# GetAgentTools

> A curated short list of AI agent tools, tested in real production workflows. Verdicts come from daily use (RUNNING / TESTED / WATCHING), not scraped directories. Also offers hands-on AI training for teams. EN / global. Independent, no sponsored placements.

## Pages

- [Home](https://getagenttools.com/index.md): The short list of AI agent tools that actually work, with verdicts from daily use and a team training offer.
- [Tools](https://getagenttools.com/tools/index.md): The full list of AI agent tools in daily rotation, each with a verdict and a link to its review where one exists.
- [Best AI SEO Tools: My Production Agent Stack](https://getagenttools.com/tools/best-ai-seo-tools/index.md): The best AI SEO tools in my production stack: Claude Code, Ahrefs, Search Console, Playwright and a custom agent, tested in a real client workflow end to end.
- [Claude Code Review: A Running Verdict](https://getagenttools.com/tools/claude-code/index.md): A Claude Code review from an operator who runs it daily in real repos: what it does, pricing, MCP support, and who should skip it. Zero sponsored fluff.
- [Figma MCP Review: Design Context Agents Can Read](https://getagenttools.com/tools/figma-mcp/index.md): Figma MCP from real design-to-code work: what the server hands an agent, why node ids beat screenshots for building, and where visual QA still needs eyes.
- [Google Ads API Review: 7 Things the Docs Skip](https://getagenttools.com/tools/google-ads-api/index.md): Google Ads API review from real use: developer token approval, manager account identity, GAQL reporting, shared budgets that move more than you think. Verdict: RUNNING.
- [Google Search Console API and Search Analytics API: An Operator Review](https://getagenttools.com/tools/google-search-console-api/index.md): The Google Search Console API is free. Its searchanalytics.query method returns clicks, impressions, CTR and position by query and page. Request shape, setup, quotas.
- [Google Sheets API: The Human-Agent Interface](https://getagenttools.com/tools/google-sheets-api/index.md): The Sheets API from daily agent use: append-only writes, dedup keys that make reruns safe, headers over positions, and why a sheet beats a dashboard.
- [Make.com Review: No-Code Glue That Keeps Running](https://getagenttools.com/tools/make/index.md): An operator review of Make.com: how credits are billed, what Make AI Agents actually do, when no-code beats a script, and when n8n is the better pick.
- [Best MCP Servers for AI Agents: Review](https://getagenttools.com/tools/mcp-servers/index.md): What are MCP servers, and which are best for AI agents? An operator review of the open protocol that wires agents into your tools. Zero sponsored picks.
- [Meta Ads API Review: 10 Traps the Docs Skip](https://getagenttools.com/tools/meta-ads-api/index.md): Meta Ads API review from daily use: immutable creatives, learning phase resets, reporting fields that change the answer, and silent token failures. Verdict: RUNNING.
- [n8n Review: Visual AI Workflows You Can Self-Host](https://getagenttools.com/tools/n8n/index.md): Is n8n worth it for AI agents? An operator review: what the AI Agent node does, how executions are billed, when self-hosting pays off, and when to pick Make instead.
- [Playwright Review: Browser Automation Agents Can Actually Rely On](https://getagenttools.com/tools/playwright/index.md): Playwright is free and open source (Apache 2.0, by Microsoft). A review for AI agents: waits, traces, logins, the Selenium comparison, and real costs.
- [Telegram Bot API Review: An Agent Output Channel](https://getagenttools.com/tools/telegram-bot-api/index.md): The Telegram Bot API as an agent's output channel: daily reports that get read, alerts that reach a human, rate limits, message splitting and the send rules.

## Writing

- [Blog](https://getagenttools.com/blog/index.md): Field notes from running AI agents on real business workflows.
- [RSS feed](https://getagenttools.com/blog/feed.xml): Published posts as RSS 2.0.
- [opencode --dangerously-skip-permissions: a hidden alias for --auto, and what deny rules still stop](https://getagenttools.com/blog/opencode-dangerously-skip-permissions/index.md): 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.
- [Codex dangerously skip permissions: --dangerously-bypass-approvals-and-sandbox and the safer pair](https://getagenttools.com/blog/codex-dangerously-skip-permissions/index.md): 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.
- [GA4 consent mode: the sessions your banner hides, measured against Search Console clicks](https://getagenttools.com/blog/ga4-consent-mode/index.md): 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.
- [RAG vs Fine Tuning: Choose by Facts, Behavior and Evaluation](https://getagenttools.com/blog/rag-vs-fine-tuning/index.md): Choose RAG or fine-tuning by the failure you need to fix: missing facts, inconsistent behavior, or both. Includes a decision worksheet and a local retrieval fixture.
- [n8n error handling: catch failures without repeating the action](https://getagenttools.com/blog/n8n-error-handling/index.md): Use n8n error workflows, node error outputs and bounded retries. A local receipt model shows why a timeout can repeat an action that already succeeded.
- [Claude Code Sandbox: Check File and Network Boundaries Before a Run](https://getagenttools.com/blog/claude-code-sandbox/index.md): Configure the Claude Code sandbox, probe file and network restrictions, and check retries, excluded commands and tools that run outside its boundary.
- [Claude Code Channels: Incoming Events, Access and Session Limits](https://getagenttools.com/blog/claude-code-channels/index.md): Understand Claude Code Channels, sender allowlists, session lifetime and permission relay. Use a local test plan before connecting an external chat platform.
- [AI Agent Cost: Measure Cost per Successfully Completed Task](https://getagenttools.com/blog/ai-agent-cost/index.md): Calculate AI agent cost with tokens, tools, retries, failed tasks and operator time. A synthetic ledger shows what cost per successful task includes.
- [Claude Code Checkpoints: Rewind Edits and Check Recovery Limits](https://getagenttools.com/blog/claude-code-checkpoints/index.md): Choose code, conversation or both in Claude Code rewind, check shell and subagent limits, and keep Git and external recovery separate from checkpoints.
- [Claude Code Worktrees: Isolate Parallel Changes and Merge Them](https://getagenttools.com/blog/claude-code-worktrees/index.md): Use Claude Code worktrees for parallel tasks, choose the right base, handle dependencies, review each branch, merge changes and clean up safely.
- [Claude Code Plugins: Install, Inspect, Update and Remove One Cleanly](https://getagenttools.com/blog/claude-code-plugins/index.md): Choose a Claude Code plugin scope, inspect its components and context cost, diagnose loading, then update, disable or remove the correct installation.
- [Codex Skills: Build a Reusable Workflow and Check It Loads](https://getagenttools.com/blog/codex-skills/index.md): Build a small Codex skill with SKILL.md, choose its local scope, check discovery, and test explicit invocation without assuming tool access.
- [GPT-6.1 Sol arrives: dots, Codex plans and what the limits mean](https://getagenttools.com/blog/gpt-6-1-sol-dots-codex-plans/index.md): GPT-6.1 Sol is here. Check dots access, ChatGPT Pro prices, Codex usage limits and the difference between faster modes and billing multipliers.
- [Claude Sonnet 5.5: the same token prices, a different migration checklist](https://getagenttools.com/blog/claude-sonnet-5-5/index.md): Claude Sonnet 5.5 keeps Sonnet 5 token prices. Check speed claims, API changes, and progress updates your agent interface could stop showing after migration.
- [Own your intelligence: an honest scorecard for my AI agent stack](https://getagenttools.com/blog/own-your-intelligence/index.md): Harrison Chase's own-your-intelligence framework, checked question by question against my own AI agent stack, with honest yes, no, and partial answers.
- [Let AI agents review your code, but never let them merge in the dark](https://getagenttools.com/blog/ai-code-review-agents/index.md): How to use AI agents for code review without losing control: specialized reviewer agents, a CI loop, fail-closed auto-merge gates, and verifying real behavior.
- [Prompt caching, explained by someone who actually pays the bill](https://getagenttools.com/blog/prompt-caching-explained/index.md): How prompt caching actually works under the hood, what is worth caching, when it does nothing for your bill, and the one-line check I run before turning it on.
- [The four types of technical debt in AI systems, and how to audit them](https://getagenttools.com/blog/ai-technical-debt/index.md): AI technical debt breaks into four types: data, model, prompt, and organizational. Here's what each looks like in practice, plus a self-audit checklist.
- [Opus 5.5, GPT-6 Sol and Luna: what launched and what changes for agents](https://getagenttools.com/blog/opus-5-5-gpt-6-sol-luna/index.md): Opus 5.5, GPT-6 Sol and Luna launched September 22, 2026. Compare API IDs, token prices, Work and Codex availability, and migration checks for agent builders.
- [Smart zone / dumb zone: where the useful part of your agent's context window ends](https://getagenttools.com/blog/smart-zone-dumb-zone/index.md): Context rot explained: why a large context window does not stop an agent from getting worse mid-session, plus how to spot the dumb zone and four ways out.
- [Your AGENTS.md is a router, not the whole project documentation](https://getagenttools.com/blog/agents-md-is-not-your-documentation/index.md): AGENTS.md and CLAUDE.md files bloat when every fix gets appended to them. A router-first structure, plus what OpenWiki automates, keeps the entry file small.
- [Google Merchant Center feed: seven things a 550,000-item feed had wrong before the first ad](https://getagenttools.com/blog/google-merchant-center-feed/index.md): Google Merchant Center feed audit: what a 548,575-item feed had wrong (empty MPN, constant availability, missing images) and which fixes actually moved.
- [claude --resume: what a resumed session restores, what it drops, and what my cheat sheet got wrong](https://getagenttools.com/blog/claude-resume/index.md): claude --resume from the Claude Code docs: when to resume, when to /clear, what a resumed session restores and what it drops, from 215 transcripts on disk.
- [--dangerously-skip-permissions: what it skips, what still stops Claude, and the dead allowlist](https://getagenttools.com/blog/dangerously-skip-permissions/index.md): --dangerously-skip-permissions: what it skips, what deny rules and hooks still block, and the matching switch in Codex, opencode, Cursor, Copilot and Gemini CLI.
- [claude -p: the flag that turns Claude Code into a build step, and what it costs](https://getagenttools.com/blog/claude-p-headless/index.md): claude -p runs Claude Code with no terminal: prompt in, result out, JSON with cost and session ID. The flags my automations use and what --bare changes.
- [What is an agent harness? The code around the model that decides what actually runs](https://getagenttools.com/blog/what-is-an-agent-harness/index.md): What is an agent harness: every piece of code around the model, the loop, the tools, the approvals and the log. Examples, harness vs agent, and the one I run.
- [Claude Code context window: what fills it before you type, and the 33 edits I wasted in July](https://getagenttools.com/blog/claude-code-context-window/index.md): Claude Code context window explained from the docs: what loads at startup, what /context shows, when auto-compaction runs, what survives, and the rules I keep.
- [What is function calling? The structured request a model returns instead of running code](https://getagenttools.com/blog/what-is-function-calling/index.md): What is function calling: the model picks a tool and writes the arguments, your code runs it and sends the result back. The loop, the cost, and MCP.
- [Claude Code memory: what 538 auto memory files taught me about the 200-line index](https://getagenttools.com/blog/claude-code-memory/index.md): Claude Code memory has two parts: CLAUDE.md you write and auto memory Claude writes. Where each lives, the 200-line and 25 KB limits, and my 538 memory files.
- [What is a system prompt? The instructions loaded before you type](https://getagenttools.com/blog/what-is-a-system-prompt/index.md): What is a system prompt: the instructions an application loads before your message, what they can and cannot enforce, and how Claude Code builds its own.
- [Claude Code subagents: two files, 125 dispatches, and the work that never touched my context](https://getagenttools.com/blog/claude-code-subagents/index.md): Claude Code subagents run a task in their own context window and return a summary. What the docs guarantee, the two agent files I run, and one leaked .env file.
- [What are AI guardrails? The controls that hold when the model has a bad day](https://getagenttools.com/blog/what-are-ai-guardrails/index.md): What AI guardrails are in operator terms: input filters, output checks and action gates, why the third one is the one agents need, and the three layers I run.
- [claude --chrome: field notes on letting Claude Code drive my own browser, and where it breaks](https://getagenttools.com/blog/claude-chrome/index.md): Field notes on claude --chrome, the flag that hands Claude Code your logged-in browser: 27 screenshot timeouts, clicks that miss, and the gates I use.
- [ChatGPT Ads: the platform is real, the measurement is what I would test first](https://getagenttools.com/blog/chatgpt-ads/index.md): ChatGPT Ads: a US test in February, self-serve in 52 countries by September. What Ads Manager Beta gives you: bids, context hints, Pixel and Conversions API.
- [What is RAG in AI? The lookup step that runs before the model answers](https://getagenttools.com/blog/what-is-rag/index.md): What is RAG in AI, in plain terms: fetch relevant text from a source you chose, put it in the prompt, then generate. How it works, RAG vs MCP, where it fails.
- [PreToolUse: the hook that reads every command before my agent runs it](https://getagenttools.com/blog/pretooluse-hook/index.md): Before a tool call runs, a PreToolUse hook in Claude Code can deny it or ask me. My 79-line production guardrail, the ssh case rules miss, and its limits.
- [What is an AI agent? A model, tools, a loop and a human at the gate](https://getagenttools.com/blog/what-is-an-ai-agent/index.md): A plain definition of what an AI agent is: a language model that picks tools inside a loop, with a stop condition and a human on the gates that matter.
- [statusLine: the Claude Code status line I rebuilt after a 13-second render](https://getagenttools.com/blog/statusline-claude-code/index.md): The statusLine setting runs a script on every update. My claude code statusline reads only stdin: median 41 ms, replacing a tool that took 13-20 s a render.
- [AI agent architecture diagram: the six layers I actually run](https://getagenttools.com/blog/ai-agent-architecture-diagram/index.md): A practical AI agent architecture diagram with six layers for goals, orchestration, context, models, tools, policy, and production observability in practice.
- [LLM evaluation: the small test stack I trust before production](https://getagenttools.com/blog/llm-evaluation/index.md): A practical LLM evaluation method using representative test cases, deterministic checks, human review, calibrated model judges, and release gates that work.
- [7 AI agent examples that actually do work](https://getagenttools.com/blog/ai-agent-examples/index.md): Seven practical AI agent examples with their inputs, tools, stop conditions, human approval gates, and the failures each design must handle in production.
- [What is a prompt? The instruction you give an AI model](https://getagenttools.com/blog/what-is-a-prompt-in-ai/index.md): A plain explanation of AI prompts, their main parts, prompt roles, practical examples, common mistakes, and how to test whether a prompt works in practice.
- [MCP server security: the trust boundaries I check first](https://getagenttools.com/blog/mcp-server-security/index.md): A practical MCP server security checklist covering trust boundaries, credentials, token handling, approvals, sessions, sandboxing, and logs for AI agents.
- [What is a context window in AI? The limit that changes agent behavior](https://getagenttools.com/blog/what-is-an-ai-context-window/index.md): What is a context window in AI? Learn what fits inside it, how it differs from memory, why long context still fails, and how agents manage it in practice.
- [AI agent deployment: the release path I use before production](https://getagenttools.com/blog/ai-agent-deployment/index.md): AI agent deployment needs more than a working prompt. Use this practical path through sandbox, staging, canary release, monitoring, rollback, and approval.
- [What is an AI hallucination? Why models make things up, and what actually helps](https://getagenttools.com/blog/what-is-ai-hallucination/index.md): What is an AI hallucination: a fluent, confident output that is not true. Why next-token prediction makes them inevitable, and which defenses work.
- [The AI time dividend should go to tests, not more features. Mine did not, at first](https://getagenttools.com/blog/ai-time-dividend-tests/index.md): Agents write code many times faster. Robert C. Martin says spend the saved time on testing rigor. Field notes on what that looks like when you actually do it.
- [What is a token in AI? The unit your whole bill is written in](https://getagenttools.com/blog/what-is-a-token/index.md): What is a token in AI: the chunk a model reads and writes text in. Roughly three-quarters of a word, and the unit behind every context limit and every invoice.
- [AI agent monitoring in production: traces, cheap judges, and the loop that compounds](https://getagenttools.com/blog/ai-agent-monitoring/index.md): AI agent monitoring is not server monitoring. Field notes from running a 36-probe cockpit over an agent fleet: traces, review queues, judges, decision stamps.
- [Slack Code: multiplayer coding also means a multiplayer prompt](https://getagenttools.com/blog/slack-code-channels/index.md): Slack Code gives coding agents their own channels with diffs, previews and a self-archiving log. What it changes for permissions, prompts and who can build.
- [What is an LLM? The engine under every AI agent, minus the mysticism](https://getagenttools.com/blog/what-is-an-llm/index.md): What is an LLM: a model trained on text to predict the next token, and the engine under chatbots and agents. How it works in practice and what people get wrong.
- [disable-model-invocation: the flag that keeps my deploy skills out of Claude's hands](https://getagenttools.com/blog/disable-model-invocation/index.md): One frontmatter line decides if Claude can run a skill on its own. disable-model-invocation on 55 real skills, 0 flagged then 8, plus Copilot, Cursor, Codex.
- [What is AI? A plain answer for people who have to buy, use or approve it](https://getagenttools.com/blog/what-is-ai/index.md): What is AI, in plain language: software that handles judgment calls, learned from data instead of programmed. What the term covers, and the myths around it.
- [I audited my CLAUDE.md against Anthropic's new context engineering rules](https://getagenttools.com/blog/claude-md-audit/index.md): Anthropic cut over 80% of Claude Code's system prompt. The new CLAUDE.md best practices, tested against a real 482-line config and its 26 loudest rules.
- [Production-ready AI agents: the 12 gates to pass before real access](https://getagenttools.com/blog/production-ready-ai-agents/index.md): A production-readiness checklist for AI agents: 12 gates across access, actions, failure and operations, each with a failure mode and a pass or stop test.
- [DeepSeek Harness: everything is a plugin, except the parts that are not](https://getagenttools.com/blog/deepseek-harness/index.md): DeepSeek Harness ships under MIT with every capability as a plugin. What the docs let you swap, what they will not, and the tools left switched off.
- [Writing your own MCP server: the code is the easy part, the tool descriptions are not](https://getagenttools.com/blog/build-your-own-mcp-server/index.md): When an MCP server integration is worth writing yourself, what it takes, and why tool descriptions cost more thought than code. Notes from two servers I run.
- [Remote MCP servers: what changes when the server is not yours](https://getagenttools.com/blog/remote-mcp-servers/index.md): Hosted and public MCP servers move the credential, the failure mode and the trust boundary off your machine. What I run, what broke today, what I check first.
- [An MCP server for your database: what breaks when the agent gets the schema](https://getagenttools.com/blog/mcp-server-database/index.md): An MCP server for your database gives an agent live SQL in minutes. Field notes on schema cost, read-only roles, and why my write path never goes through MCP.
- [Choosing an MCP server for AI agents: the criteria change when nobody is watching](https://getagenttools.com/blog/mcp-server-for-ai-agents/index.md): An MCP server for AI agents is judged differently than one for chat: tool count, description quality, error text, blast radius, and the check I run first.
- [An MCP servers list worth keeping: the eight I leave connected, and what gets removed](https://getagenttools.com/blog/mcp-servers-list/index.md): An MCP servers list is only useful if it is short. The eight I keep connected, what earns a place, what gets one removed, and why directories do not help.
- [What is an MCP server in AI, and where does your data actually go?](https://getagenttools.com/blog/what-is-an-mcp-server-in-ai/index.md): What is an MCP server in AI: host, client and server explained, both transports, and a plain answer to where your data ends up when an agent calls a tool.
- [Agent harness design: what Meta put in Muse Code, and what I already run](https://getagenttools.com/blog/muse-code-agent-harness/index.md): Agent harness design notes on Meta's Muse Code launch: an append-only event log, background agents that outlive the task, and an approval gate as a skill.
- [Field notes, not a directory](https://getagenttools.com/blog/field-notes/index.md): Why this blog only covers agent tools that carry real production work, and how the verdicts get decided.

## Legal

- [Privacy Policy](https://getagenttools.com/privacy/index.md): What data the site collects, the legal basis, processors used, and your GDPR rights.

## Notes

- Verdicts are opinions from real daily use, never paid placements.
- Contact: human@getagenttools.com