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.
git clone --depth 1 https://github.com/nuoyax/web-search-mcpInstalling this writes the configuration, not the program: `node` runs a file from the repository, so clone it first and make the path in the command match where you put it.
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.
[](https://agentmods.dev/mcp/nuoyax/web-search-mcp/web-search)<a href="https://agentmods.dev/mcp/nuoyax/web-search-mcp/web-search"><img src="https://agentmods.dev/badge/mcp/nuoyax/web-search-mcp/web-search/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.
<a href="https://agentmods.dev/mcp/nuoyax/web-search-mcp/web-search"><img src="https://agentmods.dev/badge/mcp/nuoyax/web-search-mcp/web-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
web-search 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 1mo 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
{
"web-search": {
"command": "node",
"args": [
"./index.js"
],
"env": {
"PROXY_URL": "http://127.0.0.1:7890"
}
}
}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.
- 1mo ago First seen · 11 lines scan A f257c6589bb9
web-search is an MCP server published in the GitHub repository nuoyax/web-search-mcp (0 stars, last pushed 27d ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. 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 mcp servers, from other repositories
mastra
TypeScript Execute (tsx): Node.js enhanced with esbuild to run TypeScript & ESM files. Runs locally from the tsx npm package. Needs 1 environment variable to run.
semantic-cache-mcp
MCP file cache for AI coding agents: re-reads cost 40 tokens, changed files return diffs, grep and BM25 search over the cache. Runs locally from the semantic-cache-mcp Python package.
mcp
Detect prompt injection, jailbreaks, and code injection in untrusted text before it reaches an LLM. Runs locally from the @safeprompt.dev/mcp npm package. Needs 3 environment variables to run.
sibyl
AI-powered deep research agent — market analysis, trend prediction, topic research with multi-LLM support. Runs locally from the sibyl-research Python package.
mdan-method
MDAN — AI-driven development methodology: agents, step-by-step wizards, multi-agent debate and a context graph, as IDE commands and an MCP server. Runs locally from the mdan-method npm package.
rippr-mcp
Rip YouTube transcripts to disk for AI agents, RAG pipelines, and LLM workflows. Runs locally from the rippr-mcp npm package.