How to Use the Formilla MCP in LlamaIndex

Q: Can I filter which Formilla contacts get indexed in LlamaIndex?

Yes. You can have your agent run searchcontacts with a specific query, or use listsegments to only pull contacts that belong to a certain customer group.

Index your Formilla chat logs and contact profiles into LlamaIndex to build a searchable knowledge base of customer interactions.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Formilla MCP to LlamaIndex

Create your Vinkius account to connect Formilla 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 Formilla with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index live chat history for semantic search

LlamaIndex agents don't just read data; they index it. By calling `get_conversation`, your agent pulls down raw chat transcripts and stores them as document nodes in your vector database. This lets you run semantic queries across months of customer chats. Instead of guessing keywords, your agent searches the vector store to find how support reps solved specific issues in past conversations.

Ground agent responses in real customer profiles

Avoid hallucinated support responses by giving your agent direct access to customer facts. The agent uses `get_contact_by_email` to check who they are talking to before generating any answers. By combining profile details from `get_contact` with your indexed documentation, the LlamaIndex agent writes responses that match the customer's actual plan, location, and history.

Build a dynamic RAG pipeline using this MCP Server

Feed live customer data directly into your retrieval-augmented generation pipelines. This MCP Server lets your agent use `list_visitors` and `list_segments` to understand who is currently browsing your site. This context determines which documents the agent retrieves. A visitor on a pricing page gets different context than a customer looking at technical API docs, making your automated support much more relevant.

Setup guide

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

You use the McpToolSpec to fetch the tools, then let your agent call list_conversations or list_contacts. The output can be wrapped in Document objects and added to your vector index.

Yes. You can have your agent run search_contacts with a specific query, or use list_segments to only pull contacts that belong to a certain customer group.

Install llama-index-tools-mcp, initialize the BasicMCPClient with your Vinkius endpoint, and convert the tools using to_tool_list_async(). You can then pass these tools directly to your FunctionAgent.

Yes. Your agent can search your knowledge base to answer a question, and then immediately call upsert_contact or update_contact to note that the customer's issue was addressed.

No. Your API keys are kept in your local environment variables, and customer records—including email addresses and chat logs—only flow through memory during tool execution. Vinkius uses zero-trust, ephemeral V8 isolates running your MCP server that never store your 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