Nodebench runs on your own machine — the client starts it, so there is no endpoint to ping. 75 installs a week from npm. Last commit 1 Nov 2026.
260 MCP tools across 49 domains. AI Flywheel, quality gates, research, web scraping.
We read the source, 23 h ago · rules 995398eba69f
A value the model can set ends up inside a file or shell call. That is not a flaw by itself — for a terminal server it is the job — but it is where things go wrong when it is not.
fs.writeFileSync(fullPath, file.content, "utf-8");
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
пакет nodebench-mcp ссылается на homenshum/nodebench-ai
const r = spawnSync(process.execPath, [resolve(HERE, 'scan.mjs')], { cwd: REPO, encoding: 'utf8' });
function ArtifactsTab({ media, documents, hasThread, onDocumentSelect }: ArtifactsTabProps) {
const totalSources = media.webSources.length + media.secDocuments.length;
const filePath = path.join(NOTES_DIR, filename);
os.system(f"{sys.executable} -m pip install edge-tts")
const url = `https://api.telegram.org/bot${token}/${method}`;
const ruleFiles = fs.readdirSync(rulesDir).filter((f: string) => f.startsWith("nodebench-") && f.endsWith(".md"));
container.innerHTML = html;
Found in continuous integration, deployment or infrastructure files, or in a neighbouring package of the same monorepo. None of this is installed when you add the server: it describes how the project is built and released. We list it because a leaked key in a build pipeline is still a real problem, but it is not something this server does on your machine.
NODEBENCH_API: ${{ secrets.NODEBENCH_API_URL || 'https://langgraph-agent-873372783709.us-central1.run.app' }}
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
That is not a flaw by itself — but it is where things go wrong when it is not the job. We re-read this code on every release. Watch it and you hear from us the day another one appears.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add nodebench -- npx -y nodebench-mcp
{
"mcpServers": {
"nodebench": {
"command": "npx",
"args": [
"-y",
"nodebench-mcp"
]
}
}
}
[mcp_servers.nodebench]
command = "npx"
args = ["-y", "nodebench-mcp"]
{
"mcpServers": {
"nodebench": {
"command": "npx",
"args": [
"-y",
"nodebench-mcp"
]
}
}
}
{
"servers": {
"nodebench": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"nodebench-mcp"
]
}
}
}
MCP server providing Google Search, web scraping, and multi-source research tools for AI assistants
Web scraping, crawling, deep research & autonomous extraction — 31 MCP tools, clean Markdown/JSON
Metalift MCP for AI agents: web search (2 credits), scrape, crawl, and map tools
Structured web research tool for AI agents: search, fetch and shape web data into the JSON schema…
Web search, scraping, RAG answers with citations, and translation as MCP tools.
Web scraping + research toolkit for AI agents: scrape, crawl, monitor URLs with anti-bot bypass.
23 live research tools, from web search to SEC filings. Each call bills the scraper it runs.
Firecrawl MCP — wraps the Firecrawl API (firecrawl.dev) for web scraping / crawling / search…
Answers built from our own checks of this server.