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

Q: How do I limit which Freshsales (Sales CRM & Lead Scoring API) tools a CrewAI agent can use over MCP?

You use the MCPServerHTTP class to filter the exposed endpoints. This lets you give your researcher agent access only to listleads while reserving convertlead for your manager agent.

Q: Can CrewAI agents collaborate to resolve duplicate accounts in the Freshsales (Sales CRM & Lead Scoring API)?

Yes, one agent can run searchglobal to flag potential duplicates. A supervisor agent then reviews the results and runs updatecontact to merge the records without polluting your database.

Q: How do CrewAI agents handle missing data when writing to the Freshsales (Sales CRM & Lead Scoring API)?

If an agent tries to run convertlead without a mandatory last name, the API returns an error. The agent's memory tracks this failure, prompting a search agent to run getlead and find the missing details.

Run autonomous agent teams that qualify leads and update your Freshsales (Sales CRM & Lead Scoring API) using CrewAI and this MCP Server.

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 CrewAI

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent lead qualification

The `list_leads` tool allows a researcher agent to scan your incoming pipeline for unassigned prospects. Once found, a separate analysis agent evaluates the record details to determine if they match your ideal customer profile. If the prospect passes validation, a third agent executes `convert_lead` to graduate them to a contact. This division of labor mimics a human sales development team but operates continuously without manual oversight.

Autonomous deal management via CrewAI MCP Server

The `create_deal` tool is used by your closer agent to open new sales opportunities as soon as a meeting is confirmed. By passing the contact ID from the previous research phase, the framework links the entire workflow and coordinates this action directly. To ensure the pipeline stays organized, another agent runs `list_deal_stages` to place the opportunity in the correct column. This automated hygiene prevents deals from getting lost in generic default stages.

Automated task assignment and scheduling

The `create_task` tool lets your operations agent assign follow-up actions to specific sales reps. Reps get assigned based on current workload after the crew runs `list_owners` to check availability. When a customer requests a demo, the agent invokes `create_appointment` to lock in the time slot. This automation chain guarantees that every high-intent action in your CRM is met with an immediate, scheduled human response.

Setup guide

Set up Freshsales (Sales CRM & Lead Scoring API) MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Freshsales (Sales CRM & Lead Scoring API) tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Freshsales (Sales CRM & Lead Scoring API) Analyst",
    goal="Access and analyze Freshsales (Sales CRM & Lead Scoring API) data via MCP.",
    backstory="Expert analyst with direct Freshsales (Sales CRM & Lead Scoring API) access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Freshsales (Sales CRM & Lead Scoring API) transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Freshsales (Sales CRM & Lead Scoring API) Analyst",
        goal="Access and analyze Freshsales (Sales CRM & Lead Scoring API) data via MCP.",
        backstory="Expert analyst with direct Freshsales (Sales CRM & Lead Scoring API) access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Freshsales (Sales CRM & Lead Scoring API) transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

You use the `MCPServerHTTP` class to filter the exposed endpoints. This lets you give your researcher agent access only to `list_leads` while reserving `convert_lead` for your manager agent.

Yes, one agent can run `search_global` to flag potential duplicates. A supervisor agent then reviews the results and runs `update_contact` to merge the records without polluting your database.

If an agent tries to run `convert_lead` without a mandatory last name, the API returns an error. The agent's memory tracks this failure, prompting a search agent to run `get_lead` and find the missing details.

Yes, the platform supports both stdio and HTTP transports. You can configure your local Python environment to connect directly to the hosted endpoint using your secure Vinkius token.

Your lead details, contact notes, and deal values are never stored on Vinkius servers. All transactions occur via secure, encrypted tunnels directly to the CRM endpoints, and execution environments are completely destroyed after each run.

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