How to Use the Freshsales MCP in AutoGen

Q: How do I initialize Freshsales tools in AutoGen?

Install the autogen-extmcp package. Pass your Vinkius URL to StreamableHttpServerParams and hand the tools list to your AssistantAgent constructor.

Q: Can multiple AutoGen agents use the Freshsales tools simultaneously?

They share the same tool definitions. The framework's McpToolAdapter handles the schema conversion, allowing any agent in the chat to call CRM functions.

Deploy AutoGen agents that debate Freshsales pipeline strategies and update deal records through consensus.

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 AutoGen

Create your Vinkius account to connect Freshsales to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

AutoGen agents that manage your pipeline

Stop letting a single prompt dictate your sales strategy. You spin up multiple agents that use this MCP Server to fetch pipeline data via `list_crm_deals`. They analyze the board from different angles. A risk-averse agent might flag stalled accounts using `get_deal_details`, while an aggressive agent pushes for immediate follow-ups. They debate the best action before anything gets changed in the CRM.

Multi-agent lead qualification

Lead scoring is too complex for basic rules. Give your AutoGen assistants access to `list_crm_leads` and `get_lead_details`. One agent checks the prospect's industry while another reviews their interaction history. Once they reach an agreement on the lead's quality, a designated executor agent fires `create_crm_lead` to move them into the active pipeline. You just watch the logs and approve the final step.

Coordinate sales activities automatically

Reps forget to log their meetings. Your system can pull `list_appointments` and cross-reference it with `list_crm_tasks`. The agents figure out who missed their updates. They then generate a consolidated report for the sales manager. This happens entirely through conversational turns, requiring zero custom logic on your end.

Setup guide

Set up Freshsales MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Freshsales tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

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

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Freshsales_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Freshsales data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

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

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Freshsales_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Freshsales data")
    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 AutoGen

Install the `autogen-ext[mcp]` package. Pass your Vinkius URL to `StreamableHttpServerParams` and hand the tools list to your `AssistantAgent` constructor.

They share the same tool definitions. The framework's `McpToolAdapter` handles the schema conversion, allowing any agent in the chat to call CRM functions.

You define that in your system prompt. Usually, a designated executor handles `create_crm_lead` after the analyzer agents finish debating the prospect's value.

No. The MCP standard feeds the exact JSON schema straight to the agents. They know exactly what arguments to pass without any extra code.

Only your authenticated client. Extracting prospect emails via `get_lead_details` happens securely over an ephemeral connection. Vinkius manages the auth layer so your credentials never leak into the chat logs.

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