How to Use the CRM PipeRun MCP in AutoGen

Q: What's the code to give an AutoGen agent access to CRM PipeRun?

After installing autogen-extmcp, you use the mcpservertools function with your Vinkius server URL. This returns a list of tools that you pass directly to your AssistantAgent constructor in the tools parameter.

Let a team of AutoGen agents collaborate to manage your CRM PipeRun pipeline.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CRM PipeRun MCP to AutoGen

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Agents Debate CRM Actions

This server gives your AutoGen team the tools to manage PipeRun. Instead of one agent acting alone, you can have a conversation. One agent might propose using `create_activity` to schedule a demo. A second, more cautious agent could then use `list_activities` to check the client's history and argue that a simple follow-up call is better. This is the core idea of AutoGen: agents challenge each other. They use the PipeRun tools to gather evidence for their arguments, leading to a better, consensus-driven decision before anything is actually changed in your CRM.

Automate CRM Housekeeping

Set up specialized agents for specific roles. An 'archivist' agent can periodically use `list_files` to find files older than one year. It then proposes a list of files to delete to a 'compliance' agent. The compliance agent checks the file details using `get_file` to ensure they aren't part of an active deal. Only after the compliance agent gives the okay does the archivist get permission to call `delete_file`. This conversational workflow prevents mistakes.

Your PipeRun MCP Server

Getting started is straightforward. You give a high-level goal to a user proxy agent, like "Clean up my tasks for the Acme account." The assistant agents, armed with the tools from this MCP Server, then collaborate to figure out the specific steps. They'll discuss whether to `update_activity`, `delete_activity`, or create new ones. One agent might even use `get_activity_type` to find the correct ID for a 'task' before another agent calls `create_activity`. They handle the details so you don't have to.

Setup guide

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

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

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

AutoGen manages the conversation flow. One agent proposes an action (like calling `create_activity`), and the others can review, critique, or approve it before it's executed. The final decision is what triggers the actual tool call.

Yes, that's exactly how AutoGen is designed to work. You can create different agents with different roles and give only the 'sales' agent the PipeRun tools. The 'reporting' agent can then ask it to fetch data.

After installing `autogen-ext[mcp]`, you use the `mcp_server_tools` function with your Vinkius server URL. This returns a list of tools that you pass directly to your `AssistantAgent` constructor in the `tools` parameter.

They can and they should. One agent might propose an update, and another can use `get_activity` to pull the current state and argue that the update is unnecessary. This debate helps prevent redundant actions.

This MCP server processes data about your CRM activities and files. Your Vinkius token authenticates every request, and each tool execution happens in a dedicated, secure sandbox. The agents converse, but data only moves when a tool is explicitly called.

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