How to Use the ReliefWeb MCP in LangChain

Q: How do I register the ReliefWeb MCP Server with LangChain?

Install langchain-mcp-adapters and pass the server URL to the client. Then call gettools() to expose the humanitarian tools to your agent.

Q: Can my LangChain agent search for specific document types using this ReliefWeb setup?

Yes, your agent can query getformats to find the correct format ID, then use it as a filter inside getreports to return only maps or situation reports.

Feed live disaster data and humanitarian reports directly into your LangChain reasoning loops with 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 LangChain

Create your Vinkius account to connect ReliefWeb to LangChain — 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Build multi-step humanitarian workflows in LangChain

This MCP Server exposes `get_disasters` so your LangChain agents can map active crises dynamically by chaining outputs. Your agent calls the disaster tool to flag a sudden cyclone, then feeds that geographic output directly into `get_reports` to pull the latest sitreps. This chain bypasses hardcoded API logic, letting the model decide which disaster needs immediate coverage based on live data. Because LangChain traces every step, you can audit how the agent filtered the reports using `get_formats` to isolate maps or assessments. If your chain fails to locate local data, you see exactly where the tool call stalled in LangSmith.

Trace and debug complex ReliefWeb queries

Using `get_jobs` within a LangChain workflow allows your agent to search and track humanitarian aid opportunities without manual parsing. This server exposes clean schemas so LangChain can map job types directly to your internal recruitment pipelines. You can watch the agent negotiate filters like organization types or specific languages in real-time. If the agent gets stuck trying to match a job to a country ID, you can trace the exact payload sent to `get_countries`. This visibility prevents your chains from getting trapped in loops when trying to resolve mismatched location names.

Route humanitarian updates to custom destinations

This server connects `get_report` to your LangChain graphs, letting your agents grab specific humanitarian updates and route them to other tools. For example, your agent can grab a specific report and immediately write the summary to a shared Slack channel or save it to a local database. By mapping themes with `get_themes`, the agent routes health or shelter updates to specific regional teams. This lets you build complex, multi-source chains that keep field offices informed without writing custom API integrations for every single tool.

Setup guide

Set up ReliefWeb MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes ReliefWeb tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "reliefweb-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent ReliefWeb transactions"
    })
    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 LangChain

Install `langchain-mcp-adapters` and pass the server URL to the client. Then call `get_tools()` to expose the humanitarian tools to your agent.

Yes, your agent can query `get_formats` to find the correct format ID, then use it as a filter inside `get_reports` to return only maps or situation reports.

LangChain's tracing tools let you monitor how often tools like `get_jobs` are called, helping you optimize your chain's step logic to avoid hitting API thresholds.

Yes, the connection is stateless by default, but you can use `client.session()` to maintain context across multiple report analysis steps.

The Vinkius sandbox isolates all outgoing calls to the ReliefWeb MCP Server. Only public metadata, job postings, and disaster logs are processed, meaning no internal organizational data ever leaves your local LangChain 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