How to Use the 6sense MCP in LlamaIndex

Q: Can LlamaIndex query 6sense segments during a retrieval step?

Yes, your agent can call listsegments as a query-time tool to fetch real-time lists. It then uses that context to filter or rerank documents before generating a response.

Q: How do I restrict which tools the query engine can access?

You can pass an allowedtools filter when setting up your MCP Client. This lets you restrict the engine to only run identifycompany while locking down the other tools.

Q: How does LlamaIndex handle privacy for enriched email profiles?

Email addresses sent to enrichperson are transmitted via encrypted HTTPS directly to the API endpoint and are never stored in our query logs. The resulting profile data is only stored in your local vector index, giving you complete control over your customer data.

Index live firmographics and segments directly into your LlamaIndex vector store for grounded, context-rich queries.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect 6sense MCP to LlamaIndex

Create your Vinkius account to connect 6sense 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 6sense with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Ground your RAG pipeline in real company data using LlamaIndex

LlamaIndex doesn't just call APIs; it indexes the results. When your agent calls `enrich_company` to fetch firmographics, this MCP Server helps populate your index directly. This means future queries about that company are grounded in actual data rather than LLM guesswork. You can query past sessions to see which companies your team has researched. The index updates dynamically as the server pulls fresh data, giving you a living database of target accounts.

Search visitor intent profiles semantically

Turn raw IP lookups into searchable knowledge. Use `identify_company` to turn visitor IPs into company names, then index those names alongside their domain profiles. Your sales team can search this index using natural language to find hot prospects. This approach bridges the gap between raw web traffic and structured sales intelligence. LlamaIndex handles the semantic search, while the server provides the raw signal.

Build dynamic context from marketing segments

Feed active marketing lists directly into your query engine context. By calling `list_segments`, the agent retrieves the exact lists a company belongs to and adds them to the query prompt. If you need to know who is interested in a specific product, the agent checks the indexed segments. This ensures your automated responses always match the customer's actual stage in the funnel.

Setup guide

Set up 6sense 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 6sense 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 6sense tools.",
)
response = await agent.run("List recent 6sense 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 6sense. 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 6sense 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 6sense MCP in LlamaIndex

You use the McpToolSpec to load the MCP Server tools and pass the output of `enrich_company` directly to your document parser. This turns the JSON payload into a structured node that fits right into your vector index.

Yes, your agent can call `list_segments` as a query-time tool to fetch real-time lists. It then uses that context to filter or rerank documents before generating a response.

Yes, LlamaIndex handles the async tool execution natively. When running multiple lookups like `enrich_person` concurrently, the framework handles the event loop to prevent blocking your main query thread.

You can pass an allowed_tools filter when setting up your MCP Client. This lets you restrict the engine to only run `identify_company` while locking down the other tools.

Email addresses sent to `enrich_person` are transmitted via encrypted HTTPS directly to the API endpoint and are never stored in our query logs. The resulting profile data is only stored in your local vector index, giving you complete control over your customer data.

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