How to Use the Freshsales MCP in LangChain

Q: How do I connect the Freshsales MCP Server to my LangChain agent?

Install langchain-mcp-adapters and use the MultiServerMCPClient pointing to your Vinkius HTTP endpoint. Call client.gettools() to pull all ten sales tools directly into your agent constructor.

Build multi-step LangChain pipelines that instantly query your CRM and update sales pipelines without writing custom API wrappers.

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 LangChain

Create your Vinkius account to connect Freshsales to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain lead creation directly into LangChain workflows

The `create_lead` tool lets your LangChain agent write new prospects straight to your CRM as soon as they hit your system. Your agent handles the incoming payload, checks for the required `last_name`, and pushes the record without forcing you to write boilerplate glue code. Because LangChain chains these actions, the output of this call immediately feeds the next step in your pipeline. You instantly run a `list_leads` check to verify the record exists or pass the new lead ID to other nodes in your graph.

Trace sales activity with LangSmith and MCP Server tools

This MCP Server exposes `list_tasks` and `list_appointments` so your LangChain agent tracks what your sales reps are actually doing. You get absolute visibility into every tool call via LangSmith, showing you the exact inputs and outputs of your CRM queries in real time. Debugging broken pipelines becomes trivial when you can see the exact payload your agent pulled from the CRM. If a rep forgets to log an appointment, your agent spots the gap by running `list_tasks` and alerts the team before the deal goes cold.

Automate deal tracking across multi-server pipelines

The `list_deals` tool, when combined with `list_sales_accounts`, monitors your entire sales pipeline from a single run. The agent grabs active deals, maps them to their respective company accounts, and flags stagnation before it hurts your quarterly numbers. By combining these tools with other APIs in a single LangChain agent, you build a self-correcting pipeline. Your agent queries the CRM, checks internal databases, and updates deal stages based on actual customer behavior instead of rep guesswork.

Setup guide

Set up Freshsales MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Freshsales tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "freshsales-alternative-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Freshsales transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

Install `langchain-mcp-adapters` and use the `MultiServerMCPClient` pointing to your Vinkius HTTP endpoint. Call `client.get_tools()` to pull all ten sales tools directly into your agent constructor.

Yes, your LangChain agent runs sequential operations like calling `list_leads` and then immediately running `get_lead` to inspect specific prospect details. The output of each tool flows directly into the next step of the chain.

LangSmith traces every single CRM call, showing you the exact payloads sent to `list_deals` or `list_tasks`. You see the latency, token costs, and raw JSON responses without needing custom logging code.

No, the MCP client is stateless by default, but you can use `client.session()` to keep your LangChain agent's CRM context active across multiple turns. This ensures your agent remembers previous queries when running `list_notes` or `list_appointments`.

Your leads, deals, and contacts stay secure inside the Vinkius V8 Isolate Sandbox, which isolates every execution environment. No CRM credentials or raw data are ever stored on disk, and all API communication happens over an encrypted, ephemeral tunnel.

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