How to Use the Amplitude MCP in AutoGen

Q: How do I configure AutoGen with Amplitude?

Install the autogen-extmcp package. Use mcpservertools with a StreamableHttpServerParams object pointing to your Vinkius URL. Pass the resulting tool list directly to your AssistantAgent constructor.

Give your AutoGen agents the ability to debate product analytics using live Amplitude MCP Server 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 AutoGen

Create your Vinkius account to connect Amplitude to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent conversion analysis

`get_funnel` pulls exact drop-off rates for any comma-separated list of events across a YYYYMMDD date range. A product agent grabs this data to argue that onboarding is failing. A separate engineering agent reviews the same numbers, noticing that the drop only occurs on mobile devices. They then use `get_retention` to settle the argument. By passing the acquisition and return events, the agents analyze the long-term decay curve. They debate whether the initial drop-off actually impacts 30-day retention, eventually converging on a single recommendation for the product team.

Cross-reference revenue and active users

`active_users` fetches your daily, weekly, and monthly active user counts. One agent monitors this baseline to establish normal traffic patterns. If DAU spikes, this agent alerts the group to investigate the cause. A financial agent immediately calls `revenue_analysis` for the same time period. It checks if the traffic spike actually generated money. If the DAU went up but daily revenue stayed flat, the agents discuss potential causes like a bot attack or a broken checkout flow before summarizing their findings.

Investigate anomalies via the MCP Server

`search_users` lets your diagnostic agents find specific accounts using an email or device ID. Once they agree on a suspect account, they trigger `get_user_activity` to pull the exact chronological event stream. They parse this log line by line to understand the user behavior. For massive anomalies, the agents use `export_events`. They pass a specific hour block formatted as YYYYMMDDTHH to pull raw telemetry. The McpToolAdapter converts the massive JSON response into a format the agents can digest, allowing them to debate system-wide trends without manual data wrangling.

Setup guide

Set up Amplitude MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Amplitude tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Amplitude_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Amplitude data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Amplitude_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Amplitude data")
    print(result.messages[-1].content)

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 AutoGen

Install the autogen-ext[mcp] package. Use mcp_server_tools with a StreamableHttpServerParams object pointing to your Vinkius URL. Pass the resulting tool list directly to your AssistantAgent constructor.

Yes. You provide the tool list to the specific agents that need it. A data-gathering agent can pull the metrics while a separate critic agent reviews the findings without making its own API calls.

The schema strictly requires YYYYMMDD for most endpoints and YYYYMMDDTHH for exports. The agents read these constraints from the tool descriptions and format their arguments automatically before calling the server.

The cohort tool includes built-in polling. The agent initiates the request and the tool handles the wait states, returning the final user list only when the backend finishes processing.

Your agents process highly sensitive metrics, including daily revenue figures and raw user IDs. We secure this by running the MCP tools inside an ephemeral sandbox. The container executes the request, returns the payload to your local AutoGen environment, and immediately self-destructs.

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