How to Use the Every.org Charity MCP in LlamaIndex

Q: Can I index Every.org Charity API responses for offline search in LlamaIndex?

Yes, you can run searchcharities to gather non-profit profiles and load them into a VectorStoreIndex. This lets you run semantic queries over the cached data without hitting the live API every time.

Q: How does LlamaIndex prevent hallucinated tax statuses when using Every.org Charity?

The agent uses getcharitydetails to fetch verified registration records directly before answering. By forcing the LLM to ground its response in this retrieved JSON, you eliminate fabricated non-profit data.

Index Every.org Charity data directly into your LlamaIndex vector stores to ground your agent's answers in real non-profit facts.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Every.org Charity MCP to LlamaIndex

Create your Vinkius account to connect Every.org Charity 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 Every.org Charity with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Ground your RAG applications in real charity data

This MCP Server lets your knowledge-augmented LlamaIndex agents run `get_charity_details` and store the resulting profiles directly in your local vector database. LlamaIndex specializes in turning live API outputs into searchable vector indexes for immediate retrieval. Instead of relying on old training data, your agent answers questions using fresh registration records. This prevents your system from hallucinating tax statuses or mission statements when users ask about specific organizations.

Build semantic search indexes for causes

You can ingest large batches of non-profit information into LlamaIndex by running `search_charities` to pull lists of organizations under specific causes. Once retrieved, you index that raw text for semantic search across your entire application. This setup allows users to find non-profits using natural, conversational queries even if they do not know the exact name of the organization. The index matches the user's intent with the actual mission descriptions returned by the API.

Query historical charity data alongside live documents

This MCP Server lets your LlamaIndex agent merge live API tools like `search_charities` with local document readers. Your agent can read a donor's private PDF grant guidelines, then search for matching organizations that fit those exact criteria. The agent runs the search to find potential matches and evaluates them against the PDF rules. This creates an automated matching system that respects both your local files and live non-profit data.

Setup guide

Set up Every.org Charity 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 Every.org Charity 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 Every.org Charity tools.",
)
response = await agent.run("List recent Every.org Charity 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 Every.org. 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 Every.org Charity 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 Every.org Charity MCP in LlamaIndex

Install the LlamaIndex MCP tool spec package and initialize the basic client with your Vinkius HTTP URL. Convert the server tools into LlamaIndex tool specs and pass them to your FunctionAgent.

Yes, you can run `search_charities` to gather non-profit profiles and load them into a VectorStoreIndex. This lets you run semantic queries over the cached data without hitting the live API every time.

The agent uses `get_charity_details` to fetch verified registration records directly before answering. By forcing the LLM to ground its response in this retrieved JSON, you eliminate fabricated non-profit data.

Yes, you can use the allowed tools filter in the MCP tool spec to restrict your agent. If you only want it to search but not fetch deep profiles, you can expose just one of the functions.

The system only processes public non-profit financial, registration, and mission data from Every.org. All data transfer happens over secure HTTP tunnels managed by Vinkius, ensuring no third-party intercept of your queries.

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