How to Use the Freshworks MCP in LlamaIndex

Q: How do I load Freshworks data into LlamaIndex?

Install llama-index-tools-mcp and instantiate a BasicMCPClient. Call totoollistasync() and pass the resulting tools to your FunctionAgent.

Q: Can LlamaIndex embed the Freshworks ticket text automatically?

You use the tools to fetch the raw text via getticket. Your application then passes that text to an embedding model before storing it in your vector database.

Q: Can I restrict which MCP tools the indexer uses?

Yes. You can apply an allowedtools filter when configuring the client. This keeps your agent focused on support data without touching sales pipelines.

Q: Where do the CRM contacts go during indexing?

Names and emails pulled from listcrmcontacts pass through an ephemeral, zero-trust container. Vinkius never logs the payload, so your customer identities remain secure in transit to your private vector store.

Turn your Freshworks helpdesk into a searchable LlamaIndex knowledge base. Ground your agents in real customer data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Freshworks MCP to LlamaIndex

Create your Vinkius account to connect Freshworks 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 Freshworks with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Freshworks Tickets with LlamaIndex

The `list_tickets` and `get_ticket` tools let your LlamaIndex pipelines ingest raw customer support histories directly through this MCP Server. You pull thousands of resolved issues and embed them into your vector store. Your agents stop guessing how to solve problems and start quoting actual past resolutions. When a new support request comes in, your RAG application queries the index for similar past tickets. It finds the exact steps a human took to fix the bug three months ago. You get answers based on your company's actual operational data.

Search Across Sales Deals

This MCP connection exposes `list_deals` and `list_accounts` so you can build semantic search over your active pipeline. The agent pulls the deal size, stage, and company information, then indexes it alongside your internal sales playbooks. A sales rep queries the index asking for examples of closed-won deals in the manufacturing sector. The system retrieves the exact deal records from the CRM and synthesizes a strategy based on what actually worked.

Map the Organizational Chart

Your application uses `list_agents`, `list_groups`, and `list_companies` to understand who works where. It pulls the internal support structure and the external customer hierarchies into a unified graph. You can ask your agent who handled the most critical tickets for a specific enterprise client. It cross-references the company ID with the agent groups and returns a factual summary. The data stays fresh because the tools pull directly from the source.

Setup guide

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

Install `llama-index-tools-mcp` and instantiate a `BasicMCPClient`. Call `to_tool_list_async()` and pass the resulting tools to your `FunctionAgent`.

You use the tools to fetch the raw text via `get_ticket`. Your application then passes that text to an embedding model before storing it in your vector database.

Standard calls return JSON that agents forget. Indexing the output from `list_crm_contacts` means your agent can perform semantic similarity searches across thousands of users instantly.

Yes. You can apply an `allowed_tools` filter when configuring the client. This keeps your agent focused on support data without touching sales pipelines.

Names and emails pulled from `list_crm_contacts` pass through an ephemeral, zero-trust container. Vinkius never logs the payload, so your customer identities remain secure in transit to your private vector store.

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