How to Use the Candid (GuideStar) MCP in LangChain

Q: How do I connect the Candid (GuideStar) MCP Server to LangChain?

Initialize MultiServerMCPClient with the Vinkius endpoint URL. Call client.gettools() and pass the resulting array into your ReAct agent creation function.

Q: Can LangChain agents search Candid (GuideStar) for specific grant details?

Yes. Your agent calls searchgrants with specific foundation parameters. It then passes the results to getgrantdetails to extract exact funding amounts and recipient data.

Q: How do I handle missing EINs in my database?

Give your chain the searchnonprofits tool. The agent takes a raw organization name, finds the correct EIN, and updates your records automatically.

Build ReAct pipelines that verify 501(c)(3) status and fetch grant data directly within LangChain via this MCP integration.

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 LangChain

Create your Vinkius account to connect Candid (GuideStar) 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 Candid (GuideStar) with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

LangChain ReAct agents for eligibility

Your agent needs to qualify incoming donation requests before approving matching funds. Passing `verify_charity_status` to a LangChain tool node lets the system check IRS standing in real-time. The output feeds directly into your next chain step without manual intervention. Multi-step reasoning handles the complex checks. If a nonprofit clears the basic tax hurdle, the agent triggers `get_nonprofit_eligibility` to see if they meet specific platform rules. You get full visibility into every step via LangSmith.

Deep financial data extraction

Fetching core organizational details typically requires manual scraping of 990 forms. This MCP server gives your graph direct access to `get_nonprofit_essentials` and `get_nonprofit_premier`. Your agent grabs the EIN, pulls the data, and formats a summary report automatically. Combine this capability with your internal databases. A custom chain pulls a list of prospective grantees from Postgres, runs them through `search_nonprofits`, and appends missing DEI metrics using `get_demographics`.

Automated compliance record-keeping

Grantmakers require strict audit trails for every dollar disbursed. You wire `get_charity_check_pdf` into your approval pipeline to generate official compliance documents on the fly. The agent saves the file directly to your secure storage bucket. Tracking historical context matters just as much. By calling `search_grants` and `get_grant_details`, your application cross-references past foundation awards to confirm the new application aligns with historical funding patterns.

Setup guide

Set up Candid (GuideStar) 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 Candid (GuideStar) 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({
    "candid-guidestar-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 Candid (GuideStar) 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 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 LangChain

Initialize `MultiServerMCPClient` with the Vinkius endpoint URL. Call `client.get_tools()` and pass the resulting array into your ReAct agent creation function.

Yes. Your agent calls `search_grants` with specific foundation parameters. It then passes the results to `get_grant_details` to extract exact funding amounts and recipient data.

Every call to this integration appears in your LangSmith traces. You see the exact payload sent to the API and the JSON returned, making debugging straightforward.

Give your chain the `search_nonprofits` tool. The agent takes a raw organization name, finds the correct EIN, and updates your records automatically.

The V8 Isolate Sandbox destroys itself immediately after your query finishes. We never store the EINs, demographic queries, or compliance PDFs your agent requests.

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