How to Use the ReliefWeb MCP in CrewAI

Q: Can I use CrewAI to monitor ReliefWeb for specific disaster types?

Yes. You can assign a research agent to poll getdisasters and filter by type. If a match occurs, the agent can escalate the data to your human moderator for action.

Deploy autonomous humanitarian research crews using CrewAI and the ReliefWeb 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 CrewAI

Create your Vinkius account to connect ReliefWeb to CrewAI — 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Specialized agent research teams

Assign research tasks to your CrewAI agents using `get_reports` and `get_disasters`. One agent can gather data while another summarizes findings for your team. This division of labor speeds up your intelligence gathering. Agents share memory, so your lead agent always has the latest data from the field.

Automated field report monitoring

Set up a monitor agent to watch for updates via `get_reports`. When new documents are indexed, the agent can flag them for your human team to review. This keeps your operation informed without manual oversight. The agents filter through the noise, showing you only what requires immediate attention.

Cross-referenced data analysis

Combine `get_countries` and `get_themes` to build a complete picture of a crisis. Your crew can autonomously cross-reference these data points to find gaps in current humanitarian aid. It turns raw data into actionable intelligence. Your agents do the heavy lifting, connecting disparate data points so you can focus on the response strategy.

Setup guide

Set up ReliefWeb MCP in CrewAI

Prerequisites

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

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke ReliefWeb tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="ReliefWeb Analyst",
    goal="Access and analyze ReliefWeb data via MCP.",
    backstory="Expert analyst with direct ReliefWeb access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent ReliefWeb transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

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

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="ReliefWeb Analyst",
        goal="Access and analyze ReliefWeb data via MCP.",
        backstory="Expert analyst with direct ReliefWeb access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent ReliefWeb transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

Yes. You can assign a research agent to poll `get_disasters` and filter by type. If a match occurs, the agent can escalate the data to your human moderator for action.

You provide the server URL directly in your agent configuration. CrewAI handles the connection, allowing your agents to access tools like `get_reports` as if they were local functions.

It does. Because the tools are exposed to the entire crew, agents can share the retrieved data. This allows your team to collaborate on complex research tasks efficiently.

The server follows standard API rate limits. Your agents should be configured with appropriate wait times between calls to ensure consistent performance during heavy research tasks.

Your interactions are isolated within an ephemeral sandbox. The system clears your request data immediately after the agent finishes, ensuring that no sensitive humanitarian intelligence remains on the server.

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