splitifi_next_step
Get the next recommended action in your case. Optionally mark a task as completed first. Returns next task, tool to call, and overall progress.
This record as markdown: /tools/io-github-mysplitifi-splitifi-mcp/splitifi-next-step.md
What splitifi_next_step does on Splitifi Intelligence MCP
AI agents call splitifi_next_step 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 |
|---|---|---|---|
session_token | string | Yes | Your session token from splitifi_start |
completed_task_id | string | — | ID of task just completed (optional) |
Parameters from the server's own tool schema.
Why splitifi_next_step is rated Low
This tool retrieves predictions and recommendations from a predictive model without creating permanent data changes, executing external code, moving financial assets, or destroying data. The metadata update capability (marking tasks completed) is a reversible state change typical of task management systems, not a write operation with side effects on external systems or case data.
From the tool's definition Tool description states it 'Get[s] the next recommended action' and 'Returns next task, tool to call, and overall progress.' The core function is retrieving and querying predictive information from ML models trained on court records.
Attacks that exploit this kind of access
The rule that runs splitifi_next_step 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_next_step, this is the rule to start with:
splitifi_next_step 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_next_step call is checked against it from then on.
Questions about splitifi_next_step
Get the next recommended action in your case. Optionally mark a task as completed first. Returns next task, tool to call, and overall progress. It is categorised as a Read tool in the Splitifi Intelligence MCP MCP Server, which means it retrieves data without modifying state.
splitifi_next_step accepts 2 parameters: session_token, completed_task_id. Required: session_token. 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_next_step: 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_next_step 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_next_step 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_next_step. 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_next_step 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