How to Use the Formilla MCP in AutoGen

Q: How do I register Formilla tools with an AutoGen agent?

Use mcpservertools to connect AutoGen to your MCP server and fetch the tool definitions. You then pass this tool list directly into the constructor of your AssistantAgent.

Build AutoGen agent teams that debate support issues, verify contact records, and update Formilla chats through consensus.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Formilla MCP to AutoGen

Create your Vinkius account to connect Formilla 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 Formilla with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run collaborative support triage with AutoGen

AutoGen lets you set up specialized agents that talk to each other to solve customer issues. A triage agent can call `list_conversations` to find new chats, while a CRM agent uses `get_contact` to pull the visitor's profile. They discuss the case in a group chat to decide the best response. Once they agree on a solution, the CRM agent runs `update_contact` to tag the customer, and the support agent drafts the reply.

Validate customer accounts through agent debate

Avoid bad data updates by letting agents check each other's work. When one agent wants to modify a profile, it must first run `get_contact_by_email` and present the details to a supervisor agent. The supervisor agent checks the proposed changes against existing records. Only when both agents agree on the update does the system run `upsert_contact` to commit the changes to your CRM.

Manage live chat queues using this MCP Server

Keep your support queue clean by automating routine checks. This MCP Server lets an agent run `check_formilla_status` to ensure connectivity, then execute `list_visitors` to see who is currently active on your site. If a visitor has been idle for too long, the agent can flag the conversation. For spam or junk records, the team can agree to run `delete_contact` to keep your database tidy.

Setup guide

Set up Formilla 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 Formilla 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="Formilla_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Use mcp_server_tools to connect AutoGen to your MCP server and fetch the tool definitions. You then pass this tool list directly into the constructor of your AssistantAgent.

Yes. You can register the tools with a single user proxy agent or share them across a group chat where agents like a CRM specialist call update_contact while a support specialist reads chat logs.

The McpToolAdapter in the autogen-ext package handles all schema conversions automatically. It translates the server's tool definitions into the format AutoGen's conversational agents expect.

Yes, you can run AutoGen agents in a completely headless terminal or CI/CD environment. They will execute tools like search_contacts or list_segments via standard I/O or HTTP transport.

All transit data—including visitor profiles, conversation transcripts, and segments—is encrypted using TLS. Vinkius runs the MCP server inside a zero-trust sandbox that processes requests in memory and destroys the session immediately after.

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