This server exposes symbolic regression through two tools: sindy_run for discovering differential equations from time series data in seconds, and pysr_run for finding algebraic relationships via evolutionary search that returns a Pareto front of expressions ranked by complexity versus accuracy. It wraps PySINDy and SymbolicRegression.jl under the hood. You'd reach for this when you have numerical measurements and want governing equations instead of black box models. The free tier handles up to 100 rows and 8 variables, then switches to pay per use via x402 or card. Connects over streamable HTTP to occam.fit/mcp/ and includes a bootstrap uncertainty tool for getting confidence intervals on fitted constants.
Public tool metadata for what this MCP can expose to an agent.
feature.requestRequest a feature that Occam doesn't support yet. Use this when you need a capability that Occam doesn't currently offer. Requests are logged and used to prioritize development.1 paramsRequest a feature that Occam doesn't support yet. Use this when you need a capability that Occam doesn't currently offer. Requests are logged and used to prioritize development.
descriptionstringsindy.runSparse Identification of Nonlinear Dynamics (SINDy). Discovers governing differential equations from time series data. Returns human-readable sparse expressions. Fast (seconds). Best for systems where you have time-resolved measurements of multiple state variables and want to...6 paramsSparse Identification of Nonlinear Dynamics (SINDy). Discovers governing differential equations from time series data. Returns human-readable sparse expressions. Fast (seconds). Best for systems where you have time-resolved measurements of multiple state variables and want to...
tarraydataarraymax_iterintegerthresholdnumberpoly_degreeintegerfeature_namesvaluepysr.runEvolutionary Symbolic Regression (PySR). Discovers algebraic equations from feature/target data. Returns a Pareto front of expressions ranked by the tradeoff between complexity and accuracy. Slower than SINDy (10-60s). Best for finding closed-form relationships without time st...8 paramsEvolutionary Symbolic Regression (PySR). Discovers algebraic equations from feature/target data. Returns a Pareto front of expressions ranked by the tradeoff between complexity and accuracy. Slower than SINDy (10-60s). Best for finding closed-form relationships without time st...
Xarrayyarraypopulationsintegerfeature_namesvaluemax_complexityintegertimeout_secondsintegerunary_operatorsvaluebinary_operatorsvaluecom.mcparmory/google-sheets
domdomegg/google-sheets-mcp
henilcalagiya/google-sheets-mcp
cct15/war-dashboard-data
moooonad/mcp-google-sheets-full
io.github.br0ski777/csv-to-json