High-risk tools in Cross-LLM MCP Server
12 of the 23 tools in Cross-LLM MCP Server are classified as high risk. This page profiles those tools specifically, with recommended policy actions and the attack patterns that target them.
Every operation listed below is an action PolicyLayer recommends controlling at the transport layer. Open any tool to see the full profile, risk score, and YAML policy snippet.
Tools at high risk
-
call-all-llmsExecuteCall all available LLM APIs (ChatGPT, Claude, DeepSeek, Gemini, Grok, Kimi, Perplexity, Mistral, Hugging Face) with the same prompt and get combined responses
-
call-chatgptExecuteCall OpenAI
-
call-claudeExecuteCall Anthropic
-
call-deepseekExecuteCall DeepSeek API with a prompt
-
call-geminiExecuteCall Google
-
call-grokExecuteCall xAI
-
call-huggingfaceExecuteCall Hugging Face Inference Router (OpenAI-compatible chat completions) with a prompt
-
call-kimiExecuteCall Moonshot AI
-
call-llmExecuteCall a specific LLM provider by name
-
call-mistralExecuteCall Mistral AI
-
call-perplexityExecuteCall Perplexity AI
-
submit-llm-request-asyncExecuteSubmit an LLM request to be processed asynchronously. Returns a job ID immediately that can be used to poll for results later.
Attacks that target this class
High-risk tools in any server share these documented attack patterns. Each links to the full case and the defensive policy.