splitifi_predict_criminal
Predict Criminal Defense case outcome using ML models trained on 3.52B+ court records. Provide jurisdiction and case_facts (charge_type, charge_severity, prior_record, evidence_strength, plea_offer).
This record as markdown: /tools/io-github-mysplitifi-splitifi-mcp/splitifi-predict-criminal.md
What splitifi_predict_criminal does on Splitifi Intelligence MCP
AI agents call splitifi_predict_criminal to retrieve information from Splitifi Intelligence MCP without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
judge_id | string | — | Optional — judge ID for judge-specific modifier |
case_facts | object | Yes | Case details for Criminal Defense. Key fields: charge_type, charge_severity, prior_record, evidence_strength, plea_offer |
jurisdiction | string | Yes | State/province/country code, e.g. "TX", "CA", "ON" |
Parameters from the server's own tool schema.
Why splitifi_predict_criminal is rated Low
While this tool accesses sensitive criminal justice data and predictions that could influence consequential legal decisions, it is fundamentally a read operation—it queries ML models and returns predictions without creating, modifying, deleting, or irreversibly changing any data.
From the tool's definition Tool performs prediction queries: 'Predict Criminal Defense case outcome using ML models trained on 3.52B+ court records.' It retrieves outcome predictions based on input case facts (charge_type, charge_severity, prior_record, evidence_strength, plea_offer)…
Attacks that exploit this kind of access
The rule that runs splitifi_predict_criminal safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Splitifi Intelligence MCP, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For splitifi_predict_criminal, this is the rule to start with:
splitifi_predict_criminal is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Splitifi Intelligence MCP, apply this rule, and every splitifi_predict_criminal call is checked against it from then on.
Questions about splitifi_predict_criminal
Predict Criminal Defense case outcome using ML models trained on 3.52B+ court records. Provide jurisdiction and case_facts (charge_type, charge_severity, prior_record, evidence_strength, plea_offer). It is categorised as a Read tool in the Splitifi Intelligence MCP MCP Server, which means it retrieves data without modifying state.
splitifi_predict_criminal accepts 3 parameters: judge_id, case_facts, jurisdiction. Required: case_facts, jurisdiction. The full parameter table on this page comes from the server's own tool schema.
Register the Splitifi Intelligence MCP server in PolicyLayer and add a rule for splitifi_predict_criminal: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Splitifi Intelligence MCP. Nothing to install.
splitifi_predict_criminal is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the splitifi_predict_criminal rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for splitifi_predict_criminal. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
splitifi_predict_criminal is provided by the Splitifi Intelligence MCP server (splitifi-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Splitifi Intelligence, and thousands of servers like it.
This server
Across the catalogue