How to Use the Icypeas MCP in LlamaIndex

Q: Can I use LlamaIndex to query my Icypeas lists using natural language?

Yes, by loading tools like listprospectlists into your LlamaIndex agent via this MCP Server, the model can search and filter your lists dynamically. The agent translates your natural language requests into structured API calls.

Q: How do I store email verification results from Icypeas in my LlamaIndex vector store?

You can run verifyemail on your contacts and index the deliverability status directly as metadata in your vector nodes. This lets you filter out risky or invalid emails during retrieval.

Q: Does LlamaIndex support bulk indexing of Icypeas campaign data?

Yes, you can use the MCP tool spec to pull data from listcampaigns and parse the raw JSON directly into document objects. From there, you can build a query engine over your entire outreach history.

Q: Is my Icypeas account data safe when indexing with LlamaIndex?

Absolutely, because all API calls to getaccount run locally inside a zero-trust V8 sandbox on your machine. Your API token never leaves your runtime, and your account details are never stored or cached by external indexing services.

Index live Icypeas lead data directly into your LlamaIndex vector store for grounded, hallucination-free sales context.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Icypeas MCP to LlamaIndex

Create your Vinkius account to connect Icypeas 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 Icypeas with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index live prospect data for LlamaIndex RAG

`list_prospects` allows your LlamaIndex pipeline to pull active lead databases directly into your local vector index. Instead of querying static CSVs, your RAG system searches live, up-to-date prospect records to answer sales queries. This prevents your agent from hallucinating old contact info or using outdated titles during personalization steps. It grounds your generation in actual, real-time sales data.

Semantic search over Icypeas lists via MCP Server

`get_prospect_list` retrieves the exact structure of your lead lists via this MCP Server so LlamaIndex can index and categorize them semantically. Your agent can compare new incoming leads against existing lists to identify duplicates or warm accounts. By turning raw list data into searchable embeddings, you can ask your agent natural language questions like who works in enterprise security and get immediate, accurate matches.

Ground campaign generation with live metrics

`get_campaign` pulls performance metrics and templates directly into your index to inform your draft generation. Your agent looks at what worked in previous campaigns before writing new copy for your prospects. This feedback loop ensures your generated outreach matches the tone and structure of your historically successful campaigns. You get drafts grounded in actual performance data instead of generic templates.

Setup guide

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

Yes, by loading tools like list_prospect_lists into your LlamaIndex agent via this MCP Server, the model can search and filter your lists dynamically. The agent translates your natural language requests into structured API calls.

You can run verify_email on your contacts and index the deliverability status directly as metadata in your vector nodes. This lets you filter out risky or invalid emails during retrieval.

Yes, you can use the MCP tool spec to pull data from list_campaigns and parse the raw JSON directly into document objects. From there, you can build a query engine over your entire outreach history.

Yes, you can pass a list of allowed tools to your agent initialization to restrict access. For example, you can limit your generation agent to find_email while blocking list modification tools.

Absolutely, because all API calls to get_account run locally inside a zero-trust V8 sandbox on your machine. Your API token never leaves your runtime, and your account details are never stored or cached by external indexing services.

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