# Quantcalc Retirement Engine MCP server

Source: https://glimind.com/server/mcp-registry%2Fapp.quantcalc%2Fretirement-engine
Registry id: `mcp-registry/app.quantcalc/retirement-engine`
Status: live (checked 2026-10-26T22:31:58.445Z)

## Measurements (30 days)

- Uptime: 99.96%
- Checks: 5019
- Outages (90 days): 3

## Install

```json
{
  "mcpServers": {
    "quantcalc-retirement-engine-mcp-server": {
      "type": "http",
      "url": "https://mcp.quantcalc.app"
    }
  }
}
```

Claude Code:

```sh
claude mcp add --transport http quantcalc-retirement-engine-mcp-server https://mcp.quantcalc.app
```

## Tools (7)

- `compare_return_assumptions`: Runs the same plan against several published capital market assumption sets and returns the success rate and median outcome under each, showing how far the answ
- `estimate_2026_tax_return`: Estimates a household's 2026 federal and state income tax return from its 2026 income (wages, Social Security, IRA and 401(k) distributions, pensions, Roth conv
- `explain_methodology`: Returns what the QuantCalc engine models and what it deliberately leaves out, including the tax provisions that are out of scope, and links to the published met
- `list_return_assumption_sources`: Returns the published capital market assumption sets the engine carries and which components each publisher provides (returns, volatilities, correlations).
- `optimize_social_security_claiming`: Searches every Social Security claiming age from 62 (or today's age) to 70 for the household's tax-aware plan: each age's benefit is the given benefit restated 
- `run_retirement_projection`: Runs a Monte Carlo retirement projection on the QuantCalc engine and returns the success rate, the ending-portfolio distribution, and the assumptions that produ
- `run_tax_aware_projection`: Runs the retirement projection with the household's accounts split by tax type and returns the withdrawal order and Roth-conversion programme the engine selecte

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.