How to Use the Mav MCP in LlamaIndex

Q: How do I initialize the Mav tool spec in LlamaIndex?

Install llama-index-tools-mcp and instantiate the BasicMCPClient with your Vinkius URL. Pass this client to McpToolSpec and call totoollistasync() to expose the SMS capabilities to your agent.

Q: Can I restrict which Mav playbooks my LlamaIndex agent accesses?

Yes, you can apply the allowedtools filter when initializing your tool specification in LlamaIndex. This ensures your query engine only triggers specific qualification playbooks while ignoring administrative functions.

Index your Mav SMS qualification history directly into LlamaIndex vector stores for 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 Mav MCP to LlamaIndex

Create your Vinkius account to connect Mav 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 Mav with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index SMS playbook runs into LlamaIndex vector stores

The Mav MCP server connects your live SMS lead interactions to your LlamaIndex RAG pipelines. This integration allows you to ingest real-time conversation transcripts and qualification statuses directly into your vector index. You implement this by wrapping the client in `McpToolSpec` and calling `to_tool_list_async()`. The index updates dynamically, giving your agent access to historical SMS context during active user queries.

Ground RAG applications in real SMS conversation data

This MCP Server provides the raw conversational outputs your LlamaIndex query engines need to prevent hallucinations about lead status. Your agent queries the indexed SMS history to verify if a prospect already opted in before sending duplicate messages. By feeding these live data streams into your `FunctionAgent`, you build search systems that know exactly what was promised to a customer over text. The agent retrieves the ground-truth logs instead of guessing.

Query historical playbook sessions semantically

The Mav MCP connection lets you perform semantic searches over thousands of past SMS qualification chats to identify why leads drop off. You run natural language queries across your indexed LlamaIndex storage to find common objections. This setup eliminates manual transcript reviews by letting your agent group similar SMS responses automatically. You identify friction points in your playbooks based on actual conversation semantics.

Setup guide

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

Install `llama-index-tools-mcp` and instantiate the `BasicMCPClient` with your Vinkius URL. Pass this client to `McpToolSpec` and call `to_tool_list_async()` to expose the SMS capabilities to your agent.

Yes, you can apply the `allowed_tools` filter when initializing your tool specification in LlamaIndex. This ensures your query engine only triggers specific qualification playbooks while ignoring administrative functions.

Yes, you can use the server to retrieve conversation logs and ingest them directly into your LlamaIndex document store. Once indexed, these transcripts become searchable nodes for your semantic retrieval pipelines.

Yes, LlamaIndex allows you to merge live outputs from the Mav MCP server with static documents in a unified query engine. Your agent can check local product documentation and text the correct answer to a lead.

Vinkius routes all Mav MCP server traffic through an ephemeral, zero-trust V8 Isolate Sandbox. Your raw SMS transcripts and lead phone numbers are never cached or stored on Vinkius servers, maintaining strict data privacy.

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