How to Use the ReliefWeb MCP in AutoGen

Q: How do I register the ReliefWeb MCP Server with an AutoGen assistant?

Use mcpservertools to fetch tools like getdisasters and pass the list directly to your AutoGen AssistantAgent constructor.

Let your AutoGen agents debate and verify ReliefWeb disaster data using this dedicated MCP Server.

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 AutoGen

Create your Vinkius account to connect ReliefWeb to AutoGen — 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Coordinate AutoGen agents to debate ReliefWeb data

This MCP Server exposes `get_disasters` and `get_reports` so your AutoGen agents can debate live crisis data during planning. One agent can pull active crisis data while another searches for operational reports. They can debate the severity of a flood based on conflicting field reports before recommending resources. By using `get_formats`, a data-quality agent can reject unstructured press releases, forcing the retrieval agent to find structured situation reports instead. This back-and-forth ensures your system reaches a vetted consensus before generating summaries.

Build multi-agent job routing pipelines

By exposing `get_jobs`, this server lets your AutoGen team monitor humanitarian job postings and negotiate field placements. You can set up a team where one agent monitors job postings and another evaluates candidate profiles. The agents negotiate which roles match your organization's current field deployments, using `get_countries` to verify geographic requirements. This collaborative filtering prevents single-agent bias, ensuring that open positions are analyzed from both a logistics and a human resources perspective before any application is drafted.

Validate humanitarian sources through agent consensus

Using `get_sources` and `get_organizations` allows your AutoGen agents to verify the credibility of humanitarian reports before reaching consensus. When a new report is pulled via `get_report`, a security agent checks the publisher's reputation while a logistics agent verifies the physical coordinates. They debate whether the report's themes, verified via `get_themes`, align with known regional crises. The agents only save the report to your central database once they agree on its validity, preventing unvetted rumors from polluting your system.

Setup guide

Set up ReliefWeb MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes ReliefWeb tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="ReliefWeb_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent ReliefWeb data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="ReliefWeb_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent ReliefWeb data")
    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 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 AutoGen

Use `mcp_server_tools` to fetch tools like `get_disasters` and pass the list directly to your AutoGen `AssistantAgent` constructor.

Yes, the server handles concurrent requests, allowing your retrieval agent to pull reports using `get_reports` while your routing agent checks country codes via `get_countries`.

You can program your agents to debate discrepancies between reports by comparing metadata fetched through `get_report` and validating the sources with `get_sources`.

It supports both stdio and Streamable HTTP transports, making it easy to deploy within your existing AutoGen infrastructure.

No, the ReliefWeb MCP Server only queries public data, such as country codes, disaster logs, and organization metadata. Your private coordination logs and agent prompts never leave your local environment.

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