How to Use the Toky MCP in AutoGen

Q: How do I verify a contact's existence using Toky and AutoGen?

You use getcontact for specific checks. If that fails, you run listcontacts to get a full list of records the agents can debate over.

Q: Can I initiate communication flows with Toky and AutoGen?

Yes. You can use sendsms to send texts, or you can call createcontact if the agent determines a new record is needed for later deliberation.

Q: Does the MCP Server help me check on Toky agents with AutoGen?

You use getagent to pull details, or listagents to get an overview. This information feeds into agent discussions for consensus building.

Q: What is the best way to see call history using Toky and AutoGen?

Use listcalls. The agents can then use this list as evidence, debating whether a missed call needs follow-up action or if the voicemail is sufficient.

Force multi-agent consensus on Toky data using AutoGen for complex decisions.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Toky MCP to AutoGen

Create your Vinkius account to connect Toky 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 Toky with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debate current status with the MCP Server

Agents can challenge each other's assumptions by calling `get_call` to check call records. They can also use `get_contact` and `get_voicemail` to verify if a person is available or if messages were left. This allows your AutoGen system to achieve consensus on the current communication status before taking action.

Plan actions using Toky data in AutoGen

The system plans by calling `list_agents` first. If a new interaction is needed, it can call `create_contact` to establish the record, and then use `send_sms` to execute the action. This multi-step decision process simulates how humans negotiate communication strategies.

Gather comprehensive context via MCP Server

Need a full picture? Agents can call `list_calls`, `list_contacts`, and `list_voicemails`. These tools feed all available evidence into the conversation loop. The agents debate which resource is most critical, forcing them to justify their choices based on the totality of the data.

Setup guide

Set up Toky 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 Toky 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="Toky_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

You use `get_contact` for specific checks. If that fails, you run `list_contacts` to get a full list of records the agents can debate over.

Yes. You can use `send_sms` to send texts, or you can call `create_contact` if the agent determines a new record is needed for later deliberation.

You use `get_agent` to pull details, or `list_agents` to get an overview. This information feeds into agent discussions for consensus building.

Use `list_calls`. The agents can then use this list as evidence, debating whether a missed call needs follow-up action or if the voicemail is sufficient.

This server handles core communication records, including contact details, call logs, agent information, and messaging content.

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