How to Use the Kameleoon MCP in Cursor

Q: How do I configure the Kameleoon MCP Server in Cursor?

Add the server setup to your project-scope .cursor/mcp.json file. Once saved, enable Agent mode in the chat panel to let the editor invoke tools like listexperiments automatically.

Q: How does Cursor verify that my local code matches Kameleoon?

The editor calls listcustomdata and compares the retrieved tracking dimensions against your local analytics files. It alerts you if you are using an unregistered tracking key in your codebase.

Q: Can I fetch targeting rules for specific sites?

You can run listsites to find your target site ID, then call listtargetingrules to pull the rules. This ensures your local conditional logic matches the audience filters defined in your dashboard.

Build and test Kameleoon variations directly in Cursor, generating code with this MCP Server that matches your live targeting rules.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kameleoon MCP to Cursor

Create your Vinkius account to connect Kameleoon to Cursor and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Kameleoon with Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Generate variation code in Cursor using live API data

Query your workspace via `list_variations` to pull the exact IDs and configurations of your active test branches directly into your editor. This ensures your front-end components match your live setups without manual copying. This means the editor generates functional React or JS components that match your live experiments instead of relying on outdated mock data. Your agent reads this structure to write clean conditional rendering logic directly in your editor.

Audit your Kameleoon targeting rules inside Cursor

Run `list_targeting_rules` and `list_custom_data` to verify that your local codebase matches your live targeting rules. This check keeps your telemetry sync tight and prevents analytics mismatches. If a key is missing or misspelled in your codebase, this MCP Server highlights the discrepancy. You can fix targeting mismatches before committing any code to your repository.

Monitor active test performance while you write code

Monitor your active campaigns by running `list_experiments` directly inside your code editor. This keeps you informed of active production tests while editing the corresponding files. When a test underperforms, the agent can call `get_experiment_results` to pull the latest statistical data. You can inspect these metrics directly in the sidebar and decide whether to refactor the variation code.

Setup guide

Set up Kameleoon MCP in Cursor

Prerequisites

Cursor installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the Kameleoon MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent Kameleoon transactions." If the MCP tools are loaded correctly, Cursor will call the Kameleoon tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/mcp.json

{
  "mcpServers": {
    "kameleoon-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Kameleoon. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Kameleoon now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Kameleoon MCP in Cursor

Add the server setup to your project-scope `.cursor/mcp.json` file. Once saved, enable Agent mode in the chat panel to let the editor invoke tools like `list_experiments` automatically.

Yes, you can ask the editor to set up a test structure using `create_experiment`. Provide the name and site ID, and the editor will register the experiment and return the configuration details.

The editor calls `list_custom_data` and compares the retrieved tracking dimensions against your local analytics files. It alerts you if you are using an unregistered tracking key in your codebase.

You can run `list_sites` to find your target site ID, then call `list_targeting_rules` to pull the rules. This ensures your local conditional logic matches the audience filters defined in your dashboard.

No, the server only accesses experiment metadata, targeting rules, and variation configurations. Your actual application source code remains local to your machine and is never sent to the external API.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript