How to Use the Candid (GuideStar) MCP in LlamaIndex

Q: How do I add Candid (GuideStar) to LlamaIndex?

Install llama-index-tools-mcp and set up a BasicMCPClient. Wrap it in an McpToolSpec and pass the asynchronous tool list to your agent.

Q: Can LlamaIndex embed Candid (GuideStar) demographic data?

Your agent calls getdemographics and ingests the resulting JSON. The framework then chunks and embeds that DEI data alongside your internal grant documents.

Q: Can I filter which tools the query engine accesses?

You restrict the agent to specific operations using the allowedtools parameter. This prevents it from running expensive deep dives if it only needs basic eligibility checks.

Index nonprofit financials and grant histories into searchable LlamaIndex knowledge bases using this MCP Server.

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 LlamaIndex

Create your Vinkius account to connect Candid (GuideStar) to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Vectorize nonprofit financials

Raw API responses are hard to query across hundreds of organizations. This MCP Server lets your application pull deep organizational data via `get_nonprofit_premier` and immediately index the results. Your RAG setup now answers questions based on live Candid data. Instead of returning a static JSON blob, LlamaIndex transforms the output into searchable nodes. Ask your agent to compare the financial health of five different charities, and it synthesizes the answer from the vectorized API responses.

Ground answers in real compliance data

Hallucinations ruin compliance workflows. By hooking up the Candid (GuideStar) tools, your query engine grounds its responses in verified tax statuses. It calls `verify_charity_status` to ensure the organization is actually a 501(c)(3) before generating any internal report. You also enrich your existing document indexes this way. If you have a folder of grant applications, the agent uses `get_demographics` to append real DEI metrics to each applicant's profile in your vector store.

Semantic search for foundation grants

Tracking historical funding demands exact keyword matches in traditional databases. Providing `search_grants` and `get_grant_details` to your `FunctionAgent` allows it to retrieve raw grant records and embed them for semantic search. Users then ask broad questions like which foundations fund clean water initiatives in California. The agent searches the embedded grant details and retrieves exact matches without needing precise foundation names.

Setup guide

Set up Candid (GuideStar) MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Candid (GuideStar) MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Candid (GuideStar) tools.",
)
response = await agent.run("List recent Candid (GuideStar) data")

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 LlamaIndex

Install `llama-index-tools-mcp` and set up a `BasicMCPClient`. Wrap it in an `McpToolSpec` and pass the asynchronous tool list to your agent.

Your agent calls `get_demographics` and ingests the resulting JSON. The framework then chunks and embeds that DEI data alongside your internal grant documents.

Yes. Once the tool fetches the nonprofit data, LlamaIndex handles the embedding. You push those vectors to Pinecone, Weaviate, or any other supported database.

You restrict the agent to specific operations using the `allowed_tools` parameter. This prevents it from running expensive deep dives if it only needs basic eligibility checks.

Vinkius processes all tool execution inside ephemeral containers. The specific foundations you search and the grant amounts you index are never logged or stored on our infrastructure.

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