> **Building with AI coding agents?** Install the authstack plugin with one command. This equips your agent with accurate Scalekit implementation patterns.
>
> **Recommended**:
> ```bash
> npx @scalekit-inc/cli setup
> ```
>
> Global:
> ```bash
> npm install -g @scalekit-inc/cli
> scalekit setup
> ```
>
> Supports Claude Code, Cursor, GitHub Copilot, Codex + skills for 40+ agents.
> Features: full-stack-auth, agent-auth, mcp-auth, modular-sso, modular-scim.
> [Full setup guide](https://docs.scalekit.com/dev-kit/build-with-ai/)

---

# Amplitude Experiment Management connector

1. ### Install the SDK

   ```bash frame="terminal"
       npm install @scalekit-sdk/node
       ```
     ```bash frame="terminal"
       pip install scalekit
       ```
     Full SDK reference: [Node.js](/agentkit/sdks/node/) | [Python](/agentkit/sdks/python/)

2. ### Set your credentials

   <AgentKitCredentials />

3. ### Set up the connector

   Register your Amplitude Experiment Management credentials with Scalekit so it can authenticate requests on your behalf. You do this once per environment.

   <details>
   <summary>Dashboard setup steps</summary>

   <SetupAmplitudeexperimentmanagementSection />

   </details>

4. ### Make your first call

   <QuickstartGenericApikeySection connector="amplitudeexperimentmanagement" toolName="amplitudeexperimentmanagement_list_all_versions" providerName="Amplitude Experiment Management" />

## What you can do

Connect this agent connector to let your agent:

- **Cohorts add experiment variant, add flag variant** — Add specific cohorts to this experiment variant's targeting inclusions
- **Users add experiment variant, add flag variant, remove all experiment variant** — Force-bucket specific users or devices into this experiment variant — identified by user ID, device ID, or an email-style identifier — bypassing the experiment's normal allocation
- **Delete bulk** — Remove a specific set of cohorts (by ID) from an experiment variant's targeting, leaving other included cohorts untouched
- **Create deployment, experiment, experiment deployment** — Create a new deployment in a project
- **Get experiment, experiment variant, experiment variant cohorts** — Get complete details for a single Amplitude experiment by its ID
- **List all versions, deployments, experiment deployments** — List version history across ALL flags and experiments the API key can access, in one global, paginated feed — distinct from amplitudeexperimentmanagement_list_flag_versions and amplitudeexperimentmanagement_list_experiment_versions, which return the version history for one specific flag or experiment and do NOT support start/end/limit/cursor pagination

## Tool list

Use the exact tool names from the **Tool list** below when you call `execute_tool`. If you're not sure which name to use, list the tools available for the current user first.

<ToolList tools={tools} />

---

## More Scalekit documentation

| Resource | What it contains | When to use it |
|----------|-----------------|----------------|
| [/llms.txt](/llms.txt) | Structured index with routing hints per product area | Start here — find which documentation set covers your topic before loading full content |
| [/llms-full.txt](/llms-full.txt) | Complete documentation for all Scalekit products in one file | Use when you need exhaustive context across multiple products or when the topic spans several areas |
| [sitemap-0.xml](https://docs.scalekit.com/sitemap-0.xml) | Full URL list of every documentation page | Use to discover specific page URLs you can fetch for targeted, page-level answers |
