How to Use the Freshsales MCP in LlamaIndex

Q: How do I load Freshsales tools into LlamaIndex?

Install llama-index-tools-mcp and instantiate the BasicMCPClient with your Vinkius URL. Wrap the client in McpToolSpec and call totoollistasync to pass the tools to your LlamaIndex agent.

Q: Is it possible to index live Freshsales data into my LlamaIndex vector store?

Yes, you run listleads or listdeals to pull live records and index them directly into your vector database. This keeps your RAG application updated with real-time CRM data.

Q: Can I filter which CRM tools my LlamaIndex agent can access?

Yes, you use the allowedtools filter in LlamaIndex to restrict your agent to specific operations. For example, you limit an agent to only read tools like listtasks while blocking write operations through the MCP server.

Index your Freshsales CRM data directly into LlamaIndex vector stores to build search pipelines grounded in live sales activity.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Freshsales MCP to LlamaIndex

Create your Vinkius account to connect Freshsales 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 Freshsales with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index active deals into LlamaIndex vector stores

The `list_deals` tool feeds your live sales pipeline directly into LlamaIndex document stores for semantic indexing. Your agent queries this index to find patterns in closed-won deals without writing complex SQL queries against your CRM database. This turns raw CRM records into searchable knowledge. Instead of manually scanning pipelines, you ask your LlamaIndex agent which accounts need attention, and it answers using live data pulled straight from your sales pipeline.

Build RAG applications with Freshsales MCP Server tools

The `list_contacts` and `list_leads` tools pull raw CRM data directly into your LlamaIndex document pipelines. The agent constructs a unified query index, ensuring that sales pitches are grounded in actual customer profiles rather than hallucinations. By feeding these live contacts into your vector index, your RAG pipeline always has access to the latest prospect details. Your agent drafts highly personalized emails because it knows the exact status of every lead in your database.

Surface context from CRM notes and tasks

The `list_notes` and `list_tasks` tools feed raw qualitative feedback and follow-up activities straight into your LlamaIndex vector store. Your agent searches these notes semantically to find recurring customer objections or feature requests across hundreds of accounts. This setup eliminates blind spots in your sales intelligence. Your agent searches the indexed tasks to see if a rep already scheduled a follow-up, preventing duplicate outreach and keeping your CRM hygiene clean.

Setup guide

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

Install `llama-index-tools-mcp` and instantiate the `BasicMCPClient` with your Vinkius URL. Wrap the client in `McpToolSpec` and call `to_tool_list_async` to pass the tools to your LlamaIndex agent.

Yes, you run `list_leads` or `list_deals` to pull live records and index them directly into your vector database. This keeps your RAG application updated with real-time CRM data.

LlamaIndex forces the agent to ground its answers in the actual JSON returned by tools like `get_lead` or `get_contact`. If the data is not in your CRM, the agent will not make it up.

Yes, you use the `allowed_tools` filter in LlamaIndex to restrict your agent to specific operations. For example, you limit an agent to only read tools like `list_tasks` while blocking write operations through the MCP server.

Your contacts, leads, and sales notes are processed in secure, ephemeral V8 isolates that destroy their environment after execution. Vinkius uses zero-trust architecture to ensure your CRM data never leaks into public training models or persistent third-party storage.

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