High-risk tools in Neuroverse
11 of the 21 tools in Neuroverse 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
-
india_mcp_model_routeExecuteindia_mcp_model_route
-
india_mcp_process_multilingual_inputExecuteindia_mcp_process_multilingual_input
-
india_mcp_route_agentExecuteindia_mcp_route_agent
-
india_mcp_safe_executeExecuteindia_mcp_safe_execute
-
india_mcp_synthesize_speechExecuteSynthesize text to speech using Coqui TTS.
-
neuroverse_executeExecuteParse, safety-check, and execute a user request end-to-end. Convenience tool that chains: Language → Intent → Safety → Execute. Args: - text (string): Raw user input - use...
-
neuroverse_modelExecuteQuery the multi-model AI router. If a prompt is provided, the prompt is sent to the routed model. Otherwise, returns only the routing decision. Supported providers: OpenAI, An...
-
neuroverse_processExecuteProcess mixed-language input through the full NeuroVerse pipeline. Pipeline: Language Detect → Normalise → Intent Extract → Safety Check → (optional) Execute Supported languag...
-
neuroverse_reasonExecuteExecute a complex reasoning task using specialized high-performance models (e.g. OpenRouter Reasoning). Returns the model
-
neuroverse_routeExecuteRoute a task to a registered downstream agent via HTTP. Args: - target_agent (string): Name of the agent - task (string): Task description - payload (object): Arbitrary p...
-
neuroverse_synthesizeExecuteSynthesize text to speech using Coqui TTS. Args: - text (string): Text to synthesize - language (string): Language code Returns: JSON with the path to the generated audi...
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.