How to Use the Covalent MCP in Pydantic AI

Build type-safe Pydantic AI agents that query verified multi-chain data with strict 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 Covalent MCP to Pydantic AI

Create your Vinkius account to connect Covalent 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 Covalent with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enforce Type Safety on Multi-Chain Queries with Pydantic AI

`get_token_balances` returns raw and formatted balances that Pydantic AI validates against strict schemas before your agent even sees them. If our MCP integration returns unexpected null fields or broken formats, the system raises a validation error immediately. This strict validation prevents silent data corruption in your financial models. Your agent can confidently process token decimals and contract addresses, knowing the data matches your exact type definitions.

Validate Portfolio Valuations at Runtime

`get_historical_portfolio` resolves daily balances and USD valuations directly into typed Pydantic models. Your Pydantic AI agent uses these validated models to calculate historical performance without risking parsing errors. If the USD valuation schema changes on a specific chain, the framework catches the discrepancy instantly. This ensures your automated tax and accounting agents never operate on malformed financial data from the MCP Server.

Audit NFT Balances with Zero Hallucinations

`get_nft_balances` extracts contract names, token IDs, and metadata URLs into structured Python objects. Pydantic AI guarantees that every field, including the image link, conforms to your expected data types. When your agent queries `get_block_details` to check the minting block, the runtime ensures the timestamp and transaction counts are properly typed integers. This eliminates the risk of your model hallucinating block heights.

Setup guide

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

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

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

Install the correct package and initialize the toolset with your Vinkius HTTP endpoint. Pass this toolset directly to your `Agent` constructor to auto-discover tools like `get_token_transfers` via our managed MCP gateway.

The framework raises a runtime validation error instead of letting your agent hallucinate a response. This is crucial when calling `get_transaction_details`, where missing gas metrics could break downstream calculations.

Yes, the unified toolset supports both Streamable HTTP and SSE transports. This allows your agent to query `list_supported_chains` over persistent MCP connections for faster response times.

Yes, Pydantic AI is model-agnostic. You can pair tools like `get_dex_pools` with local models or commercial APIs, and the runtime validation will function identically.

Every request containing wallet addresses or transaction logs is processed in an ephemeral, zero-trust V8 sandbox. Vinkius handles the authentication token securely, ensuring your raw queries never persist on disk or leak to external logging systems.

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