How to Use the Amplitude MCP in OpenAI Agents SDK

Q: How do I connect the Amplitude MCP Server to OpenAI Agents SDK?

Install the package using pip install openai-agents. Initialize MCPServerStreamableHttp with your Vinkius endpoint URL. Pass the resulting server object to the mcpservers array in your Agent constructor.

Q: Can OpenAI Agents SDK track individual Amplitude user journeys?

Yes, the agent calls getuseractivity to pull a specific timeline of actions. Finding the right target first requires running searchusers with an email or device ID.

Q: Why does my agent fail when querying Amplitude DAU/WAU/MAU?

Date formatting is the usual culprit. The activeusers tool strictly requires YYYYMMDD formats for both start and end parameters. OpenAI guardrails usually catch this, but manual overrides might bypass the check.

Q: Does the Amplitude integration with OpenAI Agents SDK support handoffs?

Yes. You can dedicate one agent to querying eventsegmentation and another to summarizing the results. The framework routes the MCP tool outputs between them automatically.

Connect Amplitude to OpenAI Agents SDK and let your production agents track user retention, build funnels, and pull revenue data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Amplitude MCP to OpenAI Agents SDK

Create your Vinkius account to connect Amplitude to OpenAI Agents SDK 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 Amplitude with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Trace User Drops with OpenAI Agents SDK

The `get_funnel` tool lets your agent pull conversion rates across comma-separated event sequences. You pass the start and end dates formatted as YYYYMMDD, and the agent maps exactly where users abandon the product. Setting up handoffs means a dedicated analytics agent handles this pull before passing the context back to your main workflow. Tracking long-term value requires the `get_retention` tool. Your OpenAI agent defines a start acquisition event and a return event to calculate daily drop-offs. Built-in guardrails ensure the agent requests valid date ranges before executing the MCP Server call, preventing wasted API quotas.

Isolate High-Value Cohorts

Firing the `list_cohorts` tool returns every behavioral group you defined in Amplitude. Your agent can scan these groups to identify segments that trigger specific high-value actions. Tracing via the OpenAI dashboard shows exactly which cohort IDs the system pulled during its reasoning loop. Digging deeper requires the `get_cohort` tool. Since downloading raw cohort lists takes time, the agent polls the backend until the download finishes. You get precise member lists ready for targeted outreach or secondary analysis within your production environment.

Export Raw Analytics Data

Running `export_events` pulls raw product analytics data for any specific time range formatted as YYYYMMDDTHH. Your agent grabs every click, screen view, and custom trigger without leaving its Python environment. Setting `cacheToolsList=True` during initialization keeps these heavy operations responsive. Analyzing income is just as direct with the `revenue_analysis` tool. The agent calculates daily revenue figures based on the date parameters you provide. This data flows right into your OpenAI setup, letting you correlate feature launches directly with revenue spikes.

Setup guide

Set up Amplitude MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Amplitude tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Amplitude tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Amplitude tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Amplitude Agent",
            instructions="You have access to Amplitude tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 Amplitude. 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 Amplitude 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 Amplitude MCP in OpenAI Agents SDK

Install the package using `pip install openai-agents`. Initialize `MCPServerStreamableHttp` with your Vinkius endpoint URL. Pass the resulting server object to the `mcp_servers` array in your Agent constructor.

Yes, the agent calls `get_user_activity` to pull a specific timeline of actions. Finding the right target first requires running `search_users` with an email or device ID.

Date formatting is the usual culprit. The `active_users` tool strictly requires YYYYMMDD formats for both start and end parameters. OpenAI guardrails usually catch this, but manual overrides might bypass the check.

Yes. You can dedicate one agent to querying `event_segmentation` and another to summarizing the results. The framework routes the MCP tool outputs between them automatically.

Your agent accesses raw device IDs and email addresses through the search tools. Vinkius isolates this data inside an ephemeral V8 sandbox that destroys itself after the run. Tokens live only for the duration of the request, keeping PII out of persistent storage.

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