How to Use the Amplitude MCP in LlamaIndex

Q: How do I filter which Amplitude tools my LlamaIndex agent sees?

Pass the allowedtools parameter when initializing your tool spec. You can restrict the agent to just read-only metric tools while hiding the raw export functions.

Index raw product analytics from the Amplitude MCP Server into your LlamaIndex knowledge base.

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 LlamaIndex

Create your Vinkius account to connect Amplitude to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Vectorize cohort data with LlamaIndex

`list_cohorts` fetches your saved behavioral segments directly from the analytics platform. Your FunctionAgent takes those group definitions and embeds them into your vector store. When you ask questions about user behavior, the system searches the actual definitions rather than guessing. For deeper analysis, `get_cohort` pulls the specific users inside those groups. Depending on the size, the tool polls the backend until the download is ready. You can then index these user lists alongside your `revenue_analysis` daily metrics to build a queryable database of high-value customers.

Ground answers in real conversion metrics

`get_funnel` calculates the exact drop-off between a sequence of comma-separated events. Your agent pulls this data for specific YYYYMMDD date ranges and stores the results as document nodes. Product managers can then query the index to see how onboarding conversion changed after a specific release. Retention works the exact same way. `get_retention` takes a start event and a return event, outputting the decay curve. By indexing these reports weekly, LlamaIndex builds a historical archive of your product stickiness that any team member can search using natural language.

Query individual journeys via the MCP Server

`search_users` finds accounts based on an email address or device ID. The agent retrieves the internal user ID required for deeper investigations. This prevents hallucinated identifiers from breaking your downstream API calls. Once identified, `get_user_activity` pulls the chronological event stream for that person. You can index this timeline to diagnose support tickets. The agent reads the exact sequence of actions the user took, compares it against your documentation, and drafts a highly specific response.

Setup guide

Set up Amplitude MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Amplitude MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Amplitude tools.",
)
response = await agent.run("List recent Amplitude data")

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 LlamaIndex

Run pip install llama-index-tools-mcp. Create a BasicMCPClient with your Vinkius URL, wrap it in an McpToolSpec, and call to_tool_list_async() to feed the functions to your agent.

The agent pulls the raw event stream for a specific user and converts it into indexable text. You can then ask questions about what the user did before triggering a specific error.

Pass the allowed_tools parameter when initializing your tool spec. You can restrict the agent to just read-only metric tools while hiding the raw export functions.

Yes. The cohort download tool handles the polling logic internally. Your async agent will wait for the backend to finish processing the list before it attempts to index the results.

The connection runs through a zero-trust endpoint requiring a single auth token. Tools handle raw event data and email addresses, but the execution environment is completely stateless. Vinkius destroys the sandbox as soon as the API call completes, leaving zero traces of your analytics.

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