splitifi_submit_outcome

Submit the actual outcome of a case after a Splitifi prediction was made. This improves model accuracy over time. Optional but strongly encouraged.

SERVERSplitifi Intelligence MCP SOURCEsplitifi-mcp

Medium RISK CLASS

Category Write

Parameters 32 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-github-mysplitifi-splitifi-mcp/splitifi-submit-outcome.md

WHAT IT DOES

What splitifi_submit_outcome does on Splitifi Intelligence MCP

AI agents use splitifi_submit_outcome to create or update resources in Splitifi Intelligence MCP, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Splitifi Intelligence MCP environment.

Parameter	Type	Required	Description
`case_id`	string	—	Optional case ID for your own reference
`prediction_id`	string	Yes	The prediction ID returned by splitifi_predict_* tools
`actual_outcome`	object	Yes	What actually happened: custody_type, support_amount, asset_split_pct, case_duration_days, etc.

Parameters from the server's own tool schema.

RISK

Why splitifi_submit_outcome is rated Medium

This tool creates or appends case outcome records to a database, which is a reversible write operation. It does not delete data (so not Destructive), does not execute arbitrary code (Execute), does not move money (Financial), and does not merely retrieve data (Read).

From the tool's definition Tool name 'splitifi_submit_outcome' and description 'Submit the actual outcome of a case' indicate creation/modification of outcome records. The phrase 'improves model accuracy over time' shows this data feeds back into ML systems and persists.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs splitifi_submit_outcome 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_submit_outcome, this is the rule to start with:

splitifi_submit_outcome Rate-limited

splitifi_submit_outcome stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "splitifi_submit_outcome": {
      "limits": [
        {
          "counter": "splitifi_submit_outcome_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Splitifi Intelligence MCP, apply this rule, and every splitifi_submit_outcome call is checked against it from then on.

FAQ

Questions about splitifi_submit_outcome

What does the splitifi_submit_outcome tool do? +

Submit the actual outcome of a case after a Splitifi prediction was made. This improves model accuracy over time. Optional but strongly encouraged. It is categorised as a Write tool in the Splitifi Intelligence MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

What parameters does splitifi_submit_outcome accept? +

splitifi_submit_outcome accepts 3 parameters: case_id, prediction_id, actual_outcome. Required: prediction_id, actual_outcome. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on splitifi_submit_outcome? +

Register the Splitifi Intelligence MCP server in PolicyLayer and add a rule for splitifi_submit_outcome: 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.

What risk level is splitifi_submit_outcome? +

splitifi_submit_outcome is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit splitifi_submit_outcome? +

Yes. Add a rate_limit block to the splitifi_submit_outcome 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.

How do I block splitifi_submit_outcome completely? +

Set action: deny in the PolicyLayer policy for splitifi_submit_outcome. 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.

What MCP server provides splitifi_submit_outcome? +

splitifi_submit_outcome 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.

KEEP EXPLORING

More on Splitifi Intelligence, and thousands of servers like it.

This server

All 200 Splitifi Intelligence tools →

Across the catalogue

The MCP Attack Database →

Guides

Govern customer-ops agents →Argument validation →Scoped token →