How to Use the ReliefWeb MCP in Vercel AI SDK

Q: Can I use ReliefWeb data in my AI-SDK project to track regional crises?

Yes. You can use the getdisasters tool to pull active incident lists into your app. Your agent manages the data flow, letting you display regional alerts as they happen.

Q: How do I fetch specific report formats using ReliefWeb with AI-SDK?

Call getformats to identify the correct ID, then pass that to getreports in your tool execution logic. This ensures your app only processes the document types you actually need.

Q: Is it possible to filter jobs by location using ReliefWeb and AI-SDK?

Yes. You can pass country parameters to getjobs to narrow down results. Your agent handles the filtering logic before returning the data to your UI.

Stream humanitarian data directly into your React UI with the ReliefWeb MCP Server and the Vercel AI SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect ReliefWeb MCP to Vercel AI SDK

Create your Vinkius account to connect ReliefWeb to Vercel AI SDK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup ReliefWeb with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Real-time disaster data streaming

Pipe live disaster updates straight to your frontend components. When your AI client executes `get_disasters`, the results stream into your interface without waiting for a full page reload. This keeps your dashboard current during fast-moving crises. Your users see incident details as they hit the database, ensuring your UI reflects ground truth immediately.

Direct report injection for AI-SDK

Feed structured humanitarian reports into your generation loop using `get_reports`. By passing these findings through the AI-SDK, your interface renders context-rich summaries for your end users. It removes the friction of manual data entry. Your application pulls the exact metadata needed to populate your views, keeping the data flow clean and reactive.

Humanitarian job board integration

Populate your career portal by connecting `get_jobs` to your application state. Your agent fetches the latest listings, allowing you to build dynamic job boards that stay updated automatically. This provides a live feed of open roles to your users. You control exactly how the data appears, turning raw API output into a functional part of your site.

Setup guide

Set up ReliefWeb MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all ReliefWeb tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent ReliefWeb transactions",
});

console.log(text);
await mcpClient.close();

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 ReliefWeb. 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 ReliefWeb 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 ReliefWeb MCP in Vercel AI SDK

Yes. You can use the `get_disasters` tool to pull active incident lists into your app. Your agent manages the data flow, letting you display regional alerts as they happen.

Call `get_formats` to identify the correct ID, then pass that to `get_reports` in your tool execution logic. This ensures your app only processes the document types you actually need.

It does. The MCP connection allows your agent to stream tool outputs directly to your interface. You see the data populate your components as the server returns it.

Yes. You can pass country parameters to `get_jobs` to narrow down results. Your agent handles the filtering logic before returning the data to your UI.

This server only accesses public humanitarian records. It does not store personal information or user credentials, keeping your data footprint minimal and focused solely on public-domain reports.

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