How to Use the Nodereal MCP in AutoGen

Q: How do I configure the Nodereal MCP server in AutoGen?

Install the autogen-extmcp package. Fetch the tools using mcpservertools with your HTTP endpoint parameters. Pass the resulting list directly into your AssistantAgent constructor.

Q: How does AutoGen handle Nodereal tool schemas?

The McpToolAdapter converts the MCP JSON schema into AutoGen's native format automatically. Your agents see standard function signatures for endpoints like nrgettokenbalance20.

Give your AutoGen agents the Nodereal tools to debate and execute blockchain transactions.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Nodereal MCP to AutoGen

Create your Vinkius account to connect Nodereal 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 Nodereal with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Smart Contract Auditing

`aptos_simulate_transaction` is the core of this MCP Server for AutoGen, letting your agents dry-run state changes while they argue about the results. You can build a system where a developer agent proposes a transaction payload, and a security agent runs the simulation to check for unexpected resource drains. They debate the output. If the simulation shows a massive gas spike, the security agent rejects the proposal. The developer agent then tweaks the parameters and tries again. They negotiate until the transaction is safe to submit.

Cross-Chain Data Reconciliation

`eth_get_balance` and `aptos_get_account` allow your agent teams to verify state across entirely different networks. You might have an EVM agent checking bridge deposits and an Aptos agent verifying the corresponding mints. When the data doesn't match, they cross-examine the chain. One agent pulls `eth_get_logs` while the other calls `aptos_get_transactions`. They work together to pinpoint exactly where a cross-chain message failed, saving you hours of manual block explorer digging.

Consensus-Driven Nodereal MCP Server Execution

`eth_send_raw_transaction` gives your AutoGen swarm the ability to actually execute state changes after reaching consensus. You don't want a single LLM firing off mainnet transactions blindly. You want a committee. A financial agent checks the gas price with `eth_estimate_gas`. A risk agent verifies the target address using `nr_get_asset_transfers` to look for malicious history. Only when all agents agree does the execution agent finally sign and broadcast the payload.

Setup guide

Set up Nodereal 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 Nodereal 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="Nodereal_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Install the `autogen-ext[mcp]` package. Fetch the tools using `mcp_server_tools` with your HTTP endpoint parameters. Pass the resulting list directly into your `AssistantAgent` constructor.

Yes. You can give the EVM tools to one agent and the Aptos tools to another. They will coordinate and call their respective endpoints during the conversation.

The `McpToolAdapter` converts the MCP JSON schema into AutoGen's native format automatically. Your agents see standard function signatures for endpoints like `nr_get_token_balance_20`.

The error returns directly to the conversation thread. The agents read the failure reason from `eth_call`, discuss why it reverted, and attempt a different approach.

The server handles contract addresses and event signatures to fetch your specific log data. Vinkius runs this connection through an ephemeral sandbox that spins down immediately after the query, leaving zero residual data behind.

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