How to Use the Leadfeeder MCP in LlamaIndex

Q: How do I index Leadfeeder data into LlamaIndex vector stores?

Use llama-index-tools-mcp to initialize the BasicMCPClient. Convert the tools with McpToolSpec and load the outputs of tools like listleads directly into your document ingestion pipeline.

Q: Can I filter LlamaIndex queries using Leadfeeder custom feeds?

Yes. Use listcustomfeeds to fetch your segments, then let your agent query getcustomfeed to index only high-intent corporate visitors.

Q: Does LlamaIndex support real-time updates from the Leadfeeder MCP Server?

You can schedule your agent to run listaccountvisits periodically. Each run upserts the new visit data into your index, keeping your sales team's context fresh.

Q: How does the agent know which Leadfeeder tool to call for firmographic data?

The McpToolSpec exposes the schema for getlead to the agent. LlamaIndex uses this schema to decide when it needs to fetch company metadata versus raw visit history.

Index live B2B website visit data directly into your LlamaIndex vector stores for ground-truth sales intelligence.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Leadfeeder MCP to LlamaIndex

Create your Vinkius account to connect Leadfeeder 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 Leadfeeder with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Leadfeeder MCP Server outputs for semantic search

`list_lead_visits` retrieves the raw chronological history of what specific companies read on your site. LlamaIndex takes this text output, converts it into embeddings, and stores it in your vector database. When your sales reps ask which companies showed interest in a specific product, the agent queries this index. You get answers grounded in actual web traffic instead of guessing.

Run B2B RAG with LlamaIndex and Leadfeeder

`get_lead` fetches deep firmographic details for any company that bypassed your form fills. By combining this data with your internal product documentation, your RAG pipeline builds highly personalized pitch decks. The agent uses `list_accounts` to scope these queries to the correct client workspace. This ensures your synthetic research reports only include data from the relevant business units.

Query aggregate account visits semantically

`list_account_visits` aggregates your entire site's traffic data into a single queryable source. Your agent indexes this stream to let you ask natural language questions about overall traffic trends. You can also fetch your tracking code using `get_tracking_script` to check if your active domains are properly configured. This keeps your indexing pipeline fed with clean, continuous data.

Setup guide

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

Use `llama-index-tools-mcp` to initialize the `BasicMCPClient`. Convert the tools with `McpToolSpec` and load the outputs of tools like `list_leads` directly into your document ingestion pipeline.

Yes. Use `list_custom_feeds` to fetch your segments, then let your agent query `get_custom_feed` to index only high-intent corporate visitors.

You can schedule your agent to run `list_account_visits` periodically. Each run upserts the new visit data into your index, keeping your sales team's context fresh.

The `McpToolSpec` exposes the schema for `get_lead` to the agent. LlamaIndex uses this schema to decide when it needs to fetch company metadata versus raw visit history.

Your token is stored as a secure environment variable on Vinkius, which handles the headers automatically. The agent only sees the clean JSON output of your company visit records, keeping your credentials hidden.

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