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.
/plugin marketplace add cyanheads/reliefweb-mcp-servernpx agentmods add plugins/cyanheads/reliefweb-mcp-server/reliefweb-mcp-servergit clone --depth 1 https://github.com/cyanheads/reliefweb-mcp-serverWrote 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.
[](https://agentmods.dev/plugins/cyanheads/reliefweb-mcp-server/reliefweb-mcp-server)<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="Measured on agentmods" height="20"></a>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 5d 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.
What it actually says
{
"name": "reliefweb-mcp-server",
"version": "0.2.1",
"description": "Search ReliefWeb humanitarian reports, disasters, jobs, training, and country profiles via MCP. STDIO or Streamable HTTP.",
"author": {
"name": "cyanheads"
},
"homepage": "https://github.com/cyanheads/reliefweb-mcp-server#readme",
"repository": "https://github.com/cyanheads/reliefweb-mcp-server",
"license": "Apache-2.0",
"mcpServers": {
"reliefweb-mcp-server": {
"command": "npx",
"args": ["-y", "@cyanheads/reliefweb-mcp-server"],
"env": {
"MCP_TRANSPORT_TYPE": "stdio",
"RELIEFWEB_APP_NAME": "your-app-name"
}
}
}
}
What it installs
The manifest is a name and a version. 32 skills, 1 MCP server travel with it, and installing the plugin installs all of them — 2,220 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill design-mcp-server A 62 tokens
- Skill add-tool A 35 tokens
- Skill api-context A 79 tokens
- Skill api-linter A 86 tokens
- Skill api-canvas A 85 tokens
- Skill api-errors A 54 tokens
- Skill api-testing A 46 tokens
- Skill field-test A 76 tokens
- Skill orchestrations A 159 tokens
- Skill api-config A 43 tokens
- Skill api-telemetry A 85 tokens
- Skill git-wrapup A 82 tokens
- Skill maintenance A 75 tokens
- Skill polish-docs-meta A 54 tokens
- Skill security-pass A 118 tokens
- Skill tool-defs-analysis A 177 tokens
- Skill add-service A 38 tokens
- Skill add-test A 41 tokens
- Skill api-workers A 51 tokens
- Skill release-and-publish A 112 tokens
- Skill report-issue-framework A 52 tokens
- Skill add-app-tool A 41 tokens
- Skill add-resource A 32 tokens
- Skill api-auth A 58 tokens
- Skill report-issue-local A 44 tokens
- Skill setup A 58 tokens
- Skill api-mirror A 68 tokens
- Skill add-prompt A 37 tokens
- Skill api-utils A 37 tokens
- Skill code-simplifier A 124 tokens
- Skill techniques A 79 tokens
- Skill api-services A 32 tokens
- MCP server reliefweb-mcp-server A not measured
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.
- 5d ago First seen · 22 lines scan A 8017183a9a5e
reliefweb-mcp-server is a plugin published in the GitHub repository cyanheads/reliefweb-mcp-server (1 stars, last pushed 11d 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.
Other plugins, from other repositories
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.
sandy-cli
Sandy: sandboxed TypeScript execution for AWS queries via the sandy CLI.
supsub-cli
Agent skills for the SupSub CLI: auth / sub / search / mp / focus / group / unread / deepread.
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.
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.
brave-search
Full-featured Brave Search API skill: web, images, videos, news, suggest, spellcheck, local POIs, rich results, AI summarizer, and LLM context endpoints.