How to Use the Conflux MCP in Pydantic AI

Q: How do I initialize the Conflux MCP Server toolset in Pydantic AI?

Install the package using pip install "pydantic-ai-slimmcp". Use the unified MCPToolset pointing to your Vinkius HTTP endpoint, and pass it directly to the toolsets argument of your Agent.

Q: Can Pydantic AI validate the output of Conflux write operations?

Yes. When your agent calls tools like cfxsendrawtransaction or ethsendrawtransaction, the transaction hash returned is validated against Pydantic's schema before your agent processes the next step.

Q: Is the old MCPServerHTTP class still supported?

No, MCPServerHTTP is deprecated in Pydantic AI. You should use the unified MCPToolset class to connect to your Vinkius-hosted MCP Server.

Get type-safe, validated Conflux blockchain data inside your Pydantic AI agents with zero silent errors.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Conflux MCP to Pydantic AI

Create your Vinkius account to connect Conflux 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 Conflux with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Blockchain Reads with Pydantic AI

This MCP Server ensures that every piece of Conflux ledger data returned by tools like `cfx_get_balance` matches strict Pydantic AI schemas. When your agent calls this tool or `eth_get_balance`, the response is validated at runtime, preventing silent corruption of big integer values or hex strings. If the Conflux node returns unexpected data structures, the Pydantic AI validation engine fails immediately. This is critical for financial applications where you cannot afford to let your agent hallucinate a balance or parse a block hash incorrectly.

Transaction and Receipt Verification

Track Conflux transaction statuses with complete validation safety using tools like `cfx_get_transaction_receipt` inside your Pydantic AI workflow. Connect your agent to the MCP Server to query execution status and verify if a contract call succeeded or reverted on-chain. The Pydantic AI agent parses the logs using `cfx_get_logs` and maps them to your local typed models. This keeps your application database in sync with the Conflux chain state without writing manual validation code.

Local Gas and Nonce Calculations

Prepare Conflux transactions safely by letting your agent query current network parameters with tools like `cfx_get_next_nonce` in Pydantic AI. The agent fetches the correct sequence number and uses `cfx_estimate_gas_and_collateral` to calculate costs. Because Pydantic AI enforces type safety, these numerical values are guaranteed to be parsed correctly. Your agent can then safely construct a pre-signed transaction payload and send it using `cfx_send_raw_transaction`.

Setup guide

Set up Conflux 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": {
        "conflux-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Conflux 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 Conflux. 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 Conflux 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 Conflux MCP in Pydantic AI

Install the package using `pip install "pydantic-ai-slim[mcp]"`. Use the unified `MCPToolset` pointing to your Vinkius HTTP endpoint, and pass it directly to the `toolsets` argument of your Agent.

Yes. When your agent calls tools like `cfx_send_raw_transaction` or `eth_send_raw_transaction`, the transaction hash returned is validated against Pydantic's schema before your agent processes the next step.

The framework catches the validation or network error immediately and raises a clear exception. This prevents your agent from continuing execution with incomplete or corrupted block data from `cfx_get_block_by_hash`.

No, `MCPServerHTTP` is deprecated in Pydantic AI. You should use the unified `MCPToolset` class to connect to your Vinkius-hosted MCP Server.

The server only processes public blockchain queries such as balances, transaction histories, and contract states. All network requests are isolated within ephemeral V8 containers, ensuring no sensitive session data or RPC credentials leak.

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