How to Use the Amplemarket MCP in LlamaIndex

Q: Is it possible to search for people in Amplemarket and then ask questions about the results using LlamaIndex?

Yes, that's the core idea. Use the searchpeople tool to find contacts, and LlamaIndex will automatically index the results. You can then ask follow-up questions about those specific contacts without having to run the search again.

Turn your Amplemarket sales data into a queryable knowledge base with LlamaIndex. Ask questions, get answers grounded in real contact data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Amplemarket MCP to LlamaIndex

Create your Vinkius account to connect Amplemarket 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 Amplemarket with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Your Sales Outreach

Connect LlamaIndex to Amplemarket and every tool call becomes a document in your knowledge base. When you use `search_people` to find prospects, the results are automatically indexed. Your agent doesn't just find data; it remembers it. Now you can ask natural language questions about your prospecting history. 'Who did we find from SaaS companies in New York last week?' Your LlamaIndex application queries the indexed `search_people` results and gives you a straight answer, not a guess.

RAG Over Live Amplemarket Data with LlamaIndex

Your agent can query its existing knowledge base of past leads and sequences. Then, it can use tools like `list_sequences` or `list_lead_lists` to fetch the current state of your Amplemarket account. This is how you build a RAG pipeline that's always up-to-date. Imagine asking, 'Which of our current sequences are best for the FinTech leads we found last month?' The agent retrieves the lead data from its index, fetches live sequence info with `list_sequences`, and synthesizes an answer. It's combining memory with real-time context.

Build a Self-Aware Sales Engine

Because LlamaIndex can index tool outputs, your agent can learn from its own operations. After using `add_leads_to_sequence`, that action and its result are stored. The agent builds a history of its own work. This lets you build agents that can answer questions like, 'Which sequences have I added the most leads to this week?' It queries its own indexed actions from `add_leads_to_sequence` and `trigger_custom_signal` to give you a report. Your agent isn't just executing tasks; it's building a queryable audit log of its own performance.

Setup guide

Set up Amplemarket 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 Amplemarket 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 Amplemarket tools.",
)
response = await agent.run("List recent Amplemarket 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 Amplemarket. 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 Amplemarket 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 Amplemarket MCP in LlamaIndex

LlamaIndex is built for RAG. It doesn't just call Amplemarket tools; it indexes their output. This means results from `search_people` become a searchable knowledge base you can query in plain English.

Not directly with these tools, as there isn't a 'get leads in sequence' function. You can, however, build an agent that indexes the results of every `add_leads_to_sequence` call. You'd then ask your index, 'Which leads did I add to sequence X?'

Yes, that's the core idea. Use the `search_people` tool to find contacts, and LlamaIndex will automatically index the results. You can then ask follow-up questions about those specific contacts without having to run the search again.

It creates a historical record. You can track how your sequences change over time or ask questions like 'Did we have a sequence named 'Q4 Outreach' last month?' without needing a new API call.

The MCP Server only handles your Amplemarket data, like contact names and lists, for the duration of an API call. LlamaIndex then takes the output of that call and stores it in your own vector index. You control where that indexed data lives; Vinkius never sees it.

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