How to Use the ReliefWeb MCP in LlamaIndex

Q: How do I connect the ReliefWeb MCP Server to LlamaIndex?

Install llama-index-tools-mcp and wrap the client in McpToolSpec. Call totoollistasync() to expose tools like getdisasters to your function agent.

Q: Can I build a RAG pipeline using ReliefWeb reports and LlamaIndex?

Yes, you can use getreport to fetch raw text and metadata, convert them into LlamaIndex document nodes, and index them in a vector database.

Q: How does LlamaIndex verify the source of a ReliefWeb document?

Your pipeline can run a validation query using getsources to check the publisher's credentials before indexing the report's content.

Q: Can I restrict which tools the indexer can access?

Yes, use the allowedtools filter in LlamaIndex to restrict your agent to specific data-gathering tools like getcountries or getthemes.

Index live ReliefWeb disaster data and situation reports directly into your LlamaIndex vector store using this 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 LlamaIndex

Create your Vinkius account to connect ReliefWeb to LlamaIndex — 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Index live disaster data into LlamaIndex

This MCP Server provides `get_disasters` to feed raw humanitarian crisis data directly into your LlamaIndex knowledge bases. Your indexer can pull active crisis profiles and write them directly to your vector store. This ensures your RAG pipeline queries live, ground-truth data instead of relying on outdated model parameters. When users ask about ongoing earthquakes or floods, the LlamaIndex query engine searches the local index populated by `get_reports`. This structure prevents hallucinations because every response is grounded in actual humanitarian reports fetched directly from the API.

Semantic search over humanitarian reports

By retrieving unstructured report text with `get_report`, LlamaIndex can build semantic search indexes over live crisis documentation. The indexer pulls the full text and metadata, storing them as document nodes that your agent can search semantically. You can filter these documents beforehand by querying `get_themes` to isolate topics like food security or sanitation. This setup lets you build deep research tools that connect historical disaster patterns with active field reports. Your agent can cross-reference old assessments with new entries to find matching operational gaps.

Ground RAG pipelines with verified organization data

This server exposes `get_sources` and `get_organizations` to let LlamaIndex validate report publishers before indexing their content. Your pipeline can run pre-retrieval steps to verify if a report comes from a trusted UN agency or a local NGO. This verification step ensures your knowledge base only contains vetted, high-quality humanitarian data. You can also index active aid opportunities by pulling listings via `get_jobs`. This lets your internal HR search tools query and categorize open positions across different regions and organizations automatically.

Setup guide

Set up ReliefWeb MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all ReliefWeb MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to ReliefWeb tools.",
)
response = await agent.run("List recent ReliefWeb data")

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 LlamaIndex

Install `llama-index-tools-mcp` and wrap the client in `McpToolSpec`. Call `to_tool_list_async()` to expose tools like `get_disasters` to your function agent.

Yes, you can use `get_report` to fetch raw text and metadata, convert them into LlamaIndex document nodes, and index them in a vector database.

Your pipeline can run a validation query using `get_sources` to check the publisher's credentials before indexing the report's content.

Yes, use the `allowed_tools` filter in LlamaIndex to restrict your agent to specific data-gathering tools like `get_countries` or `get_themes`.

No, the ReliefWeb MCP Server runs in a secure sandbox, processing queries locally so no raw search embeddings are exposed. It only fetches public disaster records and job listings, keeping your search history completely private.

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