How to Use the Funil de Vendas MCP in AutoGen

Q: How do I connect Funil de Vendas to AutoGen?

Install autogen-extmcp. Use mcpservertools with StreamableHttpServerParams to load the endpoints, then pass the resulting list into your AssistantAgent constructor.

Q: Can multiple AutoGen agents interact with Funil de Vendas simultaneously?

Yes. Your agents share the toolset. One might run listcompanies to verify an account exists, while another prepares the payload for createopportunity.

Q: How do AutoGen agents handle Funil de Vendas custom fields?

They query listcustomfields first. The agents use that schema to format their subsequent creation or update requests correctly.

Let AutoGen agents debate and manage your Funil de Vendas pipeline autonomously.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Funil de Vendas MCP to AutoGen

Create your Vinkius account to connect Funil de Vendas 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 Funil de Vendas with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Negotiate Deal Progression in AutoGen

This MCP server exposes the Funil de Vendas API to Microsoft's multi-agent framework. A qualification agent reviews a lead and proposes calling `update_opportunity`, while a compliance agent reviews the missing data and pushes back. They debate the deal stage based on raw output from `get_opportunity`. Once the agents reach a consensus, the primary actor executes the update, ensuring no deal moves forward without passing multiple validation checks.

Automate Entity Creation

Complex sales setups require careful data entry. Your AutoGen agents coordinate to execute `create_company` and `create_person` in the correct sequence based on parsed conversation logs. One agent validates the input against `list_custom_fields` to ensure required data is present. Another agent handles the actual creation, preventing duplicate records through strict pre-flight checks.

Analyze Metrics via MCP Server

Management agents need accurate data to forecast revenue. They pull `list_opportunities` and `get_people_stats` to build a complete picture of the current sales cycle. Different analytical agents interpret the data from `get_account_info` and `list_funnels`. They argue over conversion rates and pipeline health until they produce a unified, highly scrutinized sales report.

Setup guide

Set up Funil de Vendas 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 Funil de Vendas 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="Funil de Vendas_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Funil de Vendas 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="Funil de Vendas_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Funil de Vendas 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 Funil de Vendas. 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 Funil de Vendas 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 Funil de Vendas MCP in AutoGen

Install `autogen-ext[mcp]`. Use `mcp_server_tools` with `StreamableHttpServerParams` to load the endpoints, then pass the resulting list into your AssistantAgent constructor.

Yes. Your agents share the toolset. One might run `list_companies` to verify an account exists, while another prepares the payload for `create_opportunity`.

They query `list_custom_fields` first. The agents use that schema to format their subsequent creation or update requests correctly.

The MCP architecture allows local agents to deliberate over CRM data. They pull records via `get_opportunity` and argue about the correct next steps before taking action.

Pipeline statistics and customer profiles are processed entirely within your multi-agent environment. The server acts as a direct, stateless bridge between the CRM API and your local execution context.

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