How to Use the Nimble CRM MCP in AutoGen

Q: What's the best way to use AutoGen and Nimble CRM to manage sales tasks?

Create a 'Manager' agent that periodically calls listactivities to check for overdue tasks. It can then initiate a conversation with a 'Rep' agent, presenting the overdue tasks and asking for a status update, which can then be logged with addnotetocontact.

Q: Do I need to manually convert the Nimble CRM tool schemas for AutoGen?

No, the autogen-extmcp package handles it. You use mcpservertools to get the tools from the server, and the McpToolAdapter automatically converts them into a format that AssistantAgent understands.

Q: How is data privacy handled for my Nimble CRM user info when using AutoGen?

The getme tool fetches your user profile from Nimble CRM, but this data is only passed to your AutoGen agent conversation. Our ephemeral MCP server processes the request and doesn't log or store your personal user details. The security of the data depends on how you configure your local agent environment.

Create teams of AutoGen agents that debate and collaborate on managing your Nimble CRM, from qualifying leads to updating deal stages.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Nimble CRM MCP to AutoGen

Create your Vinkius account to connect Nimble 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 Nimble CRM with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Sales Workflows

Go beyond single-agent execution. With AutoGen, you can create a team of agents that work together on your Nimble CRM. For instance, a 'Prospector' agent uses `search_contacts` to find leads, while a 'Qualifier' agent reviews their details with `get_contact` to see if they're a fit. This conversational approach surfaces better decisions. The agents can discuss a lead, check existing activity with `list_activities`, and agree on the next step before one of them uses `add_note_to_contact` to log the outcome.

Manage Deals with an AutoGen Agent Team

Updating your sales pipeline becomes a collaborative process. An 'Analyst' agent could use `list_deals` to flag deals that are stalled. A 'Manager' agent could then review the output, use `get_deal` for details, and instruct a 'Rep' agent to follow up. This prevents impulsive actions. Before a deal's stage is changed, agents can debate whether it meets the criteria, checking notes and activities. The final action is a result of consensus, not a single command from one MCP Server call.

Assign Roles for Safer CRM Access

You can build a system where only certain agents are allowed to perform write actions. For example, give your 'Auditor' agent read-only access to tools like `list_contacts` and `get_deal`, but only give the 'Executor' agent permission to use `add_note_to_contact`. The `McpToolAdapter` makes it easy to assign these tools to different `AssistantAgent` instances. The whole conversation, including which agent called which tool and why, is logged. It's a clear audit trail of what's happening in your CRM.

Setup guide

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

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

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

You'd create at least two agents. One agent could generate the note content, and a second, specialized `AssistantAgent` would be given only the `add_note_to_contact` and `search_contacts` tools to execute the update in Nimble CRM after a group chat review.

Yes, that's a perfect use case. You can have a 'Finder' agent that runs `list_deals` based on some criteria. It then passes the list of deal IDs to an 'Analyst' agent, which then calls `get_deal` for each one to perform a deeper analysis.

Create a 'Manager' agent that periodically calls `list_activities` to check for overdue tasks. It can then initiate a conversation with a 'Rep' agent, presenting the overdue tasks and asking for a status update, which can then be logged with `add_note_to_contact`.

No, the `autogen-ext[mcp]` package handles it. You use `mcp_server_tools` to get the tools from the server, and the `McpToolAdapter` automatically converts them into a format that `AssistantAgent` understands.

The `get_me` tool fetches your user profile from Nimble CRM, but this data is only passed to your AutoGen agent conversation. Our ephemeral MCP server processes the request and doesn't log or store your personal user details. The security of the data depends on how you configure your local agent environment.

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