How to Use the Candid (GuideStar) MCP in Pydantic AI

Q: Can I use Candid (GuideStar) tools with local models in Pydantic AI?

Yes, Pydantic AI is model-agnostic. You can run tools like searchnonprofits using local models or commercial APIs.

Type-safe nonprofit validation and Candid (GuideStar) lookups validated at runtime by Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Candid (GuideStar) MCP to Pydantic AI

Create your Vinkius account to connect Candid (GuideStar) 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 Candid (GuideStar) with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe charity validation using Pydantic AI

The `verify_charity_status` tool returns IRS eligibility status, which this MCP Server validates against strict Pydantic AI schemas. Because you are using Pydantic AI, any unexpected change in the charity's status format triggers an immediate validation error instead of silently passing bad data.

Strict data parsing for grant details

The `get_grant_details` tool pulls specific award metrics that your Pydantic AI agent can parse directly into strict type models. Pydantic AI ensures that fields like award amounts and dates match your exact type definitions before your code executes.

Clean demographic and premier profiles

The `get_demographics` tool delivers structured diversity data that plugs directly into your type-safe Pydantic AI agent pipelines. By accessing this through our managed MCP Server, you bypass the hassle of writing custom API wrappers and validation schemas. You can also call `get_nonprofit_premier` to fetch deep financial profiles.

Setup guide

Set up Candid (GuideStar) 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": {
        "candid-guidestar-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Candid (GuideStar) 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 Candid (GuideStar). 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 Candid (GuideStar) 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 Candid (GuideStar) MCP in Pydantic AI

Use the MCPToolset class with the MCP Server endpoint. Pass this toolset directly into your Agent constructor to expose `get_nonprofit_essentials`.

The framework will raise a validation error at runtime. This prevents your agent from making decisions based on incomplete nonprofit profiles.

Yes, Pydantic AI is model-agnostic. You can run tools like `search_nonprofits` using local models or commercial APIs.

No, you should use the unified MCPToolset approach. It is cleaner and fully compatible with our managed server endpoints.

The MCP Server runs inside an ephemeral V8 isolate. Financial details and tax data fetched via `get_nonprofit_premier` are never stored, keeping your compliance checks isolated and private.

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