How to Use the Helius (Solana) MCP in Pydantic AI

Q: How do I connect Helius (Solana) to Pydantic AI?

Install pydantic-ai-slimmcp and initialize an MCPToolset with your Vinkius HTTP endpoint. Assign it to the toolsets array on your Agent instance.

Q: Does Pydantic AI validate Helius (Solana) responses automatically?

Yes. Every response from endpoints like getwallettransfers is checked against your Pydantic models. If the structure deviates, the framework halts execution immediately.

Q: Can Helius (Solana) resolve .sol domains in Pydantic AI?

The server provides getwalletidentity to map addresses to known entities. Your agent can enforce strict string validation on the returned domain names.

Q: What happens if an asset search fails?

If searchassets returns a 4xx or 5xx error, the MCP protocol bubbles the failure up to the agent. Pydantic AI logs the exact error state rather than trying to parse null data.

Enforce strict typing on Solana RPC data. Pydantic AI agents validate every wallet balance and transaction history against your schemas.

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 Pydantic AI

Create your Vinkius account to connect Helius (Solana) to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe Solana queries with Pydantic AI

The `get_wallet_balances` tool retrieves token and NFT holdings with exact USD valuations. Pydantic AI intercepts the raw JSON and validates it against your defined models before the agent even sees the data. If the chain returns an unexpected field format, the system throws a loud validation error. You configure this by passing `MCPToolset("http://...")` to your Agent, ensuring no silent failures corrupt your trading logic.

Parse transactions into strict models

Calling `parse_transactions` takes raw on-chain data and formats it into readable actions. Your agent relies on this structured output to understand complex DeFi interactions without hallucinating the details. You can combine this with `get_transaction_history` to pull a sequence of events. Because you dictate the expected schema, the LLM cannot invent token transfers that never actually occurred on the network.

Calculate fees and verify assets

The `get_priority_fee_estimate` endpoint requires a serialized transaction to calculate the exact micro-lamport cost. This prevents your agent from underbidding during network congestion and missing critical block inclusion. When tracking portfolios, `get_assets_by_owner` and `search_assets` pull granular metadata. The MCP Server handles the complex indexing, while your Python code focuses strictly on business logic and validation.

Setup guide

Set up Helius (Solana) MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "helius-solana-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Helius (Solana) tools.",
)

result = await agent.run("List recent Helius (Solana) transactions")
print(result.output)

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 Pydantic AI

Install `pydantic-ai-slim[mcp]` and initialize an `MCPToolset` with your Vinkius HTTP endpoint. Assign it to the `toolsets` array on your Agent instance.

Yes. Every response from endpoints like `get_wallet_transfers` is checked against your Pydantic models. If the structure deviates, the framework halts execution immediately.

The server provides `get_wallet_identity` to map addresses to known entities. Your agent can enforce strict string validation on the returned domain names.

If `search_assets` returns a 4xx or 5xx error, the MCP protocol bubbles the failure up to the agent. Pydantic AI logs the exact error state rather than trying to parse null data.

The endpoints process token mint addresses and transaction signatures. Vinkius routes these MCP Server requests through stateless, ephemeral sandboxes that discard all memory allocations the second the network call finishes.

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