How to Use the Etherscan MCP in CrewAI

Q: Who can see the wallet addresses my agents query?

Nobody. Every time your crew runs getbalancemulti, the addresses are processed inside an ephemeral V8 Isolate. The MCP Server executes the network call and immediately flushes the state, leaving zero trace of your target lists.

Deploy multi-agent CrewAI teams that autonomously audit Etherscan smart contracts and track wallet histories.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Etherscan MCP to CrewAI

Create your Vinkius account to connect Etherscan 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 Etherscan with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Autonomous Smart Contract Auditing

One agent cannot audit a protocol alone, so this MCP Server feeds raw contract data to your entire team. You build a specialized CrewAI setup where a researcher agent pulls the `get_source_code` and `get_abi`. It grabs the raw Solidity directly from the chain. The researcher passes the uncompiled code to an analyzer agent that looks for reentrancy vulnerabilities. A third moderator agent reviews the findings and compiles a final security report. The whole operation runs sequentially without you lifting a finger.

Multi-Agent Wallet Tracking

Tracking a compromised wallet requires parsing hundreds of token transfers, which these tools monitor continuously. You assign a monitor agent to constantly poll `get_token_tx` and `get_token_nft_tx`. It watches for suspicious outbound ERC-20 and ERC-721 movements. When the monitor detects a drainer, it alerts an escalation agent. That second agent immediately queries `get_token_1155_tx` to see if any fragmented assets were also stolen. They share memory, so context is never lost between queries.

Historical Chain Analytics

Correlating off-chain events with on-chain data is tedious, but this server bridges the timeline gap. Your data team agents handle this by taking a real-world timestamp and running `get_block_no_by_time`. They pinpoint the exact block where the event occurred. From there, they map out the surrounding activity using `get_transaction_by_hash`. A manager agent orchestrates these calls, ensuring the workers stay within Etherscan rate limits while building a complete timeline of the exploit.

Setup guide

Set up Etherscan 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 Etherscan tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

task = Task(
    description="List recent Etherscan 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="Etherscan Analyst",
        goal="Access and analyze Etherscan data via MCP.",
        backstory="Expert analyst with direct Etherscan access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Etherscan 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 Etherscan. 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 Etherscan 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 Etherscan MCP in CrewAI

Pass the Vinkius endpoint URL directly into the mcps array in your Agent definition. The framework automatically fetches the tool schemas and equips your crew.

Yes. Use the MCPServerHTTP class from crewai.mcp and apply a tool_filter. You can give your researcher agent access to source code tools while blocking it from wallet balances.

The tools will return an error string. Your agents will read this failure and can be instructed to wait and retry the request automatically.

The framework supports stdio, SSE, and Streamable HTTP transports. Just configure the URL, and your agents will connect to the remote endpoint.

Nobody. Every time your crew runs `get_balance_multi`, the addresses are processed inside an ephemeral V8 Isolate. The MCP Server executes the network call and immediately flushes the state, leaving zero trace of your target lists.

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