How to Use the Helius (Solana) MCP in CrewAI

Q: How do I add Helius (Solana) MCP Server tools to a CrewAI agent?

Install crewai and pass your Vinkius HTTP endpoint directly into the agent's mcps list. If you need fine-grained control, use MCPServerHTTP from the crewai.mcp package and apply a toolfilter to expose only specific tools like getwalletbalances.

Q: Can CrewAI agents collaborate on Helius (Solana) wallet analysis?

Yes, agents can share tool outputs. One agent can use getwallethistory to fetch raw transaction data, and then pass those results to a second agent specialized in running parsetransactions to decode the on-chain actions.

Q: Does CrewAI support priority fee estimation using the Helius (Solana) MCP Server?

Yes, your execution agents can call getpriorityfeeestimate before preparing transactions. This allows the crew to dynamically adjust transaction fees based on current Solana network congestion, ensuring high confirmation rates.

Run specialized agent teams to track Solana wallets using CrewAI and the Helius (Solana) MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Helius (Solana) MCP to CrewAI

Create your Vinkius account to connect Helius (Solana) 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 Helius (Solana) with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Specialized wallet monitoring crews

Dividing portfolio analysis among agents uses `get_wallet_transfers` and `get_wallet_balances` to track moving funds. You can assign a researcher agent to continuously poll transfers while an analyst agent runs balance checks to calculate current USD values. These agents share memory, allowing them to collaborate on complex portfolio assessments. The researcher feeds new transfer addresses directly to the analyst, who immediately checks holdings without starting from scratch.

Automated fraud detection and investigation

Investigating wallet histories relies on `get_wallet_funded_by` and `parse_transactions` to decode smart contract interactions. Your specialized security crew deploys one agent to find where the gas money came from, while another agent decodes recent actions. By dividing the labor, your crew flags suspicious patterns much faster than a single agent. The coordinator agent compiles these findings into a single report, detailing whether the target wallet is linked to known exploits.

Batch asset search and valuation

Scaling multi-asset queries uses `get_asset_batch` and `search_assets` to avoid performance bottlenecks. This MCP Server lets your CrewAI agents fetch data for multiple assets simultaneously, while a separate agent filters for specific custom token programs. Using multiple agents prevents bottlenecks during market volatility. While one agent is busy sorting through NFT Merkle proofs via `get_asset_proof`, another agent is free to monitor fee fluctuations using `get_priority_fee_estimate`.

Setup guide

Set up Helius (Solana) 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 Helius (Solana) tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

    task = Task(
        description="List recent Helius (Solana) 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 Helius. 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 Helius (Solana) 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 Helius (Solana) MCP in CrewAI

Install `crewai` and pass your Vinkius HTTP endpoint directly into the agent's `mcps` list. If you need fine-grained control, use `MCPServerHTTP` from the `crewai.mcp` package and apply a `tool_filter` to expose only specific tools like `get_wallet_balances`.

Yes, agents can share tool outputs. One agent can use `get_wallet_history` to fetch raw transaction data, and then pass those results to a second agent specialized in running `parse_transactions` to decode the on-chain actions.

Yes, your execution agents can call `get_priority_fee_estimate` before preparing transactions. This allows the crew to dynamically adjust transaction fees based on current Solana network congestion, ensuring high confirmation rates.

You can configure selective tool exposure when setting up the server connection. By filtering the tools, you can ensure your research agent only has access to public read tools like `get_wallet_identity` and cannot access transaction parsing tools.

Yes, your wallet addresses and on-chain histories are fully protected. The MCP Server operates on a read-only basis for public blockchain data, and Vinkius's secure sandbox ensures no credentials or sensitive transaction parameters are ever leaked or cached.

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