in Optimizely?

Any of Optimizely's 26 actions, including Update campaign, Update experiment, Update feature and Add attribute. Your agent maps the data both ways and tests every scenario before it ships.

Can I use Optimizely directly from Claude, ChatGPT or Cursor?

Yes. Connect your AI client to APIANT once and it works with Optimizely two ways. Ask it to do something in Optimizely once and it runs that action on the spot. Ask for an automation and your agent builds it, tests every scenario and keeps it running on its own. A one-off action uses your plan's tasks the same way an automation step does.

Do I need to write code against the Optimizely API?

No. APIANT connects to the Optimizely API for you, with your Optimizely API key. Describe what you want in plain language and your agent builds it on the Optimizely triggers and actions in the catalog. If you need an endpoint that is not there yet, your agent reads the Optimizely API documentation and adds it.

Which apps can Optimizely connect to?

Any app in the catalog; the list on this page pairs Optimizely with each of them. If the other app is missing, point your agent at its API documentation and it builds the connector.

What happens when something fails?

Your agent works that out for you. It plans the failure paths along with the happy path, then tests every scenario before it ships.

Is there a free plan?

Yes. Every plan includes the agent, including free, and building from your own AI client spends no assistant credits.