How to Use the Cloverly MCP in Pydantic AI

Q: How do I register the Cloverly MCP Server in Pydantic AI?

Initialize the connection using the unified MCPToolset helper with your Vinkius HTTP endpoint. Avoid the deprecated MCPServerHTTP class, and pass the toolset directly to your Agent's toolsets parameter.

Q: Can I use Pydantic AI with Cloverly to compare multiple offset projects?

Yes. Your agent can call listprojects to fetch available initiatives, and the framework will validate the project schemas so your agent can safely compare them.

Run type-safe carbon calculations and offset purchases with Pydantic AI and Cloverly.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cloverly MCP to Pydantic AI

Create your Vinkius account to connect Cloverly 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 Cloverly with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Cloverly carbon estimates at runtime with Pydantic AI

Silent data corruption can ruin your carbon ledger. This MCP Server integrates with Pydantic AI to ensure every response from tools like `create_estimate` or `get_estimate` matches strict Python type definitions before your code processes them. If Cloverly returns an unexpected payload structure, the framework raises a validation error immediately. You catch issues during development instead of discovering broken carbon calculations in production.

Buy verified carbon offsets with zero structural drift

Purchasing carbon offsets requires absolute structural integrity. When your agent calls `create_purchase`, the Pydantic AI framework validates the response against strict schemas, ensuring fields like transaction IDs and carbon weights are perfectly typed. This setup prevents your agent from hallucinating purchase details. You get a reliable, type-safe pipeline that guarantees your environmental ledger matches Cloverly's actual API responses.

Build model-agnostic sustainability agents with this MCP Server

Pydantic AI lets you swap LLM providers without rewriting your carbon offset logic. This MCP Server exposes tools like `list_projects` and `get_impact_summary` using the unified `MCPToolset` class, making them compatible with any model. If you use Anthropic, OpenAI, or local models, your agent interacts with Cloverly the exact same way. The framework handles the underlying tool calls while preserving type safety across all providers.

Setup guide

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

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

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

Initialize the connection using the unified `MCPToolset` helper with your Vinkius HTTP endpoint. Avoid the deprecated `MCPServerHTTP` class, and pass the toolset directly to your Agent's `toolsets` parameter.

The framework will fail loudly with a validation error. This prevents your agent from processing corrupted carbon estimates or hallucinating purchase confirmations.

Yes. Your agent can call `list_projects` to fetch available initiatives, and the framework will validate the project schemas so your agent can safely compare them.

Yes. Because Pydantic AI is model-agnostic, you can connect this server to local models to calculate carbon emissions using `create_estimate` without sending data to third-party LLM providers.

Yes. All communication with Cloverly runs through our secure, ephemeral V8 sandbox. We never persist your transaction values or API keys, keeping your carbon accounting fully isolated.

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