How to Use the GlobalGiving MCP in Pydantic AI

Q: Can I use GlobalGiving with any model in Pydantic AI?

Yes. The server is model-agnostic. You plug it into your Agent instance, and it works regardless of whether you are using OpenAI, Anthropic, or a local model. The focus is on the data validation.

Strictly typed charity data for Pydantic AI. Connect to GlobalGiving for reliable, validated agent responses.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect GlobalGiving MCP to Pydantic AI

Create your Vinkius account to connect GlobalGiving 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 GlobalGiving with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe GlobalGiving MCP Server for Pydantic AI

Every response from the server is validated against your Pydantic models. When you call `get_project_details`, the data must match your schema or the agent throws a validation error immediately. This prevents your agent from processing malformed data. You get the peace of mind that your logic is running on clean, verified information from the GlobalGiving API.

Thematic project discovery for Pydantic AI

You use `list_projects_by_theme` to organize your project research. The server returns a structured response that Pydantic AI validates against your predefined types. Your agent handles the results with confidence. If the data format changes unexpectedly, your agent detects it during the validation phase, protecting your system from silent failures.

Operational verification for Pydantic AI

You invoke `verify_api_connection` as part of your agent's startup sequence. This ensures the connection is ready before any critical data retrieval begins. It forces the agent to check the environment status. If the connection fails, you get an immediate error instead of wasting cycles on broken requests.

Setup guide

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

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

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

The MCP Server returns data that conforms to the expected structure. Your Pydantic models validate every field returned by `search_nonprofit_projects` or other tools. If the API returns garbage, your agent fails loudly.

Yes. The server is model-agnostic. You plug it into your `Agent` instance, and it works regardless of whether you are using OpenAI, Anthropic, or a local model. The focus is on the data validation.

The server supports SSE and Streamable HTTP. This keeps your connection alive and responsive. You verify the status using `verify_api_connection` to ensure your agent stays synced with the GlobalGiving platform.

The server operates within a zero-trust, ephemeral sandbox. It only touches public nonprofit project records. Your agent's internal state remains private, and no data is persisted beyond the session execution.

It exposes public details for nonprofits, including project titles, themes, and funding progress. This is purely public information used for project discovery. The server does not interact with protected donor accounts or private financial records.

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