How to Use the GlobalGiving MCP in LangChain

Q: Can LangChain automate my GlobalGiving data analysis?

Yes, you set up a loop where the agent calls getprojectdetails and processes the JSON output. It handles the data extraction based on the instructions you provide in the system prompt.

Chain GlobalGiving data directly into your LangChain agents to automate project discovery and charity research.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect GlobalGiving MCP to LangChain

Create your Vinkius account to connect GlobalGiving 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 GlobalGiving with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build reasoning chains with GlobalGiving

Feed the output of `list_projects_by_theme` directly into your next agent step. You define the logic flow where the agent evaluates project data before deciding its next move. This setup removes manual data handling. Your agent chains these tool calls to compare initiatives without you needing to write custom parsing scripts.

Trace your GlobalGiving tool usage

Monitor every request sent to the API using LangSmith. You see exactly how `search_nonprofit_projects` performs during your agent's decision-making process. Latency and token counts are visible for every link in the chain. You catch bottlenecks in your multi-step pipelines before they impact your results.

Aggregate multiple servers for complex tasks

Combine this MCP server with other data sources in a single agent workflow. Your pipeline manages GlobalGiving data alongside your local databases or vector stores. Everything stays stateless unless you explicitly define a session. You keep your agent architecture clean and focused on specific data retrieval tasks.

Setup guide

Set up GlobalGiving 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 GlobalGiving 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({
    "globalgiving-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 GlobalGiving 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 GlobalGiving. 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 GlobalGiving 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 GlobalGiving MCP in LangChain

Install the MCP adapters and point your client to the server URL. You then call the tool discovery method and inject the results into your agent constructor.

Yes, you set up a loop where the agent calls `get_project_details` and processes the JSON output. It handles the data extraction based on the instructions you provide in the system prompt.

The server remains stateless by default. You use the client session object if you need to maintain context between multiple tool calls during a single run.

Your chain catches the error through standard exception handling. You can define fallback logic or retry loops within your agent's reasoning path.

The server manages your credentials internally. It only exposes specific project and charity data types to your agent based on the tools you authorize.

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