Integration
Connect Cursor to Optimizely
When Agent Pull Request Created fires in Cursor, your agent runs Add page in Optimizely. Describe the whole flow and it is built, tested on every scenario and kept running.
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 Cursor and Optimizely to do together?
Ask the assistant
Connect your AI client
Give your AI client this address.
https://mcp.apiant.aiOne 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.aiStart 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)Example flows
What Cursor can start in Optimizely
When Agent Pull Request Created in Cursor
then Add page in Optimizely
Starting points drawn from the triggers and actions in the catalog today. Describe the flow you need, at any depth, and your agent builds it and tests every scenario before it ships.
Everything your agent can do with Cursor and Optimizely
Triggers and actions 3 triggers · 37 actions
- Agent Pull Request Created
Triggers when the selected Cursor cloud agent opens a new GitHub pull request.
- Agent Status Equals
Triggers when a run on the chosen Cursor agent reaches the status you select, such as Finished or Error.
- New Agent
Triggered when a new Cursor cloud agent is created.
- Add Followup Instruction to Agent
Sends a follow-up instruction to an existing Cursor cloud agent, either starting a new run or steering the run in progress. Returns the new run or how the steer was delivered.
- Cancel run
Cancels the active run of a Cursor cloud agent. The run ends in the Cancelled state; start a new run to continue the conversation.
- Delete Agent
Permanently deletes a Cursor cloud agent. This cannot be undone. Returns the ID of the deleted agent.
- Find Agent Status
Looks up a Cursor cloud agent by its ID and returns its status, name, repositories, latest run and link.
- Get run
Returns the status, timestamps, duration, final reply and pushed branches for one run of a Cursor cloud agent.
- Launch Agent
Creates a Cursor cloud agent and immediately starts its first run on the task you describe. Returns the new agent and its run.
- List agents
Returns the Cursor cloud agents for the connected user, newest first, optionally filtered by pull request URL.
- List artifacts
Returns the files a Cursor cloud agent has produced, with each file's path, size and last modified time. Returns at most 100 artifacts.
- List models
Returns the recommended Cursor models you can choose from when creating an agent, including their names, aliases, parameters and variants.
- List repositories
Returns the GitHub repositories the connected Cursor user can access through Cursor's GitHub App installation.
- List runs
Returns the runs of a Cursor cloud agent, newest first, including each run's status, duration, and final reply.
- Add attribute
Creates a new attribute in an Optimizely project, which can be used to target audiences.
- Add audience
Adds a new audience to an Optimizely project and returns the id of the audience that was created.
- Add campaign
Creates a new personalization campaign in an Optimizely project and returns its id.
- Add experiment
Creates a new experiment in an Optimizely project and returns its id.
- 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.
- 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.
- Add project
Creates a new Optimizely project in your account and returns the created project.
- Delete experiment
Archives an Optimizely experiment by its ID. Optimizely keeps archived experiments rather than permanently removing them.
- 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.
- Get campaign
Returns a single Optimizely campaign by its ID, including its status, metrics, targeting and custom field values.
- Get experiment
Returns a single experiment by its ID, including its status, variations, metrics and targeting. Fails if the experiment is not found.
- 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.
- 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.
- Get project
Returns all the properties of a single Optimizely project, including its platform, status and web snippet settings.
- List attributes
Returns all attributes in an Optimizely project, including their keys, names and archived status.
- List audiences
Returns the audiences in an Optimizely project, optionally filtered by archived or journey status.
- List campaigns
Returns all campaigns in an Optimizely project, optionally narrowed by journey or archived status.
- List environments
Returns all of the environments that have been created in an Optimizely project.
- List events
Returns all events in an Optimizely project, including pageview events and, optionally, classic goals.
- List experiments
Returns all experiments in an Optimizely project or campaign.
- List features
Returns all features created in an Optimizely project, including their variables and per-environment rollout rules.
- List pages
Returns the pages defined in an Optimizely project, optionally including single-use pages generated for campaign URL targeting.
- List projects
Returns all the projects in your Optimizely account, with their settings and status.
- 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.
- 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.
- Update feature
Updates an existing feature's name, key, description, variables, environment rollout rules or archived state, and returns the updated feature.
No trigger or action matches that. Ask your agent to add it: it reads the API documentation and builds what you describe.
Each app on its own
Reviews
What our customers say
More from Cursor
Cursor to HubSpotHubSpot is your all-in-one stop for all of your marketing software needs.
Cursor to SalesforceSalesforce is a leading enterprise customer relationship management (CRM) platform.
Cursor to SlackSlack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...
Cursor to Google SheetsGoogle Sheets is Google's online spreadsheet app for creating, editing and sharing spreadsheets.
Cursor to GmailGmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...
Cursor to Google CalendarGoogle Calendar is a time management tool providing scheduling features, event reminders, and integration...
More into Optimizely
Questions
Cursor and Optimizely, answered
What can start an automation from Cursor?
Any of Cursor's 3 triggers in the catalog, including Agent Pull Request Created, New Agent and Agent Status Equals. Describe the moment in plain language and your agent picks the right one.
What can your agent do in Optimizely when something happens in Cursor?
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 it also run from Optimizely to Cursor?
Optimizely has no triggers in the catalog today, so automations start in Cursor. If you need the other direction, ask: your agent reads Optimizely's API documentation and adds it.
Do I have to build a connector for Cursor or Optimizely?
No. Both are in the catalog with their triggers and actions. You describe the automation; your agent builds it, tests every scenario and keeps it running.
Can my AI client use Cursor and Optimizely without building an automation?
Yes. With your AI client connected to APIANT, ask it to do something in either app 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. One connection covers both.
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.