How to Use the Onpipeline MCP in AutoGen

Q: Is my organization's company data secure?

Company profiles and contact records fetched via listcrmorganizations are never stored by Vinkius. Every transaction runs in an ephemeral sandbox that is wiped clean immediately after the execution completes, keeping your CRM records safe.

Run multi-agent debates over your Onpipeline sales strategies using AutoGen to optimize your close rates.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Onpipeline MCP to AutoGen

Create your Vinkius account to connect Onpipeline 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 Onpipeline with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Resolve pipeline bottlenecks with AutoGen agents

Complex sales strategies require debate. With this MCP Server, your AutoGen agents can analyze your sales pipeline using `list_pipelines` and argue about where deals are getting stuck. One agent reviews deal velocity while another checks activity logs from `list_activities`. They reach a consensus on which deals need immediate attention before presenting the final list to your team.

AutoGen agents debate deal risk assessments

Do not let risky deals slip through your fingers unnoticed. Your AutoGen setup can run a risk analysis by passing `get_deal_details` to a specialized evaluation agent. The evaluation agent challenges the sales rep's optimism by comparing the deal's history to past patterns. If the deal lacks recent touchpoints in `list_crm_events`, the agents flag it as high risk and alert the manager.

Multi-agent consensus on lead validation

Bad data ruins CRM performance. Before adding new records, AutoGen agents can cross-reference inbound leads against existing companies using `list_crm_organizations`. A validation agent checks for duplicates, while a separate routing agent decides on the pipeline stage. Once they agree, the system runs `create_crm_contact` and `create_crm_deal` to log the clean prospect.

Setup guide

Set up Onpipeline 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 Onpipeline 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="Onpipeline_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

The framework passes tool execution results through the conversational history. When one agent calls `get_deal_details`, all other agents in the group chat can see the returned CRM fields.

Yes, you can configure the agent profiles to only register read-only tools like `list_crm_contacts`. This prevents agents from running write tools like `create_crm_deal` without human approval.

The McpToolAdapter automatically translates the JSON schemas of this MCP Server into the format AutoGen expects. You do not need to write manual conversion code.

Yes, this server supports both stdio and streamable HTTP transports. You can run it locally or host it on Vinkius and connect via HTTP.

Company profiles and contact records fetched via `list_crm_organizations` are never stored by Vinkius. Every transaction runs in an ephemeral sandbox that is wiped clean immediately after the execution completes, keeping your CRM records safe.

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