Retirement Lab connector

Use Retirement Lab in ChatGPT

Open the Retirement Lab plugin listing, install the plugin, and connect your Retirement Lab account when prompted. Sign in and approve access in the browser, then ask ChatGPT to run a hypothetical simulation based on your inputs. ChatGPT setup uses the published plugin.

1. Open the plugin listing and select Install plugin.
2. Connect Retirement Lab and approve access to your account.
3. Start a chat with @Retirement Lab and describe your assumptions.

Anonymous MCP access is not available. Calls use the connected user’s account tier and current calculator quotas.

Connect Gemini

In the Gemini web app, open Settings → Connected Apps → Custom apps and add https://retirementlab.app/api/mcp. Continue through the Retirement Lab sign-in and approval screen. In a chat, type @ and select Retirement Lab to use the connected app. Google currently limits custom apps to adults in the US with a personal Google Account, English as the app language, and Keep Activity enabled. See the Gemini setup steps for details.

Connect another MCP client

For clients such as Claude that support remote MCP servers, add the production endpoint below and complete the OAuth sign-in flow. Disconnect a client later from Connected apps in Retirement Lab.

https://retirementlab.app/api/mcp

API keys are an advanced fallback

For automation or a client that cannot complete browser OAuth, sign in to Retirement Lab, open MCP API keys in the account menu, and issue a key. Configure the client to send it only to the production endpoint as an Authorization: Bearer <key> header. Revoke unused keys from the same account screen.

Calculator tool catalog

The catalog below is generated from the live MCP registry rather than a manually maintained count.

Live registry: 23 tools · catalog revision sha256-696a2183a7f3a49b

• Render Projection render_projection

  After reading or waiting for a completed run or immutable share, call this once to render its stored hypothetical projection. It never starts or polls compute.

• Compare Two Projections compare_projections

  After two runs or shares have both completed, call this once to place exactly two stored hypothetical projections side by side. Based on your inputs, the simulation shows each side's own rates, the gap between them, and where their stored percentile bands separate. It never starts or polls compute.

• Run Retirement Simulation run_simulation

  Use this when a user asks whether their savings will last, when they could retire, or how a spending, saving, or retirement-age assumption changes their outcome. Do not use it for investment picks, live market data, or budgeting. Enqueue a hypothetical projection; based on your inputs, the simulation shows status and polling details after REST authorization checks run. For an inline simulation, omitting simulation_mode defaults to monte_carlo_iid.

• Run Parameter Sweep run_sweep

  General sweep interface for the broader sweep-variable set and engine-generated points. Enqueue a hypothetical projection after REST tier and run-limit checks; use compare_countries for country comparisons. For an inline simulation, omitting simulation_mode defaults to monte_carlo_iid.

• Compare Tax Residences compare_countries

  Use this when a user asks how retiring in, or moving to, another country would change taxes and simulated outcomes. Compare supported countries by enqueueing a country sweep for a hypothetical projection; based on your inputs, the simulation shows status and polling details. For an inline simulation, omitting simulation_mode defaults to monte_carlo_iid.

• Run Sensitivity Sweep sensitivity_sweep

  Use this when a user asks how outcomes change across several values of one assumption, such as spending levels or retirement ages. Preferred convenience wrapper for explicit values of its supported single non-country variables. Enqueue a hypothetical projection and return status and polling details. For an inline simulation, omitting simulation_mode defaults to monte_carlo_iid.

• Inspect Simulation Result get_run_result

  Return compact stored results for a run; the simulation shows probabilities, terminal-wealth percentiles, and selected details based on your inputs. Succeeded sweeps include compact sweep_points by default; sweep_points is also an explicit sweep selector. For single simulations, use yearly_percentiles for year-by-year percentile bands. For sweeps, omit selectors or use sweep_points; yearly_percentiles is invalid.

• Read Saved Scenario get_scenario

  Read a private mutable saved scenario and its normalized calculator inputs.

• Read Shared Result get_share

  Read a compact immutable public hypothetical-result share summary. The default omits the full configuration and year-by-year arrays. Select simulation_snapshot for canonical inputs or yearly_percentiles for aligned years and p10/p50/p90 arrays. To change its inputs, create a private variant from the share directly.

• List Saved Scenarios list_scenarios

  List private saved calculator scenarios, which may later be updated or cloned.

• List Simulation Runs list_runs

  List private immutable hypothetical-run summaries without loading result or simulation payloads.

• List Shared Results list_shares

  List immutable public hypothetical-result share snapshots owned by this account.

• Create Saved Scenario create_scenario

  Create a new mutable saved calculator scenario from a validated simulation payload.

• Update Saved Scenario update_scenario

  Apply JSON Merge Patch to saved calculator inputs using optimistic concurrency. Runs and public shares cannot be updated.

• Clone Scenario clone_scenario

  Create a new mutable saved calculator scenario from a scenario, immutable run, or immutable public share snapshot.

• Create Scenario Variant create_variant

  Apply JSON Merge Patch to a scenario, run, or public share; optionally save and enqueue the resulting hypothetical projection. Lineage is persisted.

• Preview Exit Tax preview_exit_tax

  Use this when a user asks what exit or departure tax leaving a country would trigger. Preview a proposed relocation exit-tax calculation; based on your inputs, the hypothetical projection shows estimated tax impact without enqueueing compute.

• Preview Roth Conversion Tax preview_conversion_tax

  Use this when a user asks what a Roth conversion would cost in tax. Preview a Roth conversion tax calculation; based on your inputs, the hypothetical projection shows estimated tax impact without enqueueing compute.

• Wait for Simulation Run wait_for_run

  Poll a stored run for a bounded period and return what the simulation shows once available, or a still-running envelope. For single simulations use yearly_percentiles for year-by-year percentile bands. For sweeps omit selectors or use sweep_points; yearly_percentiles is invalid.

• Save Run as Scenario save_scenario

  Save an unnamed run as a named scenario when the user asks to keep, name, or share it; otherwise runs stay unnamed and appear in the web app's run history. The history_url opens the stored hypothetical projection in the web app.

• Create Public Share Link create_share_link

  Create an externally visible, unlisted, immutable hypothetical-result share URL from exactly one completed run_id or the latest clean completed run for config_name. Anyone with the URL can view it; this never reruns a scenario.

• Cancel Simulation Run cancel_run

  Cancel a queued or running MCP-originated hypothetical projection owned by this account.

• List Supported Inputs get_supported_inputs

  Use this first when a user asks about retirement timing, whether savings will last, sustainable spending, financial independence, or retiring abroad, before building a simulation payload. List supported calculator inputs, including countries, tax regimes, simulation modes, and the current assumptions version. The response also includes a ready-to-adapt minimal example payload and a short list of common input traps, including that omitted simulation_mode defaults to monte_carlo_iid for MCP runs. Read account_capabilities for available features and separate run/compute allowances. Optionally pass sweep arguments for a read-only compute-cost estimate.

Public information and support

Read the first-party MCP documentation, including authentication, currency rules, quotas, example workflows, data handling, and troubleshooting. See the Privacy Policy for the complete data-use and retention terms.

Questions: contact support at support@cedarwelllabs.com. This page does not make any claim about outbound reply configuration for that address.