High-risk tools in Splitifi Intelligence MCP
4 of the 200 tools in Splitifi Intelligence MCP 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
-
splitifi_batchExecuteRun up to 50 Splitifi intelligence calls in a single request. Ideal for building case dashboards or running multiple analyses at once. Each request specifies a tool name and par...
-
splitifi_predict_judge_empowermentExecuteRun a Pillars 11–20 judicial empowerment NLP model for a specific judge. These 160 LLM-powered models assess judicial decision style, empowerment patterns, ruling clarity, cogni...
-
splitifi_run_calculatorExecuteRun any Splitifi calculator by its ID with provided inputs. Get available calculator IDs from splitifi_list_calculators first.
-
splitifi_startExecuteStart a guided Splitifi session. Declare your role (litigant, attorney, judge, mediator, paralegal, cdfa, forensic, gal, therapist), jurisdiction, and situation. Returns a perso...
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.