How to Use the Instantly MCP in LlamaIndex

Q: Can I Instantly search my campaigns using semantic search in LlamaIndex?

Yes, by pulling data with listcampaigns and loading it into a vector index. You can then ask questions about your setups without digging through the UI.

Q: How does LlamaIndex Instantly prevent duplicate leads from being added?

The agent indexes your active lists using listleads. Before it calls addleads, it runs a semantic search to ensure the prospect isn't already in another sequence.

Q: Can I Instantly query historical analytics using LlamaIndex RAG?

Absolutely. You index your historical performance data via getcampaignanalytics. Your agent can then answer complex questions about your best performing subject lines.

Index live Instantly campaign data into LlamaIndex to query your cold outreach performance using semantic search.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Instantly MCP to LlamaIndex

Create your Vinkius account to connect Instantly 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 Instantly with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Instantly campaign logs for semantic RAG

Stop guessing why your cold emails are failing. With LlamaIndex, you can pull raw data using `get_campaign` and `list_leads`, then convert those logs into searchable vector embeddings. Your agent can search past campaigns to find what copy worked. Instead of looking at sterile charts, you ask your LLM why a specific angle bombed. The LlamaIndex agent queries the vector store, pulls the exact subsequences via `list_subsequences`, and gives you a grounded analysis based on actual data.

Query your sending health with this LlamaIndex MCP Server

This MCP Server lets you turn your sending infrastructure into a queryable database. By indexing the output of `list_accounts` and `get_account_stats`, LlamaIndex builds a local knowledge base of your domain health. You don't need to write custom SQL or parse JSON to find your weakest inbox. Just ask the agent which accounts are struggling, and it searches the index to pinpoint the exact senders with high spam flags.

Ground lead generation in historical campaign data

Don't let your agent upload duplicate or cold leads. When you use LlamaIndex to manage your pipeline, the agent checks your vector store of existing leads before running `add_leads`. The system queries `list_leads` across your active campaigns, indexes the emails, and runs a semantic check. This prevents you from emailing the same prospect twice under different campaigns, keeping your sender reputation safe.

Setup guide

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

Yes, by pulling data with `list_campaigns` and loading it into a vector index. You can then ask questions about your setups without digging through the UI.

The agent indexes your active lists using `list_leads`. Before it calls `add_leads`, it runs a semantic search to ensure the prospect isn't already in another sequence.

Absolutely. You index your historical performance data via `get_campaign_analytics`. Your agent can then answer complex questions about your best performing subject lines.

Install the MCP tool pack, initialize the client, and pass the tool list to your FunctionAgent. It will automatically register tools like `resume_campaign` and `pause_campaign` for the agent to use.

Yes, your lead emails and campaign analytics are processed locally or within your private cloud. The MCP connection uses a zero-trust architecture that never logs or retains your sender profiles.

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