The real catalog of tools for AI agents

Scans untrusted web pages, emails, MCP responses, or A2A payloads for hidden prompt injections an.

Detect prompt injection, jailbreak, and social-engineering attacks in LLM agents.

Multi-agent LLM security layer detecting prompt injection and jailbreaks.

Prompt-injection firewall for AI agents — scan untrusted text before LLM calls.

Prunes 85% of HTML/DOM/JSON token bloat into semantic Markdown for LLM agents via x402 & MPP on agentdiet.dev.

Security gateway for AI agents: detects prompt injections, jailbreaks, and common vulnerabilities.

Scans RAG content/scraped pages for indirect prompt injection

Detect prompt injection, jailbreaks, and code injection in untrusted text before it reaches an LLM.

Classifies prompt injection, jailbreaks, and out-of-scope user input before agents act on it.

Single-connection meta-router indexing 500+ MCP servers & A2A tools with 85% token compression an.

Scans RAG content/scraped pages for indirect prompt injection

A2A TrustGate: 4-gate firewall that screens every AI-agent action before it runs. 50 tools.

Input/output safety for AI agents: known-pattern injection and obfuscation scan, URL/IP, secrets.

A real inbox for AI agents: send, receive and thread email, behind a prompt-injection firewall.

Executes live Google News RSS + HackerNews Algolia search queries and returns clean, token-pruned.

Decision-only prompt routing and firewall checks for local/cloud routing, PII and jailbreak risk.

Strips 85-97% of HTML/DOM bloat into clean Markdown or JSON with cryptographic ROI proof.

Scan a page for hidden prompt-injection payloads targeting AI agents.

Audits A2A Agent Cards, MCP manifests, and live x402/MPP payment quotes before autonomous spend on assay.agentdiet.dev.

Validates email syntax, disposable/burner provider status, role accounts, and live DNS MX/SPF/DMA.