relayshield_agentic_attack_surface_check_llm_credential_exposure – 1 MCP server offers this tool
What it usually takes
api_key– in 1 of 1domain– in 1 of 1
No server marks it as only reading: treat it as able to change data.
From each publisher's own tool list. We never call a tool.
Servers
| Server | Inputs | Read-only? |
|---|---|---|
RelayShield Agentic Attack Surface co.huggingface.relayshieldadmin/relayshield-agentic-attack-surface Check a domain for exposed LLM/AI provider API keys (OpenAI, Anthropic, Google, Groq, xAI, Replicate) in criminal stealer logs -- LLMjacking, a fast-growing threat where a leaked key becomes a live, uncapped billing liability rather than just a data exposure. Real incidents have run from tens of thousands of dollars per day to a $500K single-month bill from one leaked, unthrottled key. Returns: A structured result: outcome/recommended_action plus evidence and reason codes. | api_key,domain | Not stated |