Connect Occam and your agent gets 4 tools, among them feature_request, pysr_run, pysr_uncertainty. It answers at https://occam.fit/mcp/ over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 6 of 6 times since 10 September 2026; the last check, on 19 October 2026, succeeded.
Finds the simplest equation consistent with your data. SINDy and PySR symbolic regression via MCP.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
feature_request | Request 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. Rate limit: 5 requests/hour per IP, 50/hour global — stricter Inputs: description |
pysr_run | Evolutionary Symbolic Regression (PySR). Discovers algebraic equations y = f(x1, x2, ...) from feature/target data. Returns a Pareto front ranked by the complexity/accuracy tradeoff. Slower than SINDy (10-60s); searches often terminate earl Inputs: X, y, feature_names, unary_operators, binary_operators, max_complexity |
pysr_uncertainty | Bootstrap confidence intervals for the numeric constants of a frozen expression, plus optional prediction bands on an x-grid. Typical flow: call pysr_run, pick an expression from the response (best_expression or a pareto_front entry), pass Inputs: expression, X, y, feature_names, y_sigma, n_resamples |
sindy_run | Sparse Identification of Nonlinear Dynamics (SINDy). Recovers governing differential equations (dx/dt = f(x)) from time series data. Returns human-readable sparse expressions. Fast (seconds). For algebraic y = f(x) relationships without tim Inputs: data, t, feature_names, poly_degree, threshold, max_iter |
Every block below points at https://occam.fit/mcp/. Pick your client and copy.
claude mcp add --transport http occam https://occam.fit/mcp/
{
"mcpServers": {
"occam": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://occam.fit/mcp/"]
}
}
}{
"mcpServers": {
"occam": {
"url": "https://occam.fit/mcp/"
}
}
}{
"servers": {
"occam": {
"type": "http",
"url": "https://occam.fit/mcp/"
}
}
}{
"context_servers": {
"occam": {
"url": "https://occam.fit/mcp/"
}
}
}{
"mcpServers": {
"occam": {
"serverUrl": "https://occam.fit/mcp/"
}
}
}{
"mcpServers": {
"occam": {
"url": "https://occam.fit/mcp/"
}
}
}name: Occam
version: 0.0.1
schema: v1
mcpServers:
- name: Occam
type: streamable-http
url: https://occam.fit/mcp/{
"mcpServers": {
"occam": {
"httpUrl": "https://occam.fit/mcp/"
}
}
}{
"mcpServers": {
"occam": {
"type": "http",
"url": "https://occam.fit/mcp/"
}
}
}{
"mcpServers": {
"occam": {
"url": "https://occam.fit/mcp/"
}
}
}goose://extension?url=https%3A%2F%2Foccam.fit%2Fmcp%2F&type=streamable_http&id=occam&name=Occam
It answered our last check on 19 October 2026 in 322 ms. Over 6 checks since 10 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by occam.fit and served from occam.fit, the vendor's own domain: https://occam.fit/mcp/.
4, as returned by the server's own tools/list on 11 September 2026: feature_request, pysr_run, pysr_uncertainty, sindy_run.
It answered our last check on 19 October 2026 in 322 ms. Over 6 checks since 10 September 2026 it answered 6.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://occam.fit/mcp/. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: fit.occam. Endpoint host: occam.fit. ARD identifier: urn:air:fit.occam:mcp:occam.
First indexed 10 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.