How to Use the ReliefWeb MCP in Pydantic AI

Q: How does Pydantic AI handle schema mismatches from ReliefWeb?

If a tool like getreports returns unexpected fields, Pydantic AI throws a validation error at runtime. This prevents your agent from processing incomplete or malformed humanitarian data.

Q: Can I use Pydantic AI to validate ReliefWeb job postings before processing?

Yes, you can map the JSON output of getjobs to a custom Pydantic model. The framework will verify that every field, from posting date to organization type, matches your exact type definitions.

Q: How do I filter reports by specific themes using this framework?

Your agent calls getthemes to find the correct theme ID, then passes it to getreports. The returned JSON is parsed and validated against your defined schema before the model reads it.

Q: How does this setup protect the humanitarian and disaster data retrieved from the ReliefWeb MCP server?

All data from getdisasters and getreports is processed in a secure, ephemeral Vinkius sandbox. Pydantic AI connects via a single endpoint token, meaning your local environment variables and keys are never exposed.

Build type-safe humanitarian tracking pipelines using Pydantic AI to validate every report.

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 Pydantic AI

Create your Vinkius account to connect ReliefWeb to Pydantic AI — 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Force strict type safety on this MCP Server

Your Pydantic AI agent uses `get_disasters` to fetch active crisis events from this MCP server and validates the schema at runtime. If the API structure changes, the framework raises a loud validation error immediately instead of feeding garbage data to your model. By calling `get_countries`, the agent maps incoming ISO codes against strict Pydantic models. This ensures your downstream data processing pipelines never ingest malformed geographic parameters.

Validate humanitarian job postings at runtime

The framework executes `get_jobs` to pull current employment listings across global aid organizations. Pydantic AI parses the job titles, locations, and posting dates directly into typed Python objects. It checks these fields against your defined schemas using `get_organizations` to confirm the posting NGO is verified. You get clean, validated data without writing manual parsing logic.

Parse structured situation reports safely

When your agent calls `get_reports`, Pydantic AI validates the structure of the metadata before passing it to the model. The agent can then safely call `get_report` to extract specific crisis details without risk of hallucinating empty fields. It filters the documents using `get_formats` to ensure only official PDFs and text files are processed. This keeps your data pipelines running with predictable, typed inputs.

Setup guide

Set up ReliefWeb MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "reliefweb-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to ReliefWeb tools.",
)

result = await agent.run("List recent ReliefWeb transactions")
print(result.output)

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 Pydantic AI

If a tool like `get_reports` returns unexpected fields, Pydantic AI throws a validation error at runtime. This prevents your agent from processing incomplete or malformed humanitarian data.

Yes, you can map the JSON output of `get_jobs` to a custom Pydantic model. The framework will verify that every field, from posting date to organization type, matches your exact type definitions.

You initialize the connection using MCPToolset with your Vinkius HTTP endpoint. Pass this toolset directly to your Agent constructor, and the framework will auto-discover all nine tools.

Your agent calls `get_themes` to find the correct theme ID, then passes it to `get_reports`. The returned JSON is parsed and validated against your defined schema before the model reads it.

All data from `get_disasters` and `get_reports` is processed in a secure, ephemeral Vinkius sandbox. Pydantic AI connects via a single endpoint token, meaning your local environment variables and keys are never exposed.

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