How to Use the Charity Navigator MCP in LangChain

Q: How do I find cause categories for my chain?

Call the getcategories endpoint to return all valid IDs for areas like animal welfare or education. You inject those IDs into your prompt template so the agent knows the correct filters.

Build multi-step evaluation pipelines for nonprofits using LangChain and 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 Charity Navigator MCP to LangChain

Create your Vinkius account to connect Charity Navigator to LangChain 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 Charity Navigator with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build LangChain MCP Server Pipelines

The `search_charities` tool feeds your LangChain ReAct agents live nonprofit data directly from the source. You build chains that filter organizations by state, cause, and expense size before passing the results to the next step. Tracing these multi-step queries via LangSmith shows exactly how your agent decides which nonprofit to evaluate next. Output from a broad search becomes the input for deeper analysis, creating a self-driving research loop.

Chain Financial Data and Historical Ratings

You use `get_charity_ratings` to pull accountability scores and transparency metrics into your evaluation graph. The agent pulls the historical track record, then immediately calls `get_charity` to grab the current EIN and tax filings. Combining these endpoints inside a sequential chain means you never manually cross-reference 990 forms again. Your agent extracts the mission statement, verifies the financial health score, and formats the final brief automatically.

Automate Governance Risk Detection

The `get_all_advisories` tool lets your agent scan the entire nonprofit sector for active governance or operational warnings. When it finds a flag, the chain triggers `get_charity_advisories` for the specific organization to read the exact violation details. This turns a manual compliance check into a fast, automated LangGraph node. Your pipeline drops risky organizations from the candidate pool before any human spends time reviewing them.

Setup guide

Set up Charity Navigator MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Charity Navigator tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "charity-navigator-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Charity Navigator transactions"
    })
    print(result["messages"][-1].content)

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 Charity Navigator. 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 Charity Navigator 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 Charity Navigator MCP in LangChain

Install the langchain-mcp-adapters package first. You initialize a MultiServerMCPClient pointing to the Vinkius endpoint, then pass the fetched tools to your ReAct agent.

Yes, the search tool accepts specific state, city, and zip code parameters. Your agent decides how to apply these location filters based on the user prompt.

Every request your LangChain agent makes to the server gets logged. You see the exact payload sent to find a charity and the latency of the response.

Call the get_categories endpoint to return all valid IDs for areas like animal welfare or education. You inject those IDs into your prompt template so the agent knows the correct filters.

The server handles public financial metrics, tax filings, and rating histories. Vinkius runs the connection inside an ephemeral V8 Isolate sandbox, meaning your API tokens and query histories disappear the moment the session ends.

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