How to Use the ReliefWeb MCP in OpenAI Agents SDK

Q: Can I trace specific ReliefWeb tool executions inside my OpenAI Agents SDK dashboard?

Yes, every single tool call like getreports or getdisasters shows up in your run traces. You see the exact inputs, raw outputs, and execution latency directly in the OpenAI developer portal.

Q: How do specialized sub-agents share ReliefWeb data from this MCP server using the OpenAI Agents SDK?

You can set up a routing agent that calls getcountries and hands off the ISO codes to a regional analyst agent. The SDK handles this handoff natively, maintaining the tool context across different agent boundaries.

Q: How can I filter the types of documents my agent reads from this server?

Your agent runs getthemes to find specific topic IDs like health or shelter. It then passes those parameters into getreports to restrict the search to relevant humanitarian documents.

Q: How does this setup secure the humanitarian reports and job data retrieved from the ReliefWeb MCP server?

All data from getreports and getjobs runs through an ephemeral V8 sandbox on Vinkius. Your OpenAI Agents SDK client connects via a single token, ensuring no raw API keys are exposed to the LLM.

Build production-grade humanitarian tracking agents using the OpenAI Agents SDK to parse live disaster feeds.

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 OpenAI Agents SDK

Create your Vinkius account to connect ReliefWeb to OpenAI Agents 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Run safe disaster monitoring with this MCP Server

Your OpenAI agent uses `get_disasters` to pull active crisis events from this MCP server and feeds them directly into specialized sub-agents. The SDK handles safety checks on these outputs, meaning you can run automated crisis tracking without worrying about raw API data causing unexpected model loops. By calling `get_countries` alongside the disaster feed, your agent maps the exact geographic boundaries of an emergency while the SDK traces the token usage. This setup routes vetted crisis data to your dashboard, giving you a clean trace of every API call during active operations.

Automate humanitarian job matching safely

The OpenAI Agents SDK executes `get_jobs` to monitor staffing needs across global relief organizations. It automatically checks the retrieved job postings against your custom guardrails before passing anything to your main deployment pipeline. Your agent uses `get_organizations` to filter out unverified employers before suggesting roles. This keeps your automated hiring platform clean and compliant with internal organizational standards.

Validate and trace incoming relief reports

When your agent calls `get_reports` to parse incoming field data, the OpenAI SDK traces the entire payload size and token usage. It feeds the raw text into `get_report` to extract specific crisis details like casualty numbers or food shortages. The system filters these documents using `get_formats` to isolate official situation updates from opinion pieces. You get a clean, validated stream of ground-truth updates in your production logs.

Setup guide

Set up ReliefWeb MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all ReliefWeb tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives ReliefWeb tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate ReliefWeb tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="ReliefWeb Agent",
            instructions="You have access to ReliefWeb tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

The SDK manages HTTP connections via the MCPServerStreamableHttp class to avoid rate limit spikes. If ReliefWeb limits your requests, the SDK handles the backoff strategy automatically to prevent agent crashes.

Yes, every single tool call like `get_reports` or `get_disasters` shows up in your run traces. You see the exact inputs, raw outputs, and execution latency directly in the OpenAI developer portal.

You can set up a routing agent that calls `get_countries` and hands off the ISO codes to a regional analyst agent. The SDK handles this handoff natively, maintaining the tool context across different agent boundaries.

Your agent runs `get_themes` to find specific topic IDs like health or shelter. It then passes those parameters into `get_reports` to restrict the search to relevant humanitarian documents.

All data from `get_reports` and `get_jobs` runs through an ephemeral V8 sandbox on Vinkius. Your OpenAI Agents SDK client connects via a single token, ensuring no raw API keys are exposed to the LLM.

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