How to Use the Ankr (Web3 Node API) MCP in AutoGen

Q: How do AutoGen agents resolve conflicts when simulating transactions via Ankr (Web3 Node API)?

You can program a critic agent to review the output of ethsimulateV1. If the simulation fails, the critic instructs the proposing agent to adjust the transaction arguments and try again.

Run consensus-driven Web3 operations by exposing the Ankr MCP Server to your AutoGen agent debates.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Ankr (Web3 Node API) MCP to AutoGen

Create your Vinkius account to connect Ankr (Web3 Node API) 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 Ankr (Web3 Node API) with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent consensus on transaction safety

In AutoGen, you don't just execute transactions blindly. You set up a debate where a security agent uses `eth_simulateV1` or `simulateTransaction` to check for execution errors, while a financial agent queries `ankr_getTokenPrice` to verify slippage. They negotiate the optimal parameters before signing. Once both agents agree that the transaction is safe and cost-effective, a third execution agent triggers `eth_sendRawTransaction`. This multi-agent verification reduces the risk of costly smart contract errors.

Collaborative on-chain auditing with this MCP Server

Build a team of specialized agents to audit smart contracts. One agent can watch event logs using `eth_getLogs`, while another inspects the underlying contract code using `eth_getCode`. They coordinate their findings in a group chat to pinpoint potential vulnerabilities. If anomalies are found, a coordinator agent can query `ankr_getInteractions` to see which other addresses are at risk. The entire investigation is handled through structured multi-agent conversations.

Automated portfolio rebalancing via agent negotiation

Let your AutoGen agents manage asset allocations through structured debate. A portfolio agent checks balances using `ankr_getAccountBalance` and identifies underperforming assets. It then proposes a trade to a risk agent, which evaluates gas costs using `eth_estimateGas`. The agents negotiate the trade size and timing based on historical transfer patterns retrieved from `ankr_getTokenTransfers`. Once they reach consensus, they prepare the transaction payload for execution.

Setup guide

Set up Ankr (Web3 Node API) 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 Ankr (Web3 Node API) 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="Ankr (Web3 Node API)_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Ankr (Web3 Node API) 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="Ankr (Web3 Node API)_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Ankr (Web3 Node API) 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 Ankr. 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 Ankr (Web3 Node API) 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 Ankr (Web3 Node API) MCP in AutoGen

Use the AutoGen MCP adapter to fetch the tools from your Vinkius HTTP endpoint. You can then register the complete list of 32 tools with your AssistantAgent instances.

Yes, the MCP Server supports concurrent requests. A security agent can call `eth_estimateGas` while an analysis agent runs `ankr_getTokenPrice` in the same conversation turn.

You can program a critic agent to review the output of `eth_simulateV1`. If the simulation fails, the critic instructs the proposing agent to adjust the transaction arguments and try again.

Yes, the adapter exposes the entire toolset. Your agents can debate cross-chain actions, running `getLatestBlockhash` on Solana and `eth_blockNumber` on Ethereum to coordinate timing.

All tool executions occur inside a secure MCP Server sandbox. The raw RPC payloads, such as wallet addresses and contract state queries, are processed ephemerally and never persisted on Vinkius servers.

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