How to Use the Harmonyscan (Harmony One Block Explorer API) MCP in Pydantic AI

Q: How do I connect Harmonyscan (Harmony One Block Explorer API) to Pydantic AI?

Install pydantic-ai-slimmcp. Initialize an MCPToolset with your HTTP URL and pass it to your agent's toolsets parameter. Do not use the deprecated MCPServerHTTP class.

Q: Will Pydantic AI catch errors from Harmonyscan (Harmony One Block Explorer API)?

Yes. If a call to gettokentx returns malformed JSON or missing fields, Pydantic AI throws a strict validation error instead of passing bad data to the LLM.

Q: Can I use custom RPC methods with Harmonyscan (Harmony One Block Explorer API) in Pydantic AI?

Yes. The proxyrequest tool allows standard JSON-RPC calls. You define the expected Pydantic model for the response, ensuring custom queries remain type-safe.

Enforce strict type safety on Harmony blockchain queries with Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Harmonyscan (Harmony One Block Explorer API) MCP to Pydantic AI

Create your Vinkius account to connect Harmonyscan (Harmony One Block Explorer API) 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 Harmonyscan (Harmony One Block Explorer API) with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe MCP Server integration

Blockchain APIs are notoriously inconsistent. When you connect this MCP Server using MCPToolset, Pydantic AI forces every response from `get_tx_list` or `get_logs` into a strict data model. You define the types, the framework enforces them. If Harmonyscan returns a missing field, the framework fails loudly with a validation error. Your application never swallows silent data corruption or hallucinated transaction hashes.

Validate smart contract data

Pulling contract code requires exact formatting. Your agent uses `get_abi` to fetch interface definitions and `get_source_code` to pull the raw logic. The data maps directly to your Python classes. Because Pydantic AI is model-agnostic, you can route these complex queries through Anthropic, OpenAI, or local models. The framework guarantees the returned JSON matches your expected schema before the agent takes its next step.

Query balances with certainty

Financial applications cannot tolerate parsing mistakes. The `get_balance` and `get_balance_multi` tools return raw ONE token balances that map directly to your Python types. No string-to-float conversion errors. You can track network emissions with `get_block_reward` or verify execution with `get_tx_receipt_status`. Every single tool execution undergoes runtime validation, keeping your production pipelines bulletproof.

Setup guide

Set up Harmonyscan (Harmony One Block Explorer API) 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": {
        "harmonyscan-harmony-one-block-explorer-api-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Harmonyscan (Harmony One Block Explorer API) tools.",
)

result = await agent.run("List recent Harmonyscan (Harmony One Block Explorer API) 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 Harmonyscan. 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 Harmonyscan (Harmony One Block Explorer API) 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 Harmonyscan (Harmony One Block Explorer API) MCP in Pydantic AI

Install pydantic-ai-slim[mcp]. Initialize an MCPToolset with your HTTP URL and pass it to your agent's toolsets parameter. Do not use the deprecated MCPServerHTTP class.

Yes. If a call to get_token_tx returns malformed JSON or missing fields, Pydantic AI throws a strict validation error instead of passing bad data to the LLM.

Yes. The proxy_request tool allows standard JSON-RPC calls. You define the expected Pydantic model for the response, ensuring custom queries remain type-safe.

Yes. The framework is completely model-agnostic. As long as the model supports tool calling, it can execute get_one_price or get_one_supply and validate the output.

The server operates on a zero-trust model. When you query wallet addresses or token contracts, the request runs in an isolated sandbox that destroys itself after executing, ensuring no residual data persists outside your own database.

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