How to Use the Alchemy MCP in CrewAI

Q: How do I give different Alchemy tools to different agents in my CrewAI setup?

When you define your Agent in CrewAI, you can use the toolfilter option. This lets you expose specific tools, like getwalletbalance, to one agent while giving gettransactionreceipt to another.

Equip your CrewAI agents with Alchemy tools to build autonomous on-chain operations. Deploy teams that monitor wallets, verify transactions, and report on assets.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Alchemy MCP to CrewAI

Create your Vinkius account to connect Alchemy 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 Alchemy with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Autonomous Wallet Monitoring Crew

Assign roles to your agents. A 'Watcher' agent can use `get_wallet_balance` and `get_token_balances` to continuously monitor a set of high-value wallets. It doesn't act, it just observes. When the Watcher detects a significant change, it passes the data to an 'Analyst' agent. The Analyst decides if the change warrants an alert, then delegates the notification task to a 'Communicator' agent. That's how a CrewAI team works together.

Build a Transaction Verification Team

Split up the work of confirming a complex asset purchase. One agent, the 'Executor', is responsible for the initial action. It passes a transaction hash to a 'Verifier' agent. The Verifier's only job is to use `get_transaction_receipt` to confirm the transaction and `get_owned_nfts` to ensure the asset arrived. Once done, it reports success or failure back to the crew's manager agent. This creates a clear, auditable separation of duties.

On-Chain Intelligence with a CrewAI MCP Server

Deploy a research crew for market analysis. A 'Scout' agent can use `get_owned_nfts` to track what top traders are buying. A 'Tracker' agent uses `get_latest_block_number` to monitor network activity. All this data is shared in the crew's collective memory. A 'Summarizer' agent can then access this shared context to produce a daily intelligence brief. Your agents do the legwork, you get the summary.

Setup guide

Set up Alchemy 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 Alchemy tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

When you define your Agent in CrewAI, you can use the `tool_filter` option. This lets you expose specific tools, like `get_wallet_balance`, to one agent while giving `get_transaction_receipt` to another.

Yes, that's a primary use case for CrewAI. Create a monitoring agent with the Alchemy tools, and when it finds something, it can delegate a task to another agent in the crew to take action.

Use a two-agent crew. An 'Executor' agent makes the purchase and gets a transaction hash. It then passes the hash to a 'Verifier' agent, whose only tools are `get_transaction_receipt` and `get_owned_nfts` to confirm the result.

Yes. You can have a dedicated 'Coordinator' agent, or just the first agent in a sequence, call `check_api_status` as its first task. If it fails, the crew can pause or report an error.

The server processes public on-chain data your agents provide, such as wallet addresses. Vinkius ensures security by running each tool call in a dedicated V8 Isolate sandbox, which is destroyed after execution. No data from your agent's request is retained.

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