Original URL: https://getagenttools.com/ CURATED BY AN OPERATOR, NOT A CRAWLER # The short list of AI agent tools that *actually work.* Every tool here ran inside a real production workflow first. 31 made the list. The other two hundred did not. Verdicts from daily use, re-checked monthly. [Browse the tools](https://getagenttools.com/#tools)[Train your team](https://getagenttools.com/#training) No sponsored placements. No scraped lists. ![GAT: Gather, Assess, Trigger. A black pawn casts the shadows of a rook, bishop, queen, knight and king.](https://getagenttools.com/images/hero-2026-09-05-v2/1536/gat-hero-pawn-base.webp) **31**tools tested **12**running daily in production **9**categories **0**sponsored placements FEATURED ## Picks from the list Twelve tools carrying real workflows right now. Each entry says what it is good at and when to skip it, and each one links to [a full review](https://getagenttools.com/tools/). ### [Claude Code](https://getagenttools.com/tools/claude-code/) RUNNING Agentic coding and ops in the terminal. > Runs my daily operations: reports, deploys, file work, whole pipelines. The tool I measure every other agent against. BEST FOR real work in real repos, end to end SKIP IF you want a chat window, not a worker \# coding-agents ### [MCP servers](https://getagenttools.com/tools/mcp-servers/) RUNNING One protocol to wire agents into your tools. > Design files, analytics, email, hosting. One standard instead of custom glue per app. This is where agent stacks are heading. BEST FOR connecting agents to an existing stack SKIP IF you automate a single app \# mcp-servers ### [Playwright](https://getagenttools.com/tools/playwright/) RUNNING Browser control agents can rely on. > Logins, scraping, UI checks. Handles real-world pages and auth better than anything else I put into rotation. BEST FOR web automation behind a login SKIP IF plain HTTP gets the data \# browser-automation ### [Best AI SEO Tools](https://getagenttools.com/tools/best-ai-seo-tools/) RUNNING The production stack behind my SEO agent. > Claude Code, Ahrefs, Search Console, Playwright and a custom agent. Each tool has one job, a human approves what ships. BEST FOR running SEO as an agent workflow SKIP IF you publish twice a year \# custom-agents ### [Meta Ads API](https://getagenttools.com/tools/meta-ads-api/) RUNNING Paid social under full agent control. > Full scope: campaigns, ad sets, creatives, audiences, budgets and reporting. Agents run the ops, a human signs off on spend. BEST FOR automating Meta campaigns end to end SKIP IF you run one campaign and edit it by hand \# ad-platforms ### [Google Ads API](https://getagenttools.com/tools/google-ads-api/) RUNNING Search campaigns without the console grind. > Full scope: campaigns, keywords, bids, budgets and reports. Same rule as Meta, agents operate, humans approve spend. BEST FOR search ops at scale SKIP IF spend is too small to automate \# ad-platforms ### [Make](https://getagenttools.com/tools/make/) RUNNING No-code glue that keeps running for months. > Lead forms to sheets, webhooks to CRMs. Scenarios I built once and stopped thinking about. BEST FOR wiring SaaS apps without code SKIP IF the logic fits in thirty lines of code \# orchestration ### [n8n](https://getagenttools.com/tools/n8n/) RUNNING Visual workflows with an agent layer on top. > The AI nodes matured enough to carry production pipelines. Visual ops the whole team can read. BEST FOR teams that want visual ops SKIP IF your team prefers code-first \# orchestration ### [Search Console API](https://getagenttools.com/tools/google-search-console-api/) RUNNING Real search queries and positions, from the source. > Every content decision on this site starts from it: real queries, real positions, and whether Google indexed the page at all. Estimates describe the market; this describes my pages. BEST FOR planning content from measured demand SKIP IF the site you care about is not yours \# data-scraping ### [Figma MCP](https://getagenttools.com/tools/figma-mcp/) RUNNING Design files agents can read, not guess. > Entire landing pages went from mockup to deployed code through it. Node ids make prompts precise, tokens survive into the code, and the visual check stays human. BEST FOR design-to-code with a real design file SKIP IF the project has no design artifact \# mcp-servers ### [Telegram Bot API](https://getagenttools.com/tools/telegram-bot-api/) RUNNING The channel my agents report through. > Background work is invisible until a message says what happened. Daily numbers to a group, failures to my DM, one POST request each, read within minutes. BEST FOR closing the loop on every automated job SKIP IF your team does not live in Telegram \# monitoring-evals ### [Google Sheets API](https://getagenttools.com/tools/google-sheets-api/) RUNNING The table humans and agents co-author. > Agents append rows and fill blanks, people read, filter and correct. Append-only writes plus a dedup key made months of reruns boring, with zero data lost. BEST FOR reports non-technical people actually use SKIP IF no human ever opens the sheet \# data-scraping BROWSE ## Tools by job Categories follow what agents do all day, not marketing labels. ### Coding agents4 Agents that write, fix and ship code. ### MCP servers6 Connectors between agents and your tools. ### Memory & context2 What your agent remembers between runs. ### Browser automation3 Clicking, scraping and testing the web. ### Orchestration4 Multi-step and multi-agent pipelines. ### Data & scraping4 Feeding agents clean, current data. ### Monitoring & evals3 Knowing when your agent breaks, before users do. ### Ad platforms2 Campaigns agents operate, humans approve. ### SaaS building3 From idea to shipped product, agents in the loop. METHOD ## How a tool gets on the list 01 ### Run it Every candidate goes into a live workflow for at least two weeks. A demo is not evidence. 02 ### Break it I note what fails: rate limits, quirks, silent costs, the parts changelogs skip. 03 ### Verdict RUNNING, TESTED or WATCHING. Re-checked monthly. Tools get dropped. The list stays short. BLOG ## Latest field notes Write-ups from daily use: what shipped, what got cut, and what I would not run again. ### [opencode --dangerously-skip-permissions: a hidden alias for --auto, and what deny rules still stop](https://getagenttools.com/blog/opencode-dangerously-skip-permissions/) 23 Oct 2026 opencode accepts --dangerously-skip-permissions as a hidden alias for --auto. What it approves, what deny rules still block, and the permission config in opencode.json. - opencode - coding-agents - agent-security ### [Codex dangerously skip permissions: --dangerously-bypass-approvals-and-sandbox and the safer pair](https://getagenttools.com/blog/codex-dangerously-skip-permissions/) 20 Oct 2026 Codex has no --dangerously-skip-permissions. Use --dangerously-bypass-approvals-and-sandbox, or -a never with a sandbox. Plus approval\_policy, sandbox\_mode and --approve-for-me. - codex - coding-agents - agent-security ### [GA4 consent mode: the sessions your banner hides, measured against Search Console clicks](https://getagenttools.com/blog/ga4-consent-mode/) 17 Oct 2026 GA4 consent mode explained: basic vs advanced, what each sends before the click, and a store where Search Console counted clicks on days GA4 counted nothing. - measurement - ad-platforms - field-notes [Read all posts](https://getagenttools.com/blog/) FOR TEAMS ## Your team ships its first agent workflow. One workshop. No slides about the future of AI. We take one real process from your operations and automate it with the stack from this list. - A working agent workflow on your own process - Stack decisions made, with reasons written down - A playbook your team keeps and extends #### Introhalf day · remote Agent basics plus the stack. Your team leaves knowing what to build first. #### Hands-on2 days · remote We build a working workflow on your real process. You keep it. #### Customscoped Bigger rollout or a specific stack. Tell me the problem first. CLIENTS ## Clients worldwide Teams we trained and agents we shipped, by location. 9 clients · 8 countries · 5 continents ABOUT ## Who runs this `~/operator $ whoami` Marek. Eight years in performance marketing and automation ops. I run AI agents on real business workflows every day. This site is the list I wish I had when I started. NEWSLETTER ## The Agent Stack New tested tools and what broke this week. One email, Friday. By subscribing you agree to the [Privacy Policy](https://getagenttools.com/privacy/). Unsubscribe anytime. No tool ever pays to appear here.