# Optimizely MCP connector

The Optimizely connector brings campaigns, audiences, attributes, approvals and results into Elaichi, so once it is connected, Claude, ChatGPT, Cursor and Microsoft Copilot can read and update them inside each person's own Optimizely access.

Source: https://elaichi.ai/connectors/optimizely/

## Facts

| | |
| --- | --- |
| Application | Optimizely |
| Category | Feature Flag |
| AI tools | 206 |
| Authentication | Connects with an API key |
| Bring your own OAuth app | No |
| MCP endpoint | https://api.elaichi.ai/mcp |
| Works with | Claude, ChatGPT, Cursor, Microsoft Copilot, any MCP client, and the Elaichi Agent |
| Tools advertised by name | No. Connected tools are never listed one by one, however few there are. The endpoint advertises `search_tools` and `execute_tool` instead |

## What you can ask once Optimizely is connected

- Which Optimizely campaigns are still waiting on approval?
- Summarize last week's results for the checkout campaign.
- Show me the audiences that use the plan tier attribute.

## Connect Optimizely in Elaichi

This happens once for the organization, before any client is involved.

1. Open Connections, choose Add connection, and pick Optimizely.
2. Optionally set Share with, then press Connect.
3. Paste an Optimizely API key. One person generates a token in Optimizely and pastes it once. Everyone else works through Share with, and never sees it.

Credentials are vaulted and nobody, including the AI, reads them back. The connection becomes a toolbox immediately, so you can curate which Optimizely tools are exposed, rename them, or freeze arguments before anyone points a client at it.

## Optimizely MCP connector for Claude

Endpoint: https://api.elaichi.ai/mcp

1. Open Customize, then Connectors.
2. Press Add.
3. Name it, paste the MCP server URL, then Continue.
4. Sign in and approve.

On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves.

## Optimizely MCP connector for Claude Code

Endpoint: https://api.elaichi.ai/mcp

1. In a terminal, run `claude mcp add` with the endpoint.
2. Start Claude Code and run `/mcp`.
3. Pick elaichi, then sign in and approve in the browser.

```bash
claude mcp add --transport http elaichi --scope user https://api.elaichi.ai/mcp
```

Use `--scope project` instead to share it with the repository through `.mcp.json`.

## Optimizely MCP connector for ChatGPT

Endpoint: https://api.elaichi.ai/mcp

1. Open Plugins, then press the + button.
2. Name it and paste the endpoint into Server URL.
3. Leave Authentication on OAuth, then tick the risk acknowledgement.
4. Press Create, then sign in and approve.

Works on the web. The plugin directory lives at chatgpt.com/plugins.

## Optimizely MCP connector for Cursor

Endpoint: https://api.elaichi.ai/mcp

1. Open `~/.cursor/mcp.json`.
2. Add the endpoint under `mcpServers`.
3. Reload Cursor, then sign in and approve.

Set up per machine, so repeat it on each computer you work from.

## Optimizely MCP connector for Microsoft Copilot

Endpoint: https://api.elaichi.ai/mcp

1. In Copilot Studio, open your agent, then Tools, Add a tool, New tool and Model Context Protocol.
2. Paste the endpoint into Server URL, choose OAuth 2.0, then Dynamic discovery, and press Create.
3. Create a new connection, sign in and approve, then press Add to agent.
4. Under Channels, open Teams and Microsoft Copilot and make the agent available in Microsoft Copilot.

Microsoft Copilot was called Microsoft 365 Copilot. Keep the tool on end-user credentials, so each person signs in as themselves.

## Connect Optimizely to any MCP client

Endpoint: https://api.elaichi.ai/mcp

1. Add the endpoint as a remote MCP server.
2. Sign in and approve.

The Elaichi Agent already has these tools, with nothing to set up.

## What the consent screen decides

Every scope the client asks for starts ticked except "Delete things", which you tick yourself. Calling a Optimizely tool needs "Use your connected apps". Over MCP there is no trusted place to confirm a write in the moment, so the consent screen is the standing approval rather than a formality. Think hard before granting Use your connected apps, which can also delete in connected apps and cannot be undone.

## What teams do with Optimizely through Elaichi

### Check what is waiting for approval

Product. Ask which Optimizely campaigns and change requests are still waiting on sign-off before standup, without opening Optimizely yourself.

### Pull campaign results after a test ends

Growth. Get the results of a finished Optimizely campaign summarized in plain language, or exported as a CSV for the weekly deck.

### Draft a new audience from a brief

Marketing. Describe who a campaign should reach and have the Optimizely audience created with the right attributes, ready for you to review.

### Tidy up attributes before a release

Engineering. List the Optimizely attributes in use, fix a description that is out of date, or remove one that nothing references anymore.

### Trace what one visitor was shown

Analytics. Look up an attribution visitor by ID to see which Optimizely campaigns they were counted in when a number looks off.

### Check billing usage before the renewal

Finance. Pull the Optimizely billing usage summary for the period to see how close the account is to its limit before the contract conversation.

## Elaichi vs Zapier MCP vs Composio for Optimizely

All three can connect Optimizely to an AI assistant, and all three have admin controls. They differ in where access lives and how you pay.

| What to check | Elaichi | Zapier MCP | Composio |
| --- | --- | --- | --- |
| Where the AI connects | One address for the whole organization. Endpoint: https://api.elaichi.ai/mcp | A server per member, created at sign-in. | An MCP endpoint per team, or an SDK. |
| Control over Optimizely tools | Allow or restrict single Optimizely tools, per role or user. | App and action restrictions on the account. | Role permissions, down to the action. |
| Record of calls | One audit entry per Optimizely call. | A History tab of tool calls. | A log of every tool call. |
| Single sign-on | SAML or OIDC, plus SCIM, on Gold. | SAML on Enterprise. | SAML and OIDC on Enterprise. |
| Price | Free for one person; $15 per user per month on Gold. | 2 tasks per successful call. | Billed per tool call. |

Sources: Zapier MCP [docs](https://docs.zapier.com/mcp/get-started/quickstart), [security](https://docs.zapier.com/mcp/manage/security), [usage](https://docs.zapier.com/mcp/features/usage); Composio [docs](https://docs.composio.dev/docs/composio-connect), [gateway](https://composio.dev/mcp-gateway), [enterprise](https://composio.dev/enterprise), [pricing](https://composio.dev/pricing). Checked September 2026.

Longer take: [Zapier MCP alternative](/blog/zapier-mcp-alternative/) and [when you don't need an MCP gateway](/blog/when-you-dont-need-an-mcp-gateway/).

## Frequently asked questions

### How do I connect Optimizely to Claude?

Connect Optimizely in Elaichi first, then in Claude open Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp. Optimizely connects with an API key, so the sign-in step is pasting that key into Elaichi once. There is no OAuth application to register and no client ID or secret to generate.

### Does Optimizely work with ChatGPT and Cursor as well as Claude?

Yes. Once Optimizely is connected in Elaichi, the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, Microsoft Copilot, any MCP client and the Elaichi Agent. You connect Optimizely once and every client picks it up.

### What can an AI agent actually do with my Optimizely data?

With Optimizely connected, an agent can list your campaigns and their results, create or update audiences and attributes, check which approvals and change requests are open, look up an attribution visitor, and read billing usage. Ask for one thing at a time, such as the results of a named campaign; short concrete asks work better than long paragraphs.

### Does connecting Optimizely give the AI everything in my project?

No. Every call to Optimizely runs as the person who signed in, so an agent sees only the campaigns, audiences and projects that person already has access to in Optimizely. Elaichi can narrow that access further with roles and restrictions, and it never widens it.

### Can my team share one Optimizely connection?

Yes. One person connects Optimizely with the API key, shares the connection with a team in Elaichi, and nobody else on the team ever handles the key. Each person still signs in to Elaichi as themselves, so the audit log names who ran each Optimizely call.

### Can I stop an agent from deleting or changing things in Optimizely?

Yes. Restrictions in Elaichi work per action, so you can restrict deleting Optimizely campaigns or attributes, or updating audiences, for a role or for one person. A restricted action still appears in Elaichi's tool search, flagged as restricted, but no client can run it, whatever the prompt says.

### What happens to an Optimizely connection when someone leaves?

Offboarding that person in Elaichi ends their access to Optimizely through every client at once. A shared Optimizely connection keeps working for everyone else on the team. If you want to remove Optimizely entirely, disconnecting it once in Elaichi removes it from Claude, ChatGPT, Cursor, Microsoft Copilot and every other client.

### Does the Optimizely MCP connector work with Gemini, Codex, Claude Code or other MCP clients?

Yes. Optimizely is reached over the same MCP endpoint every client uses, so anything that speaks MCP can call it — Gemini, Codex, Claude Code, Windsurf, Cline, Zed and OpenCode among them — alongside Claude, ChatGPT, Cursor, Microsoft Copilot, and the Elaichi Agent. The tools on offer and the access behind them are identical whichever client asks. Only the setup screen differs.

### Is Elaichi an alternative to Zapier MCP for Optimizely?

Yes. Both let Claude, ChatGPT or Cursor use Optimizely. Zapier MCP fits a team that already automates in Zapier, since each person signs in and acts as themselves in that account. Elaichi fits when IT wants one address for the whole company, per-tool rules by role, and a record of every Optimizely call.

### How is Elaichi different from Composio for Optimizely?

Composio gives AI agents tools and sign-in handling across 1,000+ apps, for developers building agents or people using an assistant, billed per tool call. Elaichi gives a company's own people governed access to Optimizely: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call.

## All 206 Optimizely tools

Every tool below is callable through https://api.elaichi.ai/mcp once Optimizely is connected, subject to the toolbox it is in and the restrictions on the caller.

- **List all Optimizely approvals** (List). List Approvals. List Approvals of a Flag Required: project_id.
- **Delete a Optimizely attribute by ID** (Delete). Archive an Attribute. Archive Attribute by ID Required: id.
- **Create a Optimizely attribute** (Create). Create an Attribute. Create an Attribue Required: key, project_id.
- **List all Optimizely attributes** (List). List Attributes. List Attributes under a Project Required: project_id.
- **Get single Optimizely attribute by ID** (Get). Read an Attribute. Get Attribute by ID Required: id.
- **Optimizely attributes partial update** (Update). Update an Attribute. Update an Attribute by ID Required: attribute_id.
- **Get single Optimizely attribution visitor by ID** (Get). Get bucketing information for a visitor. Get a list of experiments within a project a visitor has been exposed to Required: id, account_id.
- **Create a Optimizely audience** (Create). Create an Audience. Create an Audience for a Project Required: project_id.
- **List all Optimizely audiences** (List). List Audiences. List Audiences for a Project Required: project_id.
- **Get single Optimizely audience by ID** (Get). Read an Audience. Get metadata for a single Audience Required: id.
- **Optimizely audiences partial update** (Update). Update an Audience. Update an Audience for a Project Required: audience_id.
- **Get single Optimizely billing usage by ID** (Get). Get Impressions Usage. Get Impressions Usage by account id Required: id, usage_date_from, usage_date_to.
- **List all Optimizely billing usage summary** (List). Get Impressions Usage Summary. Get Impressions Usage Summary by account id Required: account_id.
- **Delete a Optimizely campaign by ID** (Delete). Archive a Campaign. Archive Campaign by ID Required: id.
- **Create a Optimizely campaign** (Create). Create a Campaign. Create a new Campaign in your account Required: project_id.
- **List all Optimizely campaigns** (List). List Campaigns. Get a list of all the Campaigns in a Project Required: project_id.
- **Get single Optimizely campaign by ID** (Get). Read a Campaign. Get metadata for a single Campaign Required: id.
- **Optimizely campaigns partial update** (Update). Update a Campaign. Update a campaign's metadata. Required: campaign_id.
- **List all Optimizely campaigns results** (List). Get Campaign results. Get results for a Campaign Required: campaign_id.
- **List all Optimizely campaigns results CSV** (List). Get Campaign results as a CSV. Get results for a Campaign as a CSV Required: campaign_id.
- **List all Optimizely campaigns results share** (List). Get a sharable link for the campaign's results page. This link allows read-only access for anyone to view the results, even if they don't have an Optimizely account. Because anyone can use the link, be careful where you share it. Required: campaign_id.
- **List all Optimizely catalogs catalog** (List). Download a CSV with all current catalog data. Required: date, catalog_id.
- **List all Optimizely catalogs stats** (List). Download a CSV with summary stats data. Required: date, catalog_id.
- **Optimizely change requests archive** (Archive). Archive a change request. Archive a resolved or rejected change request Required: project_id, change_request_id.
- **Get single Optimizely change request by ID** (Get). Get change request details. Get detailed information about a specific change request Required: id, project_id.
- **List all Optimizely change requests** (List). List project change requests. List change requests across all flags in a project Required: project_id.
- **Create a Optimizely change requests status** (Create). Update the status of a change request. Approve, reject, or withdraw a change request Required: project_id, flag_key, environment_key, change_request_id, status.
- **List all Optimizely changes** (List). Retrieve changes for a project. Get a list of changes for a given project using optional filters. Required: project_id.
- **Create a Optimizely collaborator** (Create). Invite Collaborators. Invite collaborators to specific projects on an account
- **List all Optimizely collaborators** (List). List Collaborators. List all the Collaborators on your account, or filter by project_id to list Collaborators on a specific project
- **Delete a Optimizely custom event by ID** (Delete). Archive a Custom Event. Required: id, project_id.
- **Create a Optimizely custom event** (Create). Create a Custom Event. Create a Custom Event in a provided Project Required: project_id, key.
- **Optimizely custom events partial update** (Update). Update a Custom Event. Required: project_id, event_id.
- **Get single Optimizely custom field by ID** (Get). Read a Custom Field. Get Custom Field definition by ID Required: id.
- **Delete a Optimizely environment by ID** (Delete). Archive an Environment. Required: id.
- **Create a Optimizely environment** (Create). Create an Environment. Create an Environment in a provided Project Required: key, name, project_id.
- **List all Optimizely environments** (List). Get Environments by Project. Get all of the Environments that have been created in a given Project Required: project_id.
- **Get single Optimizely environment by ID** (Get). Read an Environment. Get all the properties of a single Environment Required: id.
- **Optimizely environments partial update** (Update). Update an Environment. Update an Environment by ID Required: environment_id.
- **List all Optimizely environments datafile** (List). Read the datafile of an Environment. Get the datafile for an Environment. The Datafile is a JSON string that describes to the Full Stack SDK all the experiments and features running in a given environment and dependent entities like audiences and attributes. Normally, you won't need to interact with the datafile directly. The SDK exposes methods that operate on it internally. Required: environment_id.
- **Create a Optimizely environments policy** (Create). Create an approval policy. Required: project_id, environment_id, name, is_default, default_preferences, approvers.
- **Delete a Optimizely environments policy by ID** (Delete). Delete an approval policy. Required: id, project_id, environment_id.
- **Get single Optimizely environments policy by ID** (Get). Get an approval policy. Required: id, project_id, environment_id.
- **List all Optimizely environments policies** (List). List approval policies for an environment. Required: project_id, environment_id.
- **Optimizely environments policies partial update** (Update). Update an approval policy. Required: project_id, environment_id, policy_id.
- **List all Optimizely environments preferences** (List). Get Environment Approval Settings. Get the approval settings for a specific environment in a project. Required: project_id, environment_id.
- **Optimizely environments preferences bulk update** (Update). Update Environment Approval Settings. Update environment approval settings for a project and environment. This operation allows updating entity approval rules, default preferences, and notification configurations for an environment within a project. Required: project_id, environment_id.
- **List all Optimizely environments preferences by project ID** (List). List Environment Approval Settings. List the approval settings for every environment in a project. Required: project_id.
- **Get single Optimizely environments rule by ID** (Get). Fetch the Rule for a Ruleset in an Environment. Fetch a Rule for a Ruleset in a specific Environment of a project. Required: id, project_id, flag_key, environment_key.
- **Optimizely environments ruleset disable** (Disable). Disable the Ruleset for a Flag in an Environment. Disables the entire Ruleset for a Flag in an Environment Required: project_id, flag_key, environment_key.
- ...and 156 more tools. Call `tools/list` via the MCP endpoint, or see the full catalog via the API, for the complete set.
