How to Use the Heymarket MCP in LlamaIndex

Q: How do I load Heymarket tools into LlamaIndex?

Run pip install llama-index-tools-mcp. Create a BasicMCPClient pointing to your URL, wrap it in an McpToolSpec, and await the async tool list method.

Q: Can LlamaIndex search through Heymarket contacts?

The listcontacts tool supports filtering by phone number. Your agent queries this endpoint before generating a response about a specific user.

Q: How do I send texts from a LlamaIndex application?

Pass the sendsmsmessage tool to your FunctionAgent. It requires a memberid and a tonumber to successfully dispatch the text.

Q: Can I restrict which Heymarket tools the MCP Server exposes?

Use the allowedtools filter when configuring your tool spec. You might only want indexing tools enabled while blocking write actions like updatechatstatus.

Index Heymarket SMS threads into LlamaIndex vector stores to build semantic search over your customer conversations.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Heymarket MCP to LlamaIndex

Create your Vinkius account to connect Heymarket 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 Heymarket with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index SMS history with LlamaIndex

Customer conversations hold massive value, but they usually stay locked inside the inbox. This MCP Server lets your RAG applications pull raw text data directly into your vector stores. Your agent calls `get_chat_history` and `get_message_details` to ingest threads. LlamaIndex embeds those texts, making years of customer interactions fully searchable for your support team.

Ground answers in Heymarket data

AI clients hallucinate when they lack context. You fix this by giving your FunctionAgent real-time access to your communications platform. When a manager asks about a specific client, the agent runs `list_contacts` to find the user and `list_active_chats` to check their current status. The final answer relies entirely on live API data.

Manage contacts via this MCP Server

Your knowledge base needs accurate metadata to function properly. RAG pipelines can actively maintain your directory instead of just reading it. If an indexed document reveals a phone number change, the agent triggers `update_contact_profile`. It also executes `create_contact` when it identifies new leads in unstructured text files.

Setup guide

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

Run `pip install llama-index-tools-mcp`. Create a BasicMCPClient pointing to your URL, wrap it in an McpToolSpec, and await the async tool list method.

The `list_contacts` tool supports filtering by phone number. Your agent queries this endpoint before generating a response about a specific user.

Pass the `send_sms_message` tool to your FunctionAgent. It requires a member_id and a to_number to successfully dispatch the text.

Use the allowed_tools filter when configuring your tool spec. You might only want indexing tools enabled while blocking write actions like `update_chat_status`.

The Vinkius architecture isolates your MCP Server in a secure V8 sandbox. Text message bodies, customer names, and internal team IDs from `list_team_members` pass through memory only. Authentication is fully managed via your endpoint token to prevent unauthorized data access.

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