How to Use the Helius (Solana) MCP in Google ADK

Q: How do I configure Helius (Solana) in Google ADK?

Install the google-adk package and create an McpToolset using the HTTP transport. Pass the toolset directly to your LlmAgent to enable Solana queries.

Q: Can Google ADK filter tools from the Helius (Solana) server?

You can restrict the exposed endpoints using the toolnames parameter. If you only want Gemini to read balances, just allow getwalletbalances and block the rest.

Q: Can this MCP read compressed NFTs?

It supports getassetproof to retrieve the Merkle proof for compressed assets. Your agent can verify off-chain data structures without running a local validator.

Connect Gemini to the Solana blockchain. Google ADK agents can read wallet histories, track assets, and estimate fees via Helius.

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 Google ADK

Create your Vinkius account to connect Helius (Solana) to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Solana asset tracking via MCP Server

The `get_asset` and `get_assets_by_owner` tools fetch granular data for any token or NFT on the network. Your Gemini agent can pull thousands of assets and feed them directly into BigQuery for enterprise analytics. Setup requires initializing a `McpToolset` with `StreamableHttpServerParameters` pointing to your Vinkius URL. Pass this into the `LlmAgent` tools array, and Gemini instantly knows how to query the MCP Server for Solana state.

Analyze massive transaction histories

You invoke `get_wallet_history` to pull complete transaction logs for any given address. Because Gemini models handle over a million tokens of context, you can dump an entire year of DeFi activity into the prompt at once. The agent uses `parse_transactions` to translate raw network bytes into readable actions. It can identify patterns, flag suspicious transfers, and cross-reference funding sources using `get_wallet_funded_by`.

Resolve identities and estimate fees

The `get_wallet_identity` tool maps raw Solana addresses to known entities and .sol domains. Your application displays human-readable names instead of base58 strings. When your system prepares to write data back to the chain, it calls `get_priority_fee_estimate`. This ensures your Vertex AI pipelines don't fail due to insufficient gas during high-volatility trading periods.

Setup guide

Set up Helius (Solana) MCP in Google ADK

Prerequisites

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

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Helius (Solana) tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Helius (Solana)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Helius (Solana) tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Install the `google-adk` package and create an `McpToolset` using the HTTP transport. Pass the toolset directly to your `LlmAgent` to enable Solana queries.

You can restrict the exposed endpoints using the `tool_names` parameter. If you only want Gemini to read balances, just allow `get_wallet_balances` and block the rest.

The underlying SDK manages standard HTTP retries. You should implement custom backoff logic in your agent loop if you plan to hit `search_assets` heavily across large BigQuery datasets.

It supports `get_asset_proof` to retrieve the Merkle proof for compressed assets. Your agent can verify off-chain data structures without running a local validator.

Your agent sends specific public keys and serialized transactions to the endpoints. The Vinkius zero-trust architecture ensures every MCP Server request runs in an isolated environment that self-destructs immediately after responding.

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