How to Use the Freshsales (Sales CRM & Lead Scoring API) MCP in LangChain

Q: How do I connect Freshsales (Sales CRM & Lead Scoring API) to LangChain?

Install langchain-mcp-adapters and use the MultiServerMCPClient. Pass the HTTP URL to the client, call gettools(), and feed the list to your ReAct agent.

Q: Can LangChain agents search the Freshsales (Sales CRM & Lead Scoring API) database?

Yes. Your agent can execute searchglobal to find records across the entire CRM. It then uses getlead or getdeal to pull the specific details it needs.

Q: What happens if a LangChain tool call fails in Freshsales (Sales CRM & Lead Scoring API)?

LangSmith traces the exact failure point. If convertlead rejects a request missing a company name, your agent sees the error output and can ask the user for the missing data.

Q: Does this MCP integration support lead scoring filters?

You can pull filtered lists using listleads. You just need to provide the specific view ID from the filters API to get the right subset of leads.

Build reliable sales pipelines in LangChain by linking Freshsales CRM actions into observable MCP tool chains.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Freshsales (Sales CRM & Lead Scoring API) MCP to LangChain

Create your Vinkius account to connect Freshsales (Sales CRM & Lead Scoring API) 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 (Sales CRM & Lead Scoring API) with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Freshsales Lead Routing with LangChain

Your ReAct agent can grab an incoming prospect and push them right into your pipeline. It calls `create_lead` using just a first name or email. If the prospect already exists, the agent catches the duplicate and runs `update_lead` instead. The output from that update feeds directly into the next link in your chain. Your agent can immediately trigger `create_task` to assign follow-up duties to an SDR. Every step logs to LangSmith, so you see exactly which tool fired and how many tokens it burned.

Manage Deals via this MCP Server

Moving leads across the finish line requires precise API calls. LangChain agents use `convert_lead` to flip a qualified prospect into a contact, demanding the mandatory last name and company name fields. Once converted, the chain continues. The agent executes `create_deal` to open an opportunity, then pulls `list_deal_stages` to place it in the correct funnel step. You build the logic once, and the agent handles the state transitions.

Query Sales Data with ReAct Agents

Sometimes your agent needs context before taking action. It can run `search_global` to sweep across all Freshsales entities, hunting for a specific company name or email address. If you need precise field matches, the agent switches to `search_lookup`. It finds the exact record, then uses `get_account` or `get_contact` to pull the full profile into the LangChain session context. No blind updates, just verified data.

Setup guide

Set up Freshsales (Sales CRM & Lead Scoring API) 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 (Sales CRM & Lead Scoring API) 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-sales-crm-lead-scoring-api-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 (Sales CRM & Lead Scoring API) 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 (Sales CRM & Lead Scoring API) 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 (Sales CRM & Lead Scoring API) MCP in LangChain

Install `langchain-mcp-adapters` and use the MultiServerMCPClient. Pass the HTTP URL to the client, call `get_tools()`, and feed the list to your ReAct agent.

Yes. Your agent can execute `search_global` to find records across the entire CRM. It then uses `get_lead` or `get_deal` to pull the specific details it needs.

LangSmith traces the exact failure point. If `convert_lead` rejects a request missing a company name, your agent sees the error output and can ask the user for the missing data.

You can pull filtered lists using `list_leads`. You just need to provide the specific view ID from the filters API to get the right subset of leads.

LangChain itself is stateless unless you configure a persistent session. Your sensitive pipeline data, including contact emails and deal values, passes through the V8 isolate sandbox directly to your agent's memory and is destroyed when the process terminates.

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