How to Use the Pipeliner MCP in AutoGen

Q: Can I create a 'manager' agent in AutoGen to approve actions on Pipeliner?

Yes, that's a perfect use case. You can set up a GroupChatManager that requires human input before an agent can act. The agents would propose a plan based on data from this MCP server, and you'd give the final go-ahead.

Q: How do I connect AutoGen to the Pipeliner MCP Server?

Use the mcpservertools function from the autogen-ext library. Just provide your server URL, and it generates a list of Pipeliner tools that you can pass directly to your AssistantAgent constructor.

Create teams of AutoGen agents that debate and manage your Pipeliner CRM. Let them collaborate to find the best sales strategy.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Pipeliner MCP to AutoGen

Create your Vinkius account to connect Pipeliner to AutoGen — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Pipeliner with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Multi-Agent Sales Analysis

Don't rely on a single agent's opinion. With AutoGen, you can create a team of specialist agents that work together. One agent can act as a "Sales Analyst," using `list_pipeliner_opportunities` to find high-value deals. A second agent, the "Risk Manager," can then take those deals and use `list_pipeliner_activities` to check if they have recent follow-ups. The agents discuss their findings and present a consensus view on pipeline health. It's automated, collaborative analysis.

Debate CRM Strategy with an AutoGen MCP Server

AutoGen's power is conversation. Your agents don't just execute tasks; they challenge each other. The Pipeliner tools provide the raw data for their debate. Imagine an agent pulling user workloads with `list_pipeliner_tasks` and arguing a team member is overloaded. Another agent could counter by pulling their closed deals from `list_pipeliner_opportunities`, arguing the workload is justified by performance. This MCP server provides the facts for that debate.

Automate Complex CRM Decisions

Some decisions aren't simple. You can build an AutoGen group chat to decide how to assign new leads. One agent gets the new leads with `list_pipeliner_leads`. Another agent checks team availability via `list_pipeliner_users` and their current tasks. A "Manager" agent oversees their conversation and makes the final assignment decision based on their arguments. This is how you automate nuanced workflows that normally require a human meeting.

Setup guide

Set up Pipeliner 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 Pipeliner 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="Pipeliner_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

You define different roles for them and give them access to the Pipeliner tools. For example, one agent's prompt focuses on finding new leads with `list_pipeliner_leads`, while the other's is to research those leads' accounts using `list_pipeliner_accounts`. They then share results in the group chat.

Yes, that's a perfect use case. You can set up a `GroupChatManager` that requires human input before an agent can act. The agents would propose a plan based on data from this MCP server, and you'd give the final go-ahead.

Use the `mcp_server_tools` function from the `autogen-ext` library. Just provide your server URL, and it generates a list of Pipeliner tools that you can pass directly to your `AssistantAgent` constructor.

A great starter is a daily pipeline health check. Create one agent to pull open opportunities using `list_pipeliner_opportunities` and another to find associated overdue tasks with `list_pipeliner_tasks`. They can then collaborate to produce a summary report.

The data is shared within your agent group chat, which runs on your infrastructure. The Vinkius server's role is to securely fetch the Pipeliner data—like tasks or account details—for your agents on demand. Each transaction is isolated and no CRM data is stored on Vinkius servers.

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