Runs the IRC §401(k)(3)(A)(ii) Actual Deferral Percentage test and the §401(m)(2) Actual Contribution Percentage test from supplied HCE vs NHCE average deferral/match percentages (current-year or prior-year method, as supplied), applying the fixed statutory permitted-disparity limits: 1.25× the NHCE rate, or 2 percentage points and 2× the NHCE rate, whichever is greater. Reports per-test pass/fail and the percentage-point excess if failed — a simplified excess figure, not a full leveling-method dollar correction schedule.
Copy this paragraph into Claude, OpenClaw, or any MCP-aware agent to run this exact tool, with this sample, and verify the artifact.
Run the AINumbers MCP tool `run_401k_adp_acp_test`. Task: Run the IRC §401(k)(3) ADP test and the §401(m)(2) ACP test from supplied HCE vs NHCE deferral/match percentages, applying the 1.25x / 2-and-2x permitted-disparity limits.
Call it with arguments: {"policy_parameters":{"method":"current_year","adp_hce_pct":0.06,"adp_nhce_pct":0.05,"acp_hce_pct":0.04,"acp_nhce_pct":0.035}}
Verify before trusting: call `verify_execution_hash` on mcp.ainumbers.co (https://mcp.ainumbers.co/mcp) with the parameter `claimed_hash` set to the returned `execution_hash`, passing the full artifact the run returned (the object containing `policy_parameters` + `output_payload` + `execution_hash`; equivalently `policy_parameters` + `output_payload` with `claimed_hash`), not the bare hash string.
Return the ledger link https://ledger.ainumbers.co/ so a human can re-verify without contacting us.
PII rule: All inputs are processed locally in your browser. No data is transmitted. Do not enter real personal data — use synthetic or anonymised inputs only.
Open the tool with the sample prefilled: https://ainumbers.co/chaingraph/art-302-401k-adp-acp-test.html#p=v1.H4sIAAAAAAAA_wFoAJf_eyJtZXRob2QiOiJjdXJyZW50X3llYXIiLCJhZHBfaGNlX3BjdCI6MC4wNiwiYWRwX25oY2VfcGN0IjowLjA1LCJhY3BfaGNlX3BjdCI6MC4wNCwiYWNwX25oY2VfcGN0IjowLjAzNX0K27DVaAAAAA