Tools We Don't Recommend
We review hundreds of Claude AI tools. Most make the catalog. Some don't. This page explains why specific tools were excluded — so you can make informed decisions if you encounter them elsewhere.
This is not a complete list of every rejected tool. It covers tools that are popular enough that you might encounter them, where the reasoning would save you time or protect you from risk.
Security Holds
These tools were flagged during review for security concerns that make them unsuitable for recommendation.
FreeRide
FreeRide gives you unlimited free AI in OpenClaw by automatically managing OpenRouter's free models.
Designed to circumvent service rate limits, which violates most providers' Terms of Service. Using this could get your accounts suspended. The approach is inherently adversarial to the platforms it targets.
View source
agent-tool
MCP tool server for AI coding agents -- encoding-aware file tools, binary analysis, DAP debugger, SSH/SFTP, process memory, and more
Grants AI access to SSH connections, remote servers, and process memory — the broadest possible attack surface. No sandboxing. A compromised prompt could read private keys, access production servers, or inspect running processes.
View source
real-browser-mcp
MCP server + Chrome extension that gives AI agents control of your real browser with existing sessions and logins
Gives AI full access to your authenticated browser sessions. Saved passwords, cookies, and active logins are all exposed. One wrong prompt could send emails, make purchases, or access sensitive accounts on your behalf.
View source
t2000
A bank account for AI agents. DeFi banking via MCP — save, borrow, invest, exchange, send. Non-custodial on Sui.
Lets AI execute financial transactions on a blockchain. Non-custodial doesn't mean safe — a misunderstood prompt could move real money. Financial operations should never be delegated to AI without human-in-the-loop controls.
View source
Not Recommended
These tools were reviewed and rejected for specific reasons beyond just being niche or incomplete.
Linkedin Mcp Server
Scrapes LinkedIn profiles, companies, and jobs via AI
Automated LinkedIn scraping violates LinkedIn's Terms of Service and can result in account termination or legal action. LinkedIn actively detects and blocks scraping. This is a compliance risk, not just a technical one.
View source
Mcp Mindmesh
Quantum-inspired swarm orchestrating multiple Claude instances
Marketing language ('quantum field coherence', 'ensemble intelligence') significantly overstates what the code actually does. The implementation is a basic multi-model aggregation. Overstated claims are a red flag for any tool touching your data.
View source
Tool authors: If you believe your tool was excluded in error or have addressed the concerns listed here,
reach out on LinkedIn.
We re-evaluate tools when significant changes are made.