How to Use the Mnemonic MCP in AutoGen

Q: Can agents debate Mnemonic data in AutoGen?

Yes, agents can challenge the results of getcollectionstats if they find inconsistencies. This leads to more rigorous analysis before any final decision.

Enable multi-agent debate and consensus on NFT market data using AutoGen.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mnemonic MCP to AutoGen

Create your Vinkius account to connect Mnemonic 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 Mnemonic with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent consensus on NFT data

Assign one agent to fetch `get_collection_stats` while another reviews `get_nft_prices`. They debate the findings to reach a consensus on the asset's current value. This approach forces the system to verify data before acting. By having agents challenge each other, you reduce the risk of relying on a single, potentially stale data point.

Security-focused MCP Server negotiation

Use a security agent to audit `list_transfers` for suspicious activity before a trading agent executes a move. They negotiate based on the evidence found in the transfer history. This creates a system where no action is taken without internal agreement. You define the rules, and the agents use the tool data to check for compliance and risk.

Autonomous market research with AutoGen

Let your agents use `search_collections` and `get_collection_details` to explore new opportunities. They collaborate to filter out low-liquidity assets based on your specific investment criteria. They share the workload of processing large datasets. One agent fetches the data, and the other synthesizes it into a report, ensuring the final decision is well-informed.

Setup guide

Set up Mnemonic 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 Mnemonic 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="Mnemonic_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

You provide the tool list to your agents, allowing them to invoke Mnemonic functions as part of their conversation. They decide together which tool to call.

Yes, agents can challenge the results of `get_collection_stats` if they find inconsistencies. This leads to more rigorous analysis before any final decision.

The adapter automatically handles the schema so agents can call tools directly. They negotiate who handles the data retrieval based on their specific roles.

It supports both stdio and Streamable HTTP. You pick the transport that fits your existing agent architecture.

Your agents operate in your environment. They only send requests to Mnemonic for the specific NFT data they need to complete their assigned task.

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