How to Use the Salespanel MCP in AutoGen

Q: How do my AutoGen agents get access to the Salespanel tools?

You use the mcpservertools function from the autogen-ext library. Just provide your Vinkius server URL, and it returns a list of tools you can register with your AssistantAgent.

Q: What's a good starting agent setup for Salespanel and AutoGen?

Start with two: a UserProxyAgent and an AssistantAgent. Register the Salespanel tools with the assistant. Then, give the user proxy a task like, 'Find the three most active new leads from the past day and summarize their activity.'

Let your AutoGen agents debate and qualify Salespanel leads. Build a team of AI specialists who find, vet, and prioritize your sales pipeline.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Salespanel MCP to AutoGen

Create your Vinkius account to connect Salespanel 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 Salespanel with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Let Your Agents Debate Leads

With AutoGen, you don't have one agent; you have a team. Create a 'Scout' agent that uses `list_anonymous_visitors` and `list_activity_feeds` to find potential leads. It then passes its findings to another agent for review. Then, a 'Profiler' agent can take over. It uses `get_visitor` and `get_company` to enrich the data and presents a summary. This multi-agent conversation ensures a lead is properly vetted from multiple angles before it ever gets to a human.

Build a Sales Ops Team in AutoGen

You can design agents with specific jobs. For example, a 'Compliance' agent's only job is to check a contact against `list_lead_segments`. If a lead is in the 'Existing Customer' segment, it vetoes any outreach. Meanwhile, a 'Growth' agent might be arguing to engage with every new lead from `list_contacts`. AutoGen lets them debate based on the data from this MCP server. The final decision is a consensus, not a single-threaded command. It's a more robust way to automate decisions.

Simulate Your Sales Workflow

This MCP server gives your agents the raw material to work with. They can pull account lists with `list_accounts` and `list_companies`, see who's active with `list_engagement_events`, and get contact details with `get_contact_details`. The power of AutoGen is modeling the handoffs. One agent finds the lead, another enriches it, a third one checks for conflicts, and a final 'Notifier' agent summarizes the result for the sales team. You're building an automated assembly line for lead intelligence.

Setup guide

Set up Salespanel 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 Salespanel 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="Salespanel_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

You use the `mcp_server_tools` function from the `autogen-ext` library. Just provide your Vinkius server URL, and it returns a list of tools you can register with your `AssistantAgent`.

Yes, and they should. The core idea of AutoGen is conversation. One agent can use `list_anonymous_visitors` to propose a lead, and another can use `get_company` to challenge or confirm its value.

In the agent's system message, give it a specific persona and goal. For example: 'You are a Data Analyst. Your only job is to use `list_activity_feeds` from Salespanel to find patterns. Do not suggest outreach.'

Start with two: a `UserProxyAgent` and an `AssistantAgent`. Register the Salespanel tools with the assistant. Then, give the user proxy a task like, 'Find the three most active new leads from the past day and summarize their activity.'

Your agents will access Salespanel contact information, lead segments, and company details. Vinkius ensures this data stays in-flight, processing it within a secure sandbox that's destroyed after each operation. Your token is the single point of authentication.

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