How to Use the Greenspark MCP in Pydantic AI

Q: How do I register Greenspark MCP Server tools in Pydantic AI?

Use MCPToolset with your server HTTP URL and pass it to your Agent constructor. This registers tools like createimpact and estimatefootprint with automatic runtime validation.

Q: Can I use Pydantic AI to validate Greenspark webhook structures?

Yes. Your agent can call listwebhooks and parse the configured endpoints into strictly typed Python models, ensuring your webhook URLs and metadata are perfectly formatted.

Q: Does the Greenspark MCP Server validate outputs automatically in Pydantic AI?

Yes. Every tool output, including historical data from listimpacts, is validated against Pydantic schemas before your agent processes the data.

Build type-safe climate integrations with Pydantic AI and Greenspark to guarantee runtime validation on every offset.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Greenspark MCP to Pydantic AI

Create your Vinkius account to connect Greenspark 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 Greenspark with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Carbon Estimation

The `estimate_footprint` tool calculates the carbon footprint of your orders with strict runtime validation enforced by Pydantic AI. The framework verifies that all transaction values match your defined schemas before calculating the offset. If the Greenspark API returns a payload that deviates from your expected structure, Pydantic AI raises a validation error immediately. That's how you prevent corrupted carbon or tree-planting data from entering your production databases.

Verified Impact Creation with MCP Server

The `create_impact` tool triggers environmental contributions like tree planting directly from your type-safe Pydantic AI agents. The framework validates the response payload containing the impact details before committing the transaction to your logs. Integrating this MCP Server with Pydantic AI guarantees that every tree-planting action is verified against structured Python models. The agent uses `get_impact` to confirm the offset status, matching the API response against your type-safe definitions.

Structured Project Discovery

The `list_projects` tool fetches active environmental projects supported by Greenspark into your Pydantic AI agent. The framework parses this list into structured models, making it easy to filter projects by type or location. Your Pydantic AI agent then calls `get_project` to retrieve specific project metadata. Because the framework enforces type safety, your application can render these Greenspark project descriptions without risking runtime crashes from unexpected null values.

Setup guide

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

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

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

Use `MCPToolset` with your server HTTP URL and pass it to your `Agent` constructor. This registers tools like `create_impact` and `estimate_footprint` with automatic runtime validation.

The framework catches the error and raises a clear validation or connection exception. This allows your application to handle the failure gracefully instead of silently ignoring a failed `create_impact` call.

Yes. Your agent can call `list_webhooks` and parse the configured endpoints into strictly typed Python models, ensuring your webhook URLs and metadata are perfectly formatted.

Yes. Every tool output, including historical data from `list_impacts`, is validated against Pydantic schemas before your agent processes the data.

Your subscription tokens are loaded as environment variables and processed strictly in memory. The server only transmits the bare minimum payload required to log offsets, ensuring that sensitive customer identity records are never exposed.

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