How to Use the HelpCrunch MCP in LlamaIndex

Q: How do I load HelpCrunch tools into LlamaIndex?

Install llama-index-tools-mcp and set up a BasicMCPClient. Call mcptoolspec.totoollistasync() and pass the array directly to your FunctionAgent.

Q: Can LlamaIndex update a HelpCrunch chat status?

Yes. The updateconversationstatus tool changes a ticket from open to closed. Your agent can do this automatically after successfully retrieving and delivering an answer from the vector store.

Q: How do I find specific HelpCrunch users in LlamaIndex?

The searchcustomers tool lets the agent look up profiles using email filters. It pulls the raw JSON, which you can then index or use for immediate context.

Q: Can the AI reply directly to a customer?

Your agent can trigger sendchatmessage to post responses. It formats the answer based on the retrieved RAG context and sends it straight to the live chat widget.

Index your HelpCrunch support history into LlamaIndex to build a searchable, grounded MCP knowledge base.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect HelpCrunch MCP to LlamaIndex

Create your Vinkius account to connect HelpCrunch 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 HelpCrunch with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index past conversations

The `list_conversations` tool pulls your entire chat history into LlamaIndex for immediate vectorization. Instead of just answering questions blindly, your RAG application queries past resolved tickets to see how human agents handled similar issues. You stop hallucinating answers and start repeating proven solutions. You can drill deeper by calling `list_messages_in_chat` for specific threads. The framework chunks these transcripts and embeds them into your vector store. When a new customer asks a complex question, the AI retrieves the exact technical steps a human typed out three months ago.

Ground answers in live customer data

The `get_customer_details` tool fetches real-time account status before generating a response. Your application checks if the user is a premium subscriber or a free tier trialist. The RAG pipeline then shapes its answer based on actual account limits rather than generic documentation. If the user does not exist, `create_customer` lets the AI build a profile on the fly. You feed the resulting ID right back into the index, keeping your vector store perfectly synced with your live HelpCrunch database.

Analyze webhook setups with this MCP Server

The `list_active_webhooks` tool extracts your current integration routing rules. LlamaIndex indexes these configurations so your internal developer tools can query how data moves out of your support system. A developer can ask the AI where billing notifications go. The agent checks the semantic index, finds the webhook payload definitions, and returns the exact endpoint URL. It turns messy backend configurations into plain English answers.

Setup guide

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

Install `llama-index-tools-mcp` and set up a `BasicMCPClient`. Call `mcp_tool_spec.to_tool_list_async()` and pass the array directly to your `FunctionAgent`.

Yes. The `update_conversation_status` tool changes a ticket from open to closed. Your agent can do this automatically after successfully retrieving and delivering an answer from the vector store.

The `search_customers` tool lets the agent look up profiles using email filters. It pulls the raw JSON, which you can then index or use for immediate context.

Your agent can trigger `send_chat_message` to post responses. It formats the answer based on the retrieved RAG context and sends it straight to the live chat widget.

The MCP integration pulls raw chat transcripts and customer names. The connection runs through ephemeral zero-trust architecture, ensuring your API credentials never leak into the broader vector store or external logging tools.

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