How to Use the Toket MCP in AutoGen

Q: How does Toket help with multi-agent debate in AutoGen?

AutoGen agents can talk about the tools. One agent might say, 'We should check listmints first,' and a second agent might argue, 'No, we need to use getgastankstatus before committing resources.' The debate leads to a decision.

Q: If I need to track minting, how does AutoGen handle it?

You can set up agents that repeatedly call tools like listmints and getmintstatus. They don't just report the data; they debate if the trend is positive or negative based on what they find.

Q: What should I pass to my AutoGen setup for Toket?

You use mcpservertools with your endpoint URL. This adapter automatically handles converting all of Toket's tool schemas into a format that the AssistantAgent can understand and discuss.

Get consensus on NFT strategies with AutoGen agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Toket MCP to AutoGen

Create your Vinkius account to connect Toket 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 Toket with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Determine Minting Strategy

The `easy_mint` tool performs a quick mint. But instead of just running it, you can have an agent debate whether to use it versus the more controlled process via `mint_nft`. Agents argue for speed vs. control, and you get the decision.

Validate New Collections

You start by using `list_collections` so a 'Risk Agent' can check for duplicates or policy violations. Then, another agent uses `create_collection`, but only after consensus is reached on the required name and symbol.

Verify Payment Readiness

A performance agent needs to know if payments are possible; it checks using `get_gas_tank_status`. A compliance agent might then use `get_collection` to verify that the target collection is active before approving any transaction.

Setup guide

Set up Toket 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 Toket 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="Toket_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

AutoGen agents can talk *about* the tools. One agent might say, 'We should check `list_mints` first,' and a second agent might argue, 'No, we need to use `get_gas_tank_status` before committing resources.' The debate leads to a decision.

Absolutely. You can build systems where a 'Strategy Agent' proposes using `create_collection`, and then a 'Validator Agent' must confirm the owner wallet before execution is approved.

You can set up agents that repeatedly call tools like `list_mints` and `get_mint_status`. They don't just report the data; they debate if the trend is positive or negative based on what they find.

You use `mcp_server_tools` with your endpoint URL. This adapter automatically handles converting all of Toket's tool schemas into a format that the AssistantAgent can understand and discuss.

This MCP Server touches Collection Metadata and Mint Status. Because agents are debating actions, you'll want to monitor which specific transaction identifiers or collection details they decide to use.

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