compoundsim MCP server

• Registry nameapp.compoundsim/compoundsimverified in the MCP registry

The registry name sits under compoundsim.app. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

• Stateanswerschecked 2026-11-01
• Tools5
• Server calls itselfcompoundsim
• Server version1.0.0
• Protocol version2025-06-18

On 2026-11-01 the server answered initialize and tools/list without a sign-in. First answer in 235 ms.

• Its tools do every use case we checked: Project year-by-year growth of monthly savings; Compare outcomes across several annual return assumptions.
• Checked on 3 of the 7 days it takes to judge reliability.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

• INITE MCP scoreafter a weeka score needs 7 daily checks: 3 so far
• What an agent can do with it2 of 2 use cases
• Answeredmeasuring3 of the 7 daily checks it takes to print a share
• Median first answer314 ms
• Space in an agent's context≈ 3,522 tokensthe definitions of all its tools (5), which an agent carries on every turn
• Tool definitionsA · 100 of 100
• Typed results0 of 5 toolsdeclared outputSchema: results come typed, read once

• Every tool passes all six checks.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

• simulate_portfolio

  Monte Carlo simulation of investing monthly (plus an optional starting sum) in one asset or a mix rebalanced monthly. Returns the range of outcomes by year (10th to 90th percentile), the deepest fall along the way, the mix's own past…

• compare_portfolios

  Runs the same monthly-investing plan through 2 to 4 portfolios (the same simulation as simulate_portfolio) and returns each one's final outcome range, deepest fall, past return and volatility, and url, for questions like 'S&P 500 or…

• simulate_withdrawal

  Monte Carlo simulation of withdrawing a yearly percentage of a starting balance, raised with inflation every month, from a portfolio (the 4% rule and its variants). Returns the share of paths that still had money at the end, when the…

• simulate_fixed_rate

  Deterministic compound growth of monthly contributions (plus an optional starting sum) at a fixed annual return. Returns contributions, gains and total by year, and a compoundsim.app url. Use simulate_portfolio for the range of outcomes…

• get_asset_returns

  Annualised past returns of the assets compoundsim simulates, over the last 5, 10 or 20 years, all the data, or a calendar span: total return with dividends reinvested, price return, the dividends' share, volatility, and the return after…