n8n-mcp
Describe an automation in English, get a working n8n workflow
About n8n-mcp
n8n-mcp is an MCP server that lets Claude Code, Claude Desktop, Cursor, or Windsurf build n8n workflows for you. Instead of dragging nodes around a canvas and guessing at field names, you describe the automation you want and the agent wires up the actual nodes, credentials references, and connections.
Why it matters
- The MCP exposes n8n’s full node catalog to the model, so it picks real nodes with real parameters instead of hallucinating a plausible-looking config.
- Works across the major agent clients — no lock-in to one editor.
- Pairs naturally with self-hosted n8n, so the automation and your data both stay on infrastructure you control.
- Great for the long tail of internal glue work: notifications, syncs, scheduled scrapes, webhook fan-out.
Good for
Builders who already run n8n and want to stop hand-assembling workflows, and for anyone who has an automation idea but not the patience to learn a node catalog first. Setup is a standard MCP server entry in your client config.
More Github
Strix
Strix is an open-source AI agent that pentests your own application: it probes for vulnerabilities the way an attacker would, then reports what it found with enough context to actually fix it. For solo builders shipping AI-assisted code fast, it closes a gap that traditional linters and dependency scanners never covered. Why it earns a slot Runs real offensive-security workflows rather than pattern-matching source code, so it surfaces logic and auth flaws static tools miss. Reports come with reproduction steps and remediation guidance, not just a severity badge. Open source and self-run, which means your code and findings never leave your environment. Fits naturally after a vibe-coded sprint, where speed usually outruns security review. Use it responsibly Point it at systems you own or are explicitly authorized to test. Used that way it is a genuinely useful pre-launch gate — run it before you open signups, not after someone else does. Repo: github.com/usestrix/strix .
Langfuse
Langfuse is the observability layer most LLM apps are missing. It traces every call your app makes — prompts, completions, tool calls, latency, token cost — and gives you evals, datasets, and prompt management on top, so you can answer "why did it do that?" without re-running the whole thing by hand. What you get Tracing — nested spans across chains, agents, and tool calls, with cost and latency attached to each step. Evals — run model-based or custom scorers over datasets so prompt changes get measured instead of vibed. Prompt management — version prompts outside your codebase and roll them forward without a deploy. Integrations — OpenTelemetry, LangChain, LlamaIndex, LiteLLM, and the OpenAI SDK, so instrumenting is usually a few lines. Good for Anyone running an LLM feature in production, or anyone whose API bill is growing faster than their understanding of it. Self-host the whole thing or use the managed cloud; the core is MIT-adjacent open source and the project came out of YC W23. Repo: github.com/langfuse/langfuse .
Firecrawl
Firecrawl is the context API for AI apps. Point it at a URL — or a whole domain — and it returns clean, LLM-ready markdown instead of the tag soup you would get from a raw fetch. It handles JavaScript rendering, pagination, rate limits, and retries so your RAG pipeline stops being 200 lines of Puppeteer glue and prayer. Why builders use it Scrape a single page, crawl an entire site, or run a search that returns full page content — one API for all three. Output is markdown or structured JSON, which means fewer tokens burned on HTML noise and better retrieval quality. Handles the annoying parts: dynamic JS pages, PDFs, proxies, and anti-bot friction. Open source and self-hostable, with a managed cloud tier when you would rather not run crawlers yourself. Good for Feeding agents real web context, building RAG over documentation, competitor monitoring, and any place you need the live web as a dependable input rather than a scraping side-quest. With 160k+ stars it has become the default answer to "how do I get the web into my model?" Get started at github.com/firecrawl/firecrawl .
promptfoo
promptfoo lets you test your prompts, agents, and RAG systems with simple declarative configs — plus red-teaming and vulnerability scanning to catch failures before your users do. Compare GPT, Claude, Gemini, and DeepSeek side by side. It plugs into the command line and CI/CD, so evals run automatically on every change instead of living in someone’s head. Used by teams at OpenAI and Anthropic, it is one of the most practical ways to make agent quality measurable.
caveman
caveman is a gloriously simple Claude Code skill with a serious payoff: it strips your prompts down to terse, caveman-style phrasing — "why use many token when few token do trick" — and cuts roughly 65% of token usage as a result. It is half meme, half real optimization. The underlying insight is sound: models do not need your politeness or filler to understand intent, and trimming it saves money on every call. Worth a look if your Claude Code bills are creeping up.