--- title: "Optimizely Web Experimentation MCP server - actionlake" description: "Give Claude 101 Optimizely Web Experimentation actions through one MCP server: events. Your agent never holds the credential. 100,000 calls a month free." canonical: https://actionlake.com/connectors/optimizely-web-experimentation updated: 2026-10-23 --- Connectors · Marketing & media # Optimizely Web Experimentation MCP server for AI agents. actionlake is an MCP gateway: one remote MCP server that connects Claude and other MCP clients to Optimizely Web Experimentation and the rest of your systems. It gives your agent 101 Optimizely Web Experimentation actions (53 reads, 34 writes and 14 that wait for a confirmation) and holds the Optimizely Web Experimentation credential itself, so the agent never does. It paces Optimizely Web Experimentation's limits and records every call. [Connect Optimizely Web Experimentation free](https://actionlake.com/console?start=sandbox) [See pricing](https://actionlake.com/pricing) 100,000 free calls a month. No card, no email, no password: press Start a free sandbox on the next screen and keep the key it shows you. `claude mcp add --transport http actionlake https://connect.actionlake.com/mcp` the first call ``` do { action: "optimizely_web_experimentation.projects.list_projects", intent: "check which Optimizely Web Experimentation account is connected" } # List Projects · read · 1 upstream call ``` - 101 actions in one signed file - 53 read look, never change - 34 write create and update - 14 wait for a yes destructive, confirmed first Set up ## Connect Optimizely Web Experimentation in three steps. 1. 01 ### Add actionlake to Claude. Run the command once in Claude Code; its consent page can create a free sandbox: 100,000 calls a month, no card. In the Claude app, add a custom connector with the URL below and paste your key on the consent page. Creating a new sandbox from the Claude app is not yet tested by us. `https://connect.actionlake.com/mcp` 2. 02 ### Connect Optimizely Web Experimentation. Bearer token. No consent screen: your agent can connect it for you, but the key then passes through your chat. To keep it out of the model's context, paste it in the console instead. actionlake stores what you paste write-only, sealed under your tenant's key. - `access_token` Optimizely personal access token (Profile > API Access > Generate New Token in app.optimizely.com), or an OAuth 2.0… ``` account { op: "connections.requirements", service: "optimizely_web_experimentation" } # free: exactly what to paste, and what is found for you ``` 3. 03 ### Make the first call. Check before a write. Ask in plain words; Claude picks the action. Before anything changes, `check` validates the call and prices it, for free. ``` do { action: "optimizely_web_experimentation.projects.list_projects" } # list projects · read · 1 upstream call check { action: "optimizely_web_experimentation.projects.create_project", input: { … } } # free: inputs, permissions, cost and confirmations, nothing sent ``` Optimizely Web Experimentation at a glance **Sign-in** Bearer token. No consent screen: your agent can connect it for you, but the key then passes through your chat. To keep it out of the model's context, paste it in the console instead. **You provide** `access_token` **Limits we pace to** 100 calls a minute, per connection **API covered** Optimizely REST API v2 (OpenAPI 3, Optimizely API 2.0)`api.optimizely.com` **Built from** Optimizely Web Experimentation's documentation, read 23 October 2026[archbee-doc-uploads.s3.amazonaws.com](https://archbee-doc-uploads.s3.amazonaws.com/BrbvVORKJ5iIeSMZye5kI/nULr2kHf4eeqXNFeEz3kr-20261022-175930.json) [docs.developers.optimizely.com](https://docs.developers.optimizely.com/web-experimentation/reference) **Service file** Version 1.0.0, signed (Ed25519) **Cached reads** 51 of 53 reads, for up to 5 minutes; a write clears what it affects **Shared entities** 2, so ask can line Optimizely Web Experimentation up with your other systems **Data** Processed and stored in Sydney, Australia. No US region yet Capabilities ## What an AI agent can do in Optimizely Web Experimentation. 101 actions in 27 areas. Every one carries its effect, so a key can allow the reads and hold the rest. - **53** read look, never change - **34** write create and update - **14** destructive wait for a confirmation 1. ### Events 8 2 read · 4 write · 2 destructive Create a Custom Event · List all Events · Get Event by ID · Archive a Custom Event 2. ### Experiments 8 5 read · 2 write · 1 destructive Create an Experiment · List Experiments · Read an Experiment · Update an Experiment 3. ### Campaigns 7 4 read · 2 write · 1 destructive Create a Campaign · List Campaigns · Read a Campaign · Get Campaign results 4. ### Environments 6 3 read · 2 write · 1 destructive Get Environments by Project · Create an Environment · Read an Environment · Update an Environment 5. ### Attributes 5 2 read · 2 write · 1 destructive Create an Attribute · List Attributes · Read an Attribute · Archive an Attribute 6. ### Extensions 5 2 read · 2 write · 1 destructive Create an Extension · List Extensions · Get an Extension · Archive an Extension 7. ### Features 5 2 read · 2 write · 1 destructive Create a Feature · Get Features by Project · Read a Feature · Archive a Feature 8. ### Groups 5 2 read · 2 write · 1 destructive Create an Exclusion Group · List Exclusion Groups · Get an Exclusion Group · Archive an Exclusion Group **19 more areas · 52 actions** - List attributes **5** - Pages **5** - Scheduled jobs **5** - Sections **5** - Webhooks **5** - Audiences **4** - Projects **4** - Collaborators **3** - Subject access requests **3** - Change history **2** - Export credentials **2** - Impressions usage **2** - Attribution **1** - Custom fields **1** - Experiment summary **1** - Plan **1** - Reports **1** - Search **1** - User **1** Top actions ## The Optimizely Web Experimentation API, shaped for agents. The ids your agent types, what each does, and the one name it shares with other systems. 28 of Optimizely Web Experimentation's 28 action names are shared with at least one other connector, so an agent learns them once. | Action | What it does | Effect | Same name in | | --- | --- | --- | --- | | `optimizely_web_experimentation.projects.list_projects` List Projects | List Projects. | read | `work.project.list` 109 connectors | | `optimizely_web_experimentation.collaborators.list_collaborators` List Collaborators | List Collaborators. | read | `identity.user.list` 474 connectors | | `optimizely_web_experimentation.projects.create_project` Create a Project | Create a Project. | write | `work.project.create` 102 connectors | | `optimizely_web_experimentation.audiences.list_audiences` List Audiences | List Audiences. | read | `analytics.segment.list` 17 connectors | | `optimizely_web_experimentation.events.create_custom_event` Create a Custom Event | Create a Custom Event. | write | `analytics.tracked_event.create` 12 connectors | | `optimizely_web_experimentation.experiments.list_experiments` List Experiments | List Experiments. | read | `analytics.experiment.list` 12 connectors | | `optimizely_web_experimentation.experiments.create_experiment` Create an Experiment | Create an Experiment. | write | `analytics.experiment.create` 12 connectors | | `optimizely_web_experimentation.events.list_events` List all Events | List all Events. | read | `analytics.tracked_event.list` 10 connectors | | `optimizely_web_experimentation.audiences.create_audience` Create an Audience | Create an Audience. | write | `analytics.segment.create` 10 connectors | | `optimizely_web_experimentation.experiments.delete_experiment` Archive an Experiment | Archive an Experiment. | destructive | `analytics.experiment.delete` 10 connectors | | `optimizely_web_experimentation.webhooks.create_webhook` Create a Webhook | Create a Webhook. | write | `automation.webhook.create` 209 connectors | | `optimizely_web_experimentation.webhooks.list_webhooks` Get Webhooks by Project | Get Webhooks by Project. | read | `automation.webhook.list` 202 connectors | Try it ## Prompts to paste into Claude. Each one names the Optimizely Web Experimentation actions it will call, so you know what it reads and what it changes before you send it. 1. Read read Give me a one-line status for every active Optimizely Web Experimentation project. calls `optimizely_web_experimentation.projects.list_projects` 2. Write write Create a Project in Optimizely Web Experimentation. Show me exactly what you will send before you save it. calls `optimizely_web_experimentation.projects.create_project` Governance for Optimizely Web Experimentation ## Destructive actions wait for a yes. 14 Optimizely Web Experimentation actions are destructive. These are all of them: - Archive an Experiment `optimizely_web_experimentation.experiments.delete_experiment` - Archive a Custom Event `optimizely_web_experimentation.events.delete_custom_event` - Delete a Webhook `optimizely_web_experimentation.webhooks.delete_webhook` - Archived a Page `optimizely_web_experimentation.pages.delete_page` - Archive a Section by ID `optimizely_web_experimentation.sections.delete_section` - Archive a Campaign `optimizely_web_experimentation.campaigns.delete_campaign` - Archive an Attribute `optimizely_web_experimentation.attributes.delete_attribute` - Archive an In-Page Event `optimizely_web_experimentation.events.delete_in_page_event` - Archive an Extension `optimizely_web_experimentation.extensions.delete_extension` - Archive an Exclusion Group `optimizely_web_experimentation.groups.delete_group` - Archive a Feature `optimizely_web_experimentation.features.delete_feature` - Archive an Environment `optimizely_web_experimentation.environments.delete_environment` - Archive a Scheduled Job `optimizely_web_experimentation.scheduled_jobs.delete_scheduled_job` - Archive a List Attribute `optimizely_web_experimentation.list_attributes.archive_list_attribute` A destructive action runs only with `confirm: true`. Under the `human` policy the agent cannot confirm for itself: the run stops until a named person approves, in the console or from a signed link in an email. The cap on a key is refused before the call is sent, never after. do optimizely_web_experimentation.experiments.delete_experiment confirm_policy: **human** Archive an Experiment? **intent:** the user asked me to archive an Experiment run suspended · waiting for a named person · key _optimizely-web-experimentation-agent_ cannot confirm itself In the console, or from an emailed signed link. a key for this connector ``` account { op: "keys.create", name: "optimizely-web-experimentation-agent", allowed_actions: ["optimizely_web_experimentation.*"], cap_calls: 2000, confirm_policy: "human_for_writes", approval_rules: [ { match: "optimizely_web_experimentation.experiments.delete_experiment", approver: "lead@example.com" }, { match: "optimizely_web_experimentation.events.delete_custom_event", approver: "lead@example.com" }, { match: "optimizely_web_experimentation.webhooks.delete_webhook", approver: "lead@example.com" } ] } ``` Illustrative. Scoped to Optimizely Web Experimentation only, capped at 2,000 upstream calls, every write confirmed, and the destructive ones approved by a named person. Cost ## What Optimizely Web Experimentation costs on actionlake. Every Optimizely Web Experimentation action is one upstream call, the only thing actionlake bills. Searching, `check`, `cost`, `account` and any call Optimizely Web Experimentation refused with 401, 403, 429 or a 5xx are free. Paid plans start at US$49 a month for 250,000 calls, with overage from US$0.30 down to US$0.18 per 1,000. - 1 upstream call per action all 101 Optimizely Web Experimentation actions - 101 actions page each page of a long list is one call - 51 reads can be cached a cache hit costs nothing - 100,000 calls a month, free paid plans from US$49 a month for 250,000 [See pricing](https://actionlake.com/pricing) Action index ## Every Optimizely Web Experimentation action. 101 actions by area: the id your agent calls, what it does, and its effect. **Events 8** - `optimizely_web_experimentation.events.create_custom_event` Create a Custom Event write - `optimizely_web_experimentation.events.create_in_page_event` Create an In-Page Event write - `optimizely_web_experimentation.events.delete_custom_event` Archive a Custom Event destructive - `optimizely_web_experimentation.events.delete_in_page_event` Archive an In-Page Event destructive - `optimizely_web_experimentation.events.get_event` Get Event by ID read - `optimizely_web_experimentation.events.list_events` List all Events read - `optimizely_web_experimentation.events.update_custom_event` Update a Custom Event write - `optimizely_web_experimentation.events.update_in_page_event` Update an In-Page Event write **Experiments 8** - `optimizely_web_experimentation.experiments.create_experiment` Create an Experiment write - `optimizely_web_experimentation.experiments.delete_experiment` Archive an Experiment destructive - `optimizely_web_experimentation.experiments.get_experiment` Read an Experiment read - `optimizely_web_experimentation.experiments.get_experiment_results` Get Experiment results read - `optimizely_web_experimentation.experiments.get_experiment_results_share_link` Get a sharable link for the experiment's results page read - `optimizely_web_experimentation.experiments.get_experiment_timeseries` Get Experiment results time series read - `optimizely_web_experimentation.experiments.list_experiments` List Experiments read - `optimizely_web_experimentation.experiments.update_experiment` Update an Experiment write **Campaigns 7** - `optimizely_web_experimentation.campaigns.create_campaign` Create a Campaign write - `optimizely_web_experimentation.campaigns.delete_campaign` Archive a Campaign destructive - `optimizely_web_experimentation.campaigns.get_campaign` Read a Campaign read - `optimizely_web_experimentation.campaigns.get_campaign_results` Get Campaign results read - `optimizely_web_experimentation.campaigns.get_campaign_results_share_link` Get a sharable link for the campaign's results page read - `optimizely_web_experimentation.campaigns.list_campaigns` List Campaigns read - `optimizely_web_experimentation.campaigns.update_campaign` Update a Campaign write **Environments 6** - `optimizely_web_experimentation.environments.create_environment` Create an Environment write - `optimizely_web_experimentation.environments.delete_environment` Archive an Environment destructive - `optimizely_web_experimentation.environments.get_datafile` Read the datafile of an Environment read - `optimizely_web_experimentation.environments.get_environment` Read an Environment read - `optimizely_web_experimentation.environments.list_environments` Get Environments by Project read - `optimizely_web_experimentation.environments.update_environment` Update an Environment write **Attributes 5** - `optimizely_web_experimentation.attributes.create_attribute` Create an Attribute write - `optimizely_web_experimentation.attributes.delete_attribute` Archive an Attribute destructive - `optimizely_web_experimentation.attributes.get_attribute` Read an Attribute read - `optimizely_web_experimentation.attributes.list_attributes` List Attributes read - `optimizely_web_experimentation.attributes.update_attribute` Update an Attribute write **Extensions 5** - `optimizely_web_experimentation.extensions.create_extension` Create an Extension write - `optimizely_web_experimentation.extensions.delete_extension` Archive an Extension destructive - `optimizely_web_experimentation.extensions.get_extension` Get an Extension read - `optimizely_web_experimentation.extensions.list_extensions` List Extensions read - `optimizely_web_experimentation.extensions.update_extension` Update an Extension write **Features 5** - `optimizely_web_experimentation.features.create_feature` Create a Feature write - `optimizely_web_experimentation.features.delete_feature` Archive a Feature destructive - `optimizely_web_experimentation.features.get_feature` Read a Feature read - `optimizely_web_experimentation.features.list_features` Get Features by Project read - `optimizely_web_experimentation.features.update_feature` Update a Feature write **Groups 5** - `optimizely_web_experimentation.groups.create_group` Create an Exclusion Group write - `optimizely_web_experimentation.groups.delete_group` Archive an Exclusion Group destructive - `optimizely_web_experimentation.groups.get_group` Get an Exclusion Group read - `optimizely_web_experimentation.groups.list_groups` List Exclusion Groups read - `optimizely_web_experimentation.groups.update_group` Update an Exclusion Group write **List attributes 5** - `optimizely_web_experimentation.list_attributes.archive_list_attribute` Archive a List Attribute destructive - `optimizely_web_experimentation.list_attributes.create_list_attribute` Create a List Attribute write - `optimizely_web_experimentation.list_attributes.get_list_attribute` Read a List Attribute read - `optimizely_web_experimentation.list_attributes.list_list_attributes` Get list attributes by project read - `optimizely_web_experimentation.list_attributes.update_list_attribute` Update a List Attribute write **Pages 5** - `optimizely_web_experimentation.pages.create_page` Create a Page write - `optimizely_web_experimentation.pages.delete_page` Archived a Page destructive - `optimizely_web_experimentation.pages.get_page` Read a page read - `optimizely_web_experimentation.pages.list_pages` List Pages read - `optimizely_web_experimentation.pages.update_page` Update a Page write **Scheduled jobs 5** - `optimizely_web_experimentation.scheduled_jobs.create_scheduled_job` Create a Scheduled Job write - `optimizely_web_experimentation.scheduled_jobs.delete_scheduled_job` Archive a Scheduled Job destructive - `optimizely_web_experimentation.scheduled_jobs.get_scheduled_job` Get a Scheduled Job read - `optimizely_web_experimentation.scheduled_jobs.list_scheduled_jobs` Get a list of Scheduled Jobs read - `optimizely_web_experimentation.scheduled_jobs.update_scheduled_job` Update a Scheduled Job write **Sections 5** - `optimizely_web_experimentation.sections.create_section` Create a new Section in a Multivariate Test write - `optimizely_web_experimentation.sections.delete_section` Archive a Section by ID destructive - `optimizely_web_experimentation.sections.get_experiment_sections` Read all the Sections in a Multivariate Test read - `optimizely_web_experimentation.sections.get_section` Read a Section of a Multivariate Test read - `optimizely_web_experimentation.sections.update_section` Update a Section by ID write **Webhooks 5** - `optimizely_web_experimentation.webhooks.create_webhook` Create a Webhook write - `optimizely_web_experimentation.webhooks.delete_webhook` Delete a Webhook destructive - `optimizely_web_experimentation.webhooks.get_webhook` Read a Webhook read - `optimizely_web_experimentation.webhooks.list_webhooks` Get Webhooks by Project read - `optimizely_web_experimentation.webhooks.update_webhook` Update a Webhook write **Audiences 4** - `optimizely_web_experimentation.audiences.create_audience` Create an Audience write - `optimizely_web_experimentation.audiences.get_audience` Read an Audience read - `optimizely_web_experimentation.audiences.list_audiences` List Audiences read - `optimizely_web_experimentation.audiences.update_audience` Update an Audience write **Projects 4** - `optimizely_web_experimentation.projects.create_project` Create a Project write - `optimizely_web_experimentation.projects.get_project` Read a Project read - `optimizely_web_experimentation.projects.list_projects` List Projects read - `optimizely_web_experimentation.projects.update_project` Update a Project write **Collaborators 3** - `optimizely_web_experimentation.collaborators.create_collaborators` Invite Collaborators write - `optimizely_web_experimentation.collaborators.list_collaborators` List Collaborators read - `optimizely_web_experimentation.collaborators.list_invitations` List Collaborators who have not yet accepted the invitations read **Subject access requests 3** - `optimizely_web_experimentation.subject_access_requests.create_sar_request` Create a Subject Access Request write - `optimizely_web_experimentation.subject_access_requests.get_sar_request` Get Subject Access Request read - `optimizely_web_experimentation.subject_access_requests.list_sar_requests_by_account` List Subject Access Requests read **Change history 2** - `optimizely_web_experimentation.change_history.compare_revisions` Compare two revisions read - `optimizely_web_experimentation.change_history.list_change_history` Retrieve changes for a project read **Export credentials 2** - `optimizely_web_experimentation.export_credentials.get_enriched_events_export_credentials` Get AWS credentials to access experimentation events export data read - `optimizely_web_experimentation.export_credentials.get_gcp_e3_credentials` Get GCP credentials to access experimentation events export data read **Impressions usage 2** - `optimizely_web_experimentation.impressions_usage.get_impressions_usage_request` Get Impressions Usage read - `optimizely_web_experimentation.impressions_usage.get_impressions_usage_summary_request` Get Impressions Usage Summary read **Attribution 1** - `optimizely_web_experimentation.attribution.get_bucketing_history` Get bucketing information for a visitor read **Custom fields 1** - `optimizely_web_experimentation.custom_fields.get_custom_field` Read a Custom Field read **Experiment summary 1** - `optimizely_web_experimentation.experiment_summary.get_experiment_summaries` Summaries of Experiments and Campaigns read **Plan 1** - `optimizely_web_experimentation.plan.get_plan` Get Plan & Usage information for all products read **Reports 1** - `optimizely_web_experimentation.reports.get_experiment_report` Get Experiment Result's Report read **Search 1** - `optimizely_web_experimentation.search.get_search_results` Search read **User 1** - `optimizely_web_experimentation.user.get_me` Get current User information read Questions ## The Optimizely Web Experimentation MCP server, answered. **Is there an Optimizely Web Experimentation MCP server for Claude?** Yes. actionlake is an MCP gateway: a remote MCP server that gives Claude, or another MCP client, 101 Optimizely Web Experimentation actions across events, experiments, campaigns and environments, through the same eight tools it uses for every other connector. actionlake is independent; it is not made or endorsed by Optimizely Web Experimentation. **What do I need to connect Optimizely Web Experimentation?** Optimizely personal access token (Profile > API Access > Generate New Token in app.optimizely.com), or an OAuth 2.0…. The free call account { op: "connections.requirements", service: "optimizely_web_experimentation" } lists exactly what to paste. **Can an AI agent delete or change things in Optimizely Web Experimentation?** Only if its key allows it, and only with an explicit confirmation. 14 Optimizely Web Experimentation actions are destructive, including archive an Experiment, archive a Custom Event and delete a Webhook. Each runs only with confirm: true. Under the human confirm policy, or an approval rule on the key, the run waits until a named person approves it. **Will an AI agent use up my Optimizely Web Experimentation API limit?** actionlake paces every call to the limits in the Optimizely Web Experimentation service file: 100 calls a minute per connection. Repeated reads are answered from cache (51 Optimizely Web Experimentation actions can be), which never reaches Optimizely Web Experimentation. **What does an Optimizely Web Experimentation action cost?** One upstream call, the only unit actionlake bills. A list that pages bills one call per page (101 Optimizely Web Experimentation actions page). Cache hits, searches, dry runs and calls Optimizely Web Experimentation refused with 401, 403, 429 or a 5xx are free. The Free plan includes 100,000 calls a month with no card. Paid plans start at US$49 a month for 250,000 calls, with overage from US$0.30 down to US$0.18 per 1,000. **Which Optimizely Web Experimentation API does it cover?** The Optimizely REST API v2 (OpenAPI 3, Optimizely API 2.0) at api.optimizely.com. It is built from Optimizely Web Experimentation's documentation as read on 23 October 2026. 101 actions in 27 areas, each one in the signed service file (version 1.0.0). **Does actionlake keep my Optimizely Web Experimentation data, and where?** actionlake processes and stores data in Sydney, Australia; there is no US region yet. Reads may be cached for up to 5 minutes, and a write clears the reads it affects. Each run's request and response is kept, sealed, for your plan's trace window: 1 day on Free, 3 days on Starter, 7 days on Pro, 14 days on Team, 30 days on Business and 30 days on Enterprise. Your Optimizely Web Experimentation credential is sealed under your tenant's key, never logged and never returned. Your traffic is not used to train models. **Which AI clients can use it?** Claude Code, tested by us end to end, and the Claude app as a custom connector, tested by us with an existing key. Other MCP clients that support remote servers over Streamable HTTP (MCP revisions 2025-06-18 and 2025-11-25) and OAuth dynamic client registration, or a bearer header, should connect the same way; we have not tested them. Or plain REST, under the same action names. ## More connectors like Optimizely Web Experimentation Shares the most action names with - [Phrase Strings 11](https://actionlake.com/connectors/phrase-strings) - [Crowdin 10](https://actionlake.com/connectors/crowdin) - [Lokalise 10](https://actionlake.com/connectors/lokalise) - [Luma 7](https://actionlake.com/connectors/luma) - [Mux Video 6](https://actionlake.com/connectors/mux-video) - [Vimeo 6](https://actionlake.com/connectors/vimeo) Joins with, on shared entities - [HaloPSA 2](https://actionlake.com/connectors/halopsa) - [Procore 2](https://actionlake.com/connectors/procore) - [Adobe Workfront 2](https://actionlake.com/connectors/adobe-workfront) - [Gcore 2](https://actionlake.com/connectors/gcore) - [Odoo 2](https://actionlake.com/connectors/odoo) - [Azure DevOps Services 2](https://actionlake.com/connectors/azure-devops-services) Browse - [All Marketing & media connectors](https://actionlake.com/connectors/category/marketing-and-media) - [All connectors](https://actionlake.com/connectors) - [How actionlake compares](https://actionlake.com/compare) actionlake is independent. It is not made or endorsed by Optimizely Web Experimentation; the name is the vendor's own. Counts are from the Optimizely Web Experimentation service file, version 1.0.0. ## Give your agent Optimizely Web Experimentation today. [Connect Optimizely Web Experimentation free](https://actionlake.com/console?start=sandbox) [See pricing](https://actionlake.com/pricing) Start free - 100,000 calls/month, no card. No signup. Hard caps on every key. Cached answers are free. --- Source: https://actionlake.com/connectors/optimizely-web-experimentation More: https://actionlake.com/llms.txt