YUSA
MCP serverPrompt-injection scanner and tool-call gate for AI agents, run locally over stdio
Runs locally- 3 tools
- Open source
- Security
Prompt-injection scanner and tool-call gate for AI agents, run locally over stdio
Runs locally
Scan prompts, tool definitions and model output for injection, and guard tool calls
Runs locallyCheck the key factual claims in AI output against live web sources
Not checked yetAsk an action firewall for an allow, review or block verdict before an agent acts
Not checked yetRed-team chatbots, RAG apps and agents with 41 OWASP LLM Top 10 probes
Runs locallyGuard that holds risky MCP tool calls for human approval and signs the decisions
Not checked yetStep-order enforcement for AI agents: ALLOW or DENY each step, with signed receipts
Not checked yetScreen untrusted text for prompt injection and jailbreaks before it reaches your LLM
Not checked yetDeterministic policy rules that gate AI agent tool calls before they run
Not checked yetRun 124 security checks on AI agents and MCP configs from your coding assistant
Runs locallyReview and block risky AI agent actions, installs and MCP calls on your machine
Runs locallyCheck factual claims in AI answers against public sources, paid per call in USDC
Remote MCP package of 12 pre- and post-execution security checks for autonomous agents
Not checked yetHosted MCP check that reviews an agent's planned purchase, booking or message first
Not checked yetThe closest alternatives to HallucC — Hallucination & Safety Guardian are YUSA, prompt-protection, Faultline, Verdict L402 and LLM Assure.
Yes. YUSA, prompt-protection, Faultline have a free or open-source option.