How to Use the Nodereal MCP in CrewAI

Q: What's a good starter crew for monitoring a contract with Nodereal and CrewAI?

Start with two agents. A 'Watcher' agent that uses ethgetlogs to monitor for specific events. When an event is found, it passes the details to an 'Investigator' agent that uses ethgettransactionreceipt to get more context.

Deploy autonomous on-chain crews with CrewAI and Nodereal. Let specialized agents monitor, analyze, and execute on EVM and Aptos.

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 CrewAI

Create your Vinkius account to connect Nodereal to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Deploy an On-Chain Monitoring Crew

Stop writing monolithic monitoring scripts. With CrewAI, you can build a team of agents with specific jobs. Assign one agent the `Block_Watcher` role, with the sole task of using `eth_block_number` to find new blocks. When it finds one, it passes the block number to a `Receipt_Scanner` agent. This second agent uses `nr_get_transaction_receipts_by_block_number` to scan for interesting transactions and alerts a third `Notifier` agent. Each agent does one thing well.

Build a DeFi Arbitrage Team

This is what multi-agent systems are for. A `Scout` agent uses `eth_get_logs` to watch for large swaps on a DEX. When it spots one, it passes the data to an `Analyst` agent. The `Analyst` agent uses `eth_call` to simulate arbitrage trades and `eth_estimate_gas` to check profitability. If a trade is viable, it delegates the task to an `Executor` agent, which is the only one with permission to use `eth_send_raw_transaction`. This separation of roles is key for security.

An MCP Server for NFT Intelligence

Create a crew to analyze an entire NFT collection. A `Distribution_Analyst` agent's job is to use `nr_get_nft_holders` to track ownership distribution. This agent can also use `nr_get_token_holders` for ERC20 tokens. Meanwhile, a `Wallet_Profiler` agent can use `nr_get_nft_inventory` and `nr_get_asset_transfers` to analyze the activity of top holders. A final `Reporter` agent synthesizes their findings into a daily brief. CrewAI manages the shared context between them.

Setup guide

Set up Nodereal MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Nodereal tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Nodereal Analyst",
    goal="Access and analyze Nodereal data via MCP.",
    backstory="Expert analyst with direct Nodereal access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Nodereal transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Nodereal Analyst",
        goal="Access and analyze Nodereal data via MCP.",
        backstory="Expert analyst with direct Nodereal access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Nodereal transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

When you define each agent in CrewAI, you can pass a specific list of tools to it. For example, give your 'Executor' agent only the `eth_send_raw_transaction` tool and give your 'Analyst' agent read-only tools like `eth_get_logs`.

Yes. The Nodereal MCP server exposes tools for both. You can have an 'Aptos_Scout' agent using `aptos_get_transactions` and an 'EVM_Scout' agent using `eth_get_logs` working in parallel within the same crew.

Start with two agents. A 'Watcher' agent that uses `eth_get_logs` to monitor for specific events. When an event is found, it passes the details to an 'Investigator' agent that uses `eth_get_transaction_receipt` to get more context.

CrewAI provides a shared memory context for the crew. When one agent gets a block number from Nodereal, it can add it to the context. The next agent in the process can then read that block number to perform its own task.

Your CrewAI agents run in your Python environment. They communicate over HTTPS with the Nodereal MCP server, which runs in a Vinkius-managed zero-trust sandbox. The server only processes data like contract addresses and transaction data for the duration of the request.

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