What is reliefweb-mcp-server?

An MCP server for searching ReliefWeb, a United Nations information service about humanitarian crises and disaster response. It can search reports, disasters, jobs, training, and country profiles through a local process or a network connection.

Finding humanitarian reports, disaster information, related jobs, training opportunities, and country profiles. It can be connected over standard input/output or Streamable HTTP.

It lets a coding agent retrieve humanitarian information through one structured interface instead of requiring manual website searches. The input does not describe filtering, saving, or analysis features beyond searching.

reliefweb-mcp-server — Plugin for Claude Code by cyanheads

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo

git clone --depth 1 https://github.com/cyanheads/reliefweb-mcp-server

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/cyanheads/reliefweb-mcp-server/reliefweb-mcp-server/github.svg)](https://agentmods.dev/plugins/cyanheads/reliefweb-mcp-server/reliefweb-mcp-server)

Your own site

<a href="https://agentmods.dev/plugins/cyanheads/reliefweb-mcp-server/reliefweb-mcp-server"><img src="https://agentmods.dev/badge/plugins/cyanheads/reliefweb-mcp-server/reliefweb-mcp-server/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/plugins/cyanheads/reliefweb-mcp-server/reliefweb-mcp-server"><img src="https://agentmods.dev/badge/plugins/cyanheads/reliefweb-mcp-server/reliefweb-mcp-server.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured The manifest loads nothing itself; its 33 skills, 1 MCP server cost 2,508 tokens a session between them.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

reliefweb-mcp-server scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude-plugin/plugin.json · 34 lines

What it actually says

{
  "$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
  "name": "reliefweb-mcp-server",
  "version": "0.2.3",
  "description": "Search ReliefWeb humanitarian reports, disasters, jobs, training, and country profiles via MCP. STDIO or Streamable HTTP.",
  "author": {
    "name": "cyanheads",
    "email": "[email protected]",
    "url": "https://github.com/cyanheads"
  },
  "homepage": "https://github.com/cyanheads/reliefweb-mcp-server#readme",
  "repository": "https://github.com/cyanheads/reliefweb-mcp-server",
  "license": "Apache-2.0",
  "keywords": ["mcp", "mcp-server", "model-context-protocol", "reliefweb", "humanitarian", "disasters"],
  "userConfig": {
    "reliefweb_app_name": {
      "type": "string",
      "title": "ReliefWeb App Name",
      "description": "Pre-approved appname for the ReliefWeb API v2. Register at https://reliefweb.int/help/api.",
      "required": true
    }
  },
  "mcpServers": {
    "reliefweb-mcp-server": {
      "command": "npx",
      "args": ["-y", "@cyanheads/reliefweb-mcp-server"],
      "env": {
        "MCP_TRANSPORT_TYPE": "stdio",
        "RELIEFWEB_APP_NAME": "${user_config.reliefweb_app_name}"
      }
    }
  }
}

Contents

What it installs

The manifest is a name and a version. 33 skills, 1 MCP server travel with it, and installing the plugin installs all of them — 2,508 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

11d ago Changed 82ec605f8164
1mo ago Changed · +12 lines 3f67999f988a
1mo ago First seen · 22 lines scan A 8017183a9a5e

Subscribe to this mod's changes

reliefweb-mcp-server is a plugin published in the GitHub repository cyanheads/reliefweb-mcp-server (1 stars, last pushed 12d ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Research ai-agent bun crisis-data disasters humanitarian humanitarian-aid

ccmux

Drive the ccmux cross-harness CLI to dispatch work to other AI coding agents (Claude Code, Codex, Cursor, OpenCode, Pi, Gemini) through programmatic ccmux invoke calls. Requires the ccmux CLI on PATH.

epilande/ccmux · not measured

sandy-cli

Sandy: sandboxed TypeScript execution for AWS queries via the sandy CLI.

jamestelfer/sandy · not measured

supsub-cli

Agent skills for the SupSub CLI: auth / sub / search / mp / focus / group / unread / deepread.

SupSub-AI/supsub-cli · not measured

vibegroup

Ask peer Claude Code agents in other repos and machines what they're working on, over an end-to-end-encrypted relay. Answers come from their live session via Claude Code Channels.

TerryCM/vibegroup · not measured

graph-engineering

Runs coding work as an explicit execution graph (DAG) instead of a natural-language conversation. Deterministic work is executed by the server with zero LLM calls, the points where a human steps in are declared in the graph, and run state is owned by the server rather than the conversation.

sciencemj/graph-engineering · not measured

brave-search

Full-featured Brave Search API skill: web, images, videos, news, suggest, spellcheck, local POIs, rich results, AI summarizer, and LLM context endpoints.

bdmorin/the-no-shop · not measured