How to Use the Amplitude MCP in CrewAI

Q: How do I expose Amplitude tools to specific CrewAI agents?

Use the MCPServerHTTP class from crewai.mcp and apply a toolfilter. This lets you give the revenueanalysis tool to your Finance Agent while restricting the Support Agent to only use searchusers.

Q: Can CrewAI handle massive data dumps from Amplitude?

It depends on your LLM context window. The exportevents tool pulls raw telemetry data which gets huge fast. You should instruct your CrewAI agents to request narrow timeframes, like a single hour, to avoid overwhelming their memory limits.

Q: Why does CrewAI hang when requesting an Amplitude cohort?

The getcohort tool requires backend polling because grouping users by behavior takes time. Your agent is waiting for the download to finish. You can configure your CrewAI tasks with higher timeout limits to accommodate this wait.

Q: Does CrewAI store my Amplitude user emails permanently?

No. When your agents query searchusers by email, Vinkius routes the request through an ephemeral V8 Isolate. The data exists in memory just long enough to return the user ID to your crew, and the sandbox evaporates immediately after the connection closes.

Deploy autonomous CrewAI analyst teams that interrogate Amplitude MCP Server data, monitor funnels, and flag revenue drops.

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 CrewAI

Create your Vinkius account to connect Amplitude to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run multi-agent funnel analysis

The `get_funnel` tool calculates conversion rates between critical product steps. In CrewAI, you assign this tool to a specialized Data Analyst agent. This agent monitors the funnel daily, looking for statistical anomalies in the step-to-step drop-off rates. When the analyst detects a problem, it passes the context to a Researcher agent in the crew. The researcher then uses `event_segmentation` to break down the failing step by device type or geography. This hierarchical execution means your AI team diagnoses the root cause before a human even opens a dashboard.

Automate retention and revenue audits

Firing `get_retention` alongside `revenue_analysis` gives your crew a complete picture of customer lifetime value. A monitoring agent runs these checks every weekend using YYYYMMDD date formats. It stores the historical baselines in CrewAI's shared memory. If daily revenue drops while retention stays flat, the crew knows exactly what to investigate. They can pull `active_users` to see if MAU dropped, or spin up a new task to investigate pricing page errors. The agents collaborate to build a complete diagnostic report.

Investigate individual user journeys via CrewAI

Calling `search_users` lets your Support Agent find a specific customer by email. Once located, the agent hands the device ID to a Debugger Agent equipped with the `get_user_activity` tool. This separation of duties keeps your agent prompts focused and highly effective. The debugger pulls the raw event stream for that specific user. It reads the exact sequence of clicks leading up to a crash or a failed payment. You set this up by passing the MCP Server URL directly into the `mcps` array of your specific agent definitions.

Setup guide

Set up Amplitude MCP in CrewAI

Prerequisites

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

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Amplitude tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Amplitude Analyst",
    goal="Access and analyze Amplitude data via MCP.",
    backstory="Expert analyst with direct Amplitude access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Amplitude transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

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

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Amplitude Analyst",
        goal="Access and analyze Amplitude data via MCP.",
        backstory="Expert analyst with direct Amplitude access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Amplitude transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

Use the `MCPServerHTTP` class from `crewai.mcp` and apply a `tool_filter`. This lets you give the `revenue_analysis` tool to your Finance Agent while restricting the Support Agent to only use `search_users`.

It depends on your LLM context window. The `export_events` tool pulls raw telemetry data which gets huge fast. You should instruct your CrewAI agents to request narrow timeframes, like a single hour, to avoid overwhelming their memory limits.

The `get_cohort` tool requires backend polling because grouping users by behavior takes time. Your agent is waiting for the download to finish. You can configure your CrewAI tasks with higher timeout limits to accommodate this wait.

Instruct your agents in their system prompts to strictly use the YYYYMMDD format for tools like `active_users` and `event_segmentation`. For raw exports, they must use the YYYYMMDDTHH format.

No. When your agents query `search_users` by email, Vinkius routes the request through an ephemeral V8 Isolate. The data exists in memory just long enough to return the user ID to your crew, and the sandbox evaporates immediately after the connection closes.

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