How to Use the Nutshell CRM MCP in AutoGen

Enable multi-agent debate in AutoGen by connecting this MCP server to Nutshell CRM for collaborative, consensus-driven sales tasks.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Nutshell CRM MCP to AutoGen

Create your Vinkius account to connect Nutshell CRM 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 Nutshell CRM with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Deploy CRM tools in AutoGen

Give your agents access to `get_lead_details` and `get_account_details` so they can debate specific data points. Multiple agents can now review the same record to reach a consensus on sales priorities. This setup allows for specialized agents to challenge each other's interpretations of CRM data. It ensures your final output is vetted by multiple perspectives before any action is taken.

Manage CRM lists with MCP Server

Use `list_leads` and `list_contacts` to feed your agent team the data they need for negotiation. Each agent evaluates the list according to its own logic, leading to more robust decision-making. The server handles schema conversion automatically, allowing your agents to focus on the conversation. They spend less time on formatting and more time on high-level strategy.

Coordinate via universal search

The `universal_search` tool provides a common ground for your agents to find and discuss entity information. It prevents information silos by keeping the agent team synchronized on the same CRM facts. When agents disagree, they use this tool to verify their data. This iterative process creates a reliable system for managing your sales relationships.

Setup guide

Set up Nutshell CRM 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 Nutshell CRM 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="Nutshell CRM_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Nutshell CRM 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="Nutshell CRM_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Nutshell CRM 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 Nutshell CRM. 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 Nutshell CRM 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 Nutshell CRM MCP in AutoGen

You pass the tool list to your AssistantAgent constructor. The agents then invoke these tools during their discussions to inform their decisions.

Yes. You can assign a verification agent to double-check the results of any `list_leads` call. This creates a secure, multi-step validation loop for your sales data.

The MCP server uses ephemeral connections for every request. No CRM data is persisted between sessions, keeping your lead information safe from unauthorized access.

You can introduce a human-in-the-loop agent to mediate the discussion. It can manually inspect the tool outputs and guide the agents to a resolution.

The server is built to handle concurrent requests from multiple agents. You just need to ensure your total API usage stays within the CRM rate limits.

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