How to Use the FtmScan (Fantom Network Explorer) MCP in Pydantic AI

Q: How do I initialize the FtmScan (Fantom Network Explorer) MCP Server in Pydantic AI?

Use the MCPToolset class pointing to the Vinkius HTTP endpoint. Pass this toolset into your Agent's toolsets parameter to register the tools.

Q: Can I query the latest block number using FtmScan (Fantom Network Explorer) in Pydantic AI?

Yes, your agent can call getethblocknumber to get the latest block. The returned block height is validated as a clean integer.

Q: Is there a tool to check token supplies?

Yes, geterc20tokensupply retrieves the total supply of any ERC20 token. The output is parsed and validated before being handed to your agent.

Build type-safe Fantom data pipelines in Pydantic AI using this MCP Server for runtime validation.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect FtmScan (Fantom Network Explorer) MCP to Pydantic AI

Create your Vinkius account to connect FtmScan (Fantom Network Explorer) 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 FtmScan (Fantom Network Explorer) with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe wallet balance queries

`get_ftm_balance` fetches the exact native balance of a Fantom address and validates the response schema at runtime. If the API returns unexpected formats, Pydantic AI raises a validation error immediately instead of letting your agent work with corrupted data. For multi-wallet checks, `get_ftm_balance_multi` pulls balances for up to 20 addresses in a single call. This keeps your MCP network overhead low while ensuring every single balance field matches your expected Python types.

Strict validation for token transfers

`get_erc20_transfers` extracts transfer event logs with guaranteed schema enforcement. Your agent gets clean, validated lists of token movements, complete with sender, receiver, and value fields that conform to your Pydantic models. If you are tracking digital assets, `get_erc721_transfers` enforces the same level of strict typing for NFT movements within your MCP client. This prevents your agent from crashing due to unexpected null fields or dynamic contract structures.

Parse contract events using an MCP Server

`get_logs` retrieves raw event logs from the Fantom blockchain based on your filter parameters. This tool allows your agent to monitor specific smart contract events, such as deposits or liquidations, with high precision. To check if a transaction went through, `get_transaction_status` returns the execution state. The server wraps this in a strict schema, ensuring your agent never misinterprets a failed transaction as a success.

Setup guide

Set up FtmScan (Fantom Network Explorer) 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": {
        "ftmscan-fantom-network-explorer-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent FtmScan (Fantom Network Explorer) 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 FtmScan. 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 FtmScan (Fantom Network Explorer) 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 FtmScan (Fantom Network Explorer) MCP in Pydantic AI

Use the `MCPToolset` class pointing to the Vinkius HTTP endpoint. Pass this toolset into your Agent's `toolsets` parameter to register the tools.

The framework validates the JSON payload against strict Pydantic models before your agent sees it. If FtmScan returns unexpected data, the system raises a validation error to prevent hallucinations.

Yes, your agent can call `get_eth_block_number` to get the latest block. The returned block height is validated as a clean integer.

Yes, `get_erc20_token_supply` retrieves the total supply of any ERC20 token. The output is parsed and validated before being handed to your agent.

All queried wallet addresses are processed in an isolated V8 sandbox hosted by Vinkius. The data is processed in-memory and never stored, keeping your on-chain research private.

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