Can I verify if a non-profit is eligible for tax-deductible donations?

Yes! Use the `verify_charity_status` tool with the organization's EIN. Your agent will fetch the real-time compliance status from Candid's Charity Check API.

How do I find the EIN for an organization if I only have its name?

Simply ask the agent to `search_nonprofits` and provide the name. The search results will include the EIN for each matching organization, which you can then use for deeper lookups.

Does the integration allow accessing diversity and inclusion data?

Yes. Use the `get_demographics` tool. It will retrieve the DEI metadata provided by the organization to Candid, helping you understand their leadership and staff representation.

Candid (GuideStar) MCP Server for Pydantic AI 10 tools — connect in under 2 minutes

Name: Candid (GuideStar)
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 10 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Candid (GuideStar) through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Candid (GuideStar) "
            "(10 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Candid (GuideStar)?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Candid (GuideStar) MCP Server

Connect your Candid (formerly GuideStar) account to any AI agent and orchestrate your non-profit research, due diligence, and philanthropic data workflows through natural conversation.

Pydantic AI validates every Candid (GuideStar) tool response against typed schemas, catching data inconsistencies at build time. Connect 10 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Organization Oversight — Search for non-profits by name, location, or NTEE code and retrieve basic metadata using the Essentials API.
Deep-Dive Profiles — Access comprehensive data (Premier tier) including mission statements, leadership, and detailed financials.
Charity Compliance — Verify IRS tax-exempt status and eligibility to receive tax-deductible contributions using the Charity Check tool.
Financial Auditing — Retrieve detailed financial records and IRS Form 990 data straight from your workspace.
Demographics Analysis — Access diversity, equity, and inclusion (DEI) data for organizations to inform your philanthropic strategy.
Organization Discovery — Use the EIN (Employer Identification Number) as a primary key to fetch 760+ data fields for individual entities.

The Candid (GuideStar) MCP Server exposes 10 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Candid (GuideStar) to Pydantic AI via MCP

Follow these steps to integrate the Candid (GuideStar) MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 10 tools from Candid (GuideStar) with type-safe schemas

Why Use Pydantic AI with the Candid (GuideStar) MCP Server

Pydantic AI provides unique advantages when paired with Candid (GuideStar) through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your Candid (GuideStar) integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Candid (GuideStar) connection logic from agent behavior for testable, maintainable code

Candid (GuideStar) + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Candid (GuideStar) MCP Server delivers measurable value.

Type-safe data pipelines: query Candid (GuideStar) with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Candid (GuideStar) tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Candid (GuideStar) and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Candid (GuideStar) responses and write comprehensive agent tests

Candid (GuideStar) MCP Tools for Pydantic AI (10)

These 10 tools become available when you connect Candid (GuideStar) to Pydantic AI via MCP:

get_charity_check_pdf

Generate a PDF report for compliance record-keeping

get_demographics

Get DEI data for a nonprofit

get_grant_details

Get specific details for a grant

get_nonprofit_eligibility

Verify nonprofit eligibility for specific donation platforms

get_nonprofit_essentials

Get core details for a nonprofit by EIN

get_nonprofit_news

Get real-time social sector news related to a nonprofit

get_nonprofit_premier

Get comprehensive deep-dive data for a nonprofit by EIN

search_grants

Search for grants awarded by foundations

search_nonprofits

Search for nonprofits using filters

verify_charity_status

Verify an organization's eligibility to receive tax-deductible contributions

Example Prompts for Candid (GuideStar) in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Candid (GuideStar) immediately.

"Search for non-profits in 'Miami' with the name 'Red Cross'."

"Get detailed financial info for EIN 13-162xxxx."

"Verify the charity status for EIN 52-153xxxx."

Troubleshooting Candid (GuideStar) MCP Server with Pydantic AI

Common issues when connecting Candid (GuideStar) to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Candid (GuideStar) + Pydantic AI FAQ

Common questions about integrating Candid (GuideStar) MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer. your Candid (GuideStar) MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.