# 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. Agent View of the PolicyLayer registry record for `splitifi_submit_outcome`. HTML page: https://policylayer.com/tools/io-github-mysplitifi-splitifi-mcp/splitifi-submit-outcome ## Facts - Tool: `splitifi_submit_outcome` - Server: Splitifi Intelligence MCP (`splitifi-mcp`) — https://policylayer.com/tools/io-github-mysplitifi-splitifi-mcp.md - Install: `npx -y splitifi-mcp` - Homepage: https://github.com/mysplitifi/Splitifi - Risk category: Write (Medium risk) - Registry record: grade F, identity unverified - Server rate-limited: no - Parameters: 3 (2 required) - Recommended policy verdict: Rate-limited ## Parameters | Parameter | Type | Required | Description | | --- | --- | --- | --- | | `case_id` | string | no | 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. ## Example call (MCP tools/call, JSON-RPC 2.0) ```json { "jsonrpc": "2.0", "id": 1, "method": "tools/call", "params": { "name": "splitifi_submit_outcome", "arguments": { "prediction_id": "", "actual_outcome": {} } } } ``` ## 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 own 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." ## Use case 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. ## Recommended policy (PolicyLayer) Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Splitifi Intelligence MCP: ```json { "version": "1", "default": "deny", "tools": { "splitifi_submit_outcome": { "limits": [ { "counter": "splitifi_submit_outcome_rate", "window": "minute", "max": 30, "scope": "grant" } ] } } } ``` ## Other tools on Splitifi Intelligence MCP (199) - `splitifi_batch` — Execute — https://policylayer.com/tools/io-github-mysplitifi-splitifi-mcp/splitifi-batch.md - `splitifi_predict_judge_empowerment` — Execute — https://policylayer.com/tools/io-github-mysplitifi-splitifi-mcp/splitifi-predict-judge-empowerment.md - `splitifi_run_calculator` — Execute — https://policylayer.com/tools/io-github-mysplitifi-splitifi-mcp/splitifi-run-calculator.md - `splitifi_start` — Execute — https://policylayer.com/tools/io-github-mysplitifi-splitifi-mcp/splitifi-start.md - `bva_screen` — Read — https://policylayer.com/tools/io-github-mysplitifi-splitifi-mcp/bva-screen.md - `eoir_judge_screen` — Read — https://policylayer.com/tools/io-github-mysplitifi-splitifi-mcp/eoir-judge-screen.md - `securities_company_screen` — Read — https://policylayer.com/tools/io-github-mysplitifi-splitifi-mcp/securities-company-screen.md - `splitifi_arbitration_screen` — Read — https://policylayer.com/tools/io-github-mysplitifi-splitifi-mcp/splitifi-arbitration-screen.md - `splitifi_arbitration_stats` — Read — https://policylayer.com/tools/io-github-mysplitifi-splitifi-mcp/splitifi-arbitration-stats.md - `splitifi_asset_classifier` — Read — https://policylayer.com/tools/io-github-mysplitifi-splitifi-mcp/splitifi-asset-classifier.md - `splitifi_asset_tracing` — Read — https://policylayer.com/tools/io-github-mysplitifi-splitifi-mcp/splitifi-asset-tracing.md - `splitifi_award_ranges` — Read — https://policylayer.com/tools/io-github-mysplitifi-splitifi-mcp/splitifi-award-ranges.md - `splitifi_billing_estimate` — Read — https://policylayer.com/tools/io-github-mysplitifi-splitifi-mcp/splitifi-billing-estimate.md - `splitifi_budget_planner` — Read — https://policylayer.com/tools/io-github-mysplitifi-splitifi-mcp/splitifi-budget-planner.md - `splitifi_calculate_child_support` — Read — https://policylayer.com/tools/io-github-mysplitifi-splitifi-mcp/splitifi-calculate-child-support.md - `splitifi_calculate_co_parenting` — Read — https://policylayer.com/tools/io-github-mysplitifi-splitifi-mcp/splitifi-calculate-co-parenting.md - `splitifi_calculate_divorce_cost` — Read — https://policylayer.com/tools/io-github-mysplitifi-splitifi-mcp/splitifi-calculate-divorce-cost.md - `splitifi_calculate_home_buyout` — Read — https://policylayer.com/tools/io-github-mysplitifi-splitifi-mcp/splitifi-calculate-home-buyout.md - `splitifi_calculate_property_division` — Read — https://policylayer.com/tools/io-github-mysplitifi-splitifi-mcp/splitifi-calculate-property-division.md - `splitifi_case_brief` — Read — https://policylayer.com/tools/io-github-mysplitifi-splitifi-mcp/splitifi-case-brief.md - `splitifi_case_strategy` — Read — https://policylayer.com/tools/io-github-mysplitifi-splitifi-mcp/splitifi-case-strategy.md - `splitifi_case_summary` — Read — https://policylayer.com/tools/io-github-mysplitifi-splitifi-mcp/splitifi-case-summary.md - `splitifi_client_intake` — Read — https://policylayer.com/tools/io-github-mysplitifi-splitifi-mcp/splitifi-client-intake.md - `splitifi_comparable_adr` — Read — https://policylayer.com/tools/io-github-mysplitifi-splitifi-mcp/splitifi-comparable-adr.md - `splitifi_comparable_antitrust` — Read — https://policylayer.com/tools/io-github-mysplitifi-splitifi-mcp/splitifi-comparable-antitrust.md - `splitifi_comparable_appellate` — Read — https://policylayer.com/tools/io-github-mysplitifi-splitifi-mcp/splitifi-comparable-appellate.md - `splitifi_comparable_bankruptcy` — Read — https://policylayer.com/tools/io-github-mysplitifi-splitifi-mcp/splitifi-comparable-bankruptcy.md - `splitifi_comparable_cases` — Read — https://policylayer.com/tools/io-github-mysplitifi-splitifi-mcp/splitifi-comparable-cases.md - `splitifi_comparable_civil_rights` — Read — https://policylayer.com/tools/io-github-mysplitifi-splitifi-mcp/splitifi-comparable-civil-rights.md - `splitifi_comparable_class_action` — Read — https://policylayer.com/tools/io-github-mysplitifi-splitifi-mcp/splitifi-comparable-class-action.md - …and 169 more: https://policylayer.com/tools/io-github-mysplitifi-splitifi-mcp.md ## For agents This record is a snapshot. Live verdicts and the full registry: - Check every server in your MCP config at once: `npx -y policylayer stack` - Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md) - Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events` --- Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=io-github-mysplitifi-splitifi-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/io-github-mysplitifi-splitifi-mcp