# Occam (remote · occam.fit)

Finds the simplest equation consistent with your data. SINDy and PySR symbolic regression via MCP.

- Trust score: 75/100 (medium)
- Change this week: +6
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `occam.fit`: 75/100 (this document), [markdown](https://verifymcp.io/servers/fit-occam-occam/occam.md), [page](https://verifymcp.io/servers/fit-occam-occam/occam)

## Channel facts

- Endpoint: `https://occam.fit/mcp/`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.1.1`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Endpoint Security**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 72/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 3860 tokens (~482/item across 8 items; 4 tools + 4 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http fit-occam-occam https://occam.fit/mcp/
```

### Codex

```toml
[mcp_servers.fit-occam-occam]
url = "https://occam.fit/mcp/"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "fit-occam-occam": {
      "type": "remote",
      "url": "https://occam.fit/mcp/",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add fit-occam-occam --url https://occam.fit/mcp/ --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  fit-occam-occam:
    url: "https://occam.fit/mcp/"
```

### Other

```json
{
  "mcpServers": {
    "fit-occam-occam": {
      "type": "http",
      "url": "https://occam.fit/mcp/"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-02 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-31 (score 74, +3)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 71, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-29 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-27 (score 69, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 68)

First indexed and scored.

## MCP tools (4)

### `feature_request` (~139 tokens)

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 than
    the compute tools' 10/hour to prevent log flooding. Descriptions
    longer than 500 characters are truncated.

Input parameters:

- `description` (string, required): A short description of the feature you need. Examples: 'LaTeX output for equations', 'support for ODE constraints', 'GPU-accelerated search', 'larger dataset limits'. Helps prioritize development.

Output parameters:

- `description` (string)
- `message` (string)
- `ok` (boolean)

### `sindy_run` (~889 tokens)

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 time structure, use
    pysr_run instead.

    Pricing: free tier up to 100 rows and 8 variables. Beyond that,
    $0.05 + $0.01 per 100 extra rows + $0.01 per extra variable squared,
    via x402 (USDC on Base) or MPP/Stripe. MPP/Stripe adds a flat $0.35
    per-transaction fee (Stripe processing), so the MPP challenge amount
    in a `payment_required` response is $0.35 higher than the x402 amount
    for the same base price; x402 gets the lower rate. Omit `payment`
    for free-tier requests; paid requests without a valid credential
    receive a `payment_required` result with pricing and accepted schemes.
    Full pricing table as structured JSON: occam://pricing

    Advisory limits: jobs over 500,000 rows or 50 variables are accepted
    but may not converge within the time budget; the response carries a
    top-level `warning` the agent should surface and treat as tentative.

    If `feature_names` is supplied, its length must equal the number of
    data columns; a mismatch is rejected with a validation error.

    Rate limit: 10 requests/hour per IP, 200/hour global, max queue
    depth 20 (shared with pysr_run and pysr_uncertainty).

    Response (success) includes `equations[]` (each with `variable`,
    `equation`, `expression`, `expression_latex`, `r2`), `library_terms`,
    `nonzero_terms`, `elapsed_seconds`, `canonical_match` (dict with
    `system`, `form`, `variable_map`, `parameter_map`, `confidence` if
    the discovered system matches one of Lorenz / Lotka-Volterra /
    Van der Pol / Duffing; `null` otherwise), optional `warning`,
    optional `_meta` (MPP receipt on paid calls). Full response and
    payment-required schemas: occam://tool-schemas

    Example request:
      data=[[1.0, 0.0], [0.95,…

Input parameters:

- `data` (array, required): 2D array of time series data. Each row is a timestep, each column is a state variable. Free tier: 100 rows, 8 variables. Paid tier: up to 500,000 rows, 50 variables.
- `feature_names`: Names for each variable/feature column. Defaults to x0, x1, ...
- `max_iter` (integer): Maximum STLSQ optimizer iterations. Default 20.
- `payment`: Payment credential. Accepts either a JSON object or a JSON-encoded string (FastMCP's transport pre-parses strings whose field annotation is non-bare-`str` into objects, so the object form is canonica…
- `poly_degree` (integer): Polynomial library degree for SINDy candidate functions. Default 2.
- `t` (array, required): Timestamps corresponding to each row of data. Length must match row count.
- `threshold` (number): STLSQ sparsity threshold. Higher values produce sparser equations. Default 0.1.

Output parameters:

- `canonical_match`
- `elapsed_seconds`
- `equations`
- `library_terms`
- `nonzero_terms`
- `warning`

### `pysr_run` (~1457 tokens)

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 early
    on convergence. For differential equations from time series, use
    sindy_run instead.

    Pricing: free tier up to 100 rows × 8 features, 60s timeout. Beyond
    that, $0.25 + $0.03 per 100 extra rows + $0.01 per extra feature
    squared, timeout up to 300s (5 min), via x402 (USDC on Base) or
    MPP/Stripe. MPP/Stripe adds a flat $0.35 per-transaction fee (Stripe
    processing), so the MPP challenge amount in a `payment_required`
    response is $0.35 higher than the x402 amount for the same base
    price; x402 gets the lower rate. Omit `payment` for free-tier
    requests; paid requests without a valid credential receive a
    `payment_required` result with pricing and accepted schemes. Full
    pricing: occam://pricing

    Advisory limits: jobs over 50,000 rows or 20 features are accepted
    but may not converge; response carries a top-level `warning`.

    Operators: fixed supported set only — custom operators (e.g.
    'inv(x) = 1/x') are rejected. Unary: sin, cos, tan, exp, log, log2,
    log10, sqrt, abs, sinh, cosh, tanh. Binary: +, -, *, /, ^.
    See also prompt `supported_operators`.

    Loss metric: `loss` (in `pareto_front[].loss` and `best_loss`) is
    mean squared error between model prediction and `y` on the full
    training set — not RMSE, and not normalized by Var(y). A threshold
    appropriate for one dataset scales with y's magnitude, so set
    `loss_threshold` with that in mind (e.g. for y values near 1.0,
    1e-6 is a tight fit; for y near 1000, the equivalent is 1.0).

    Early termination: set `loss_threshold` to stop at your noise floor.
    The server also stops when the search stalls (<1% improvement in the
    last third of the budget); disable with `stall_detection=fa…

Input parameters:

- `X` (array, required): 2D array of input features. Each row is an observation, each column is a feature. Free tier: 100 rows, 8 features. Paid tier: up to 50,000 rows, 20 features.
- `binary_operators`: Allowed binary operators, drawn from the fixed supported set: +, -, *, /, ^. Custom operators are NOT supported. Default: +, -, *, /. Pass [] for none.
- `feature_names`: Names for each variable/feature column. Defaults to x0, x1, ...
- `loss_threshold`: Optional early-stop threshold on the best loss found. If set, the search terminates as soon as any Pareto-front member reaches a loss at or below this value, even if the timeout has not been reached.…
- `max_complexity` (integer): Maximum expression tree size. Higher allows more complex expressions. Default 20, max 25.
- `payment`: Payment credential. Accepts either a JSON object or a JSON-encoded string (FastMCP's transport pre-parses strings whose field annotation is non-bare-`str` into objects, so the object form is canonica…
- `populations` (integer): Number of evolutionary populations for the search. Default 15, max 20.
- `stall_detection` (boolean): When true (default), the server stops the search early if the best loss has not improved by more than 1% during the last third of the time budget. This reclaims compute once the search has converged.…
- `timeout_seconds` (integer): Wall clock time limit in seconds. Free tier: max 60. Paid tier: max 300 (5 minutes). Default 60.
- `unary_operators`: Allowed unary operators, drawn from the fixed supported set: sin, cos, tan, exp, log, log2, log10, sqrt, abs, sinh, cosh, tanh. Custom operators (e.g. 'inv(x) = 1/x') are NOT supported — only the nam…
- `y` (array, required): Target values, one per row of X.

Output parameters:

- `best_complexity`
- `best_expression`
- `best_expression_latex`
- `best_loss`
- `elapsed_seconds`
- `pareto_front`
- `queue_seconds`
- `stop_reason`
- `warning`

### `pysr_uncertainty` (~858 tokens)

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 it back here with
    the same dataset to get CIs on its fit constants.

    Returns frequentist bootstrap confidence intervals, not Bayesian
    credible intervals — posterior inference over expression structures
    is an open research problem. This tool freezes the expression
    chosen by the caller and bootstraps only its numeric constants;
    uncertainty about *which* expression is correct is not quantified.

    Bootstrap semantics:
      - If y_sigma is supplied, uses parametric bootstrap
        (y_b = y + Normal(0, y_sigma)). CI reflects user-stated
        measurement noise.
      - Otherwise uses residual bootstrap: fit once, resample residuals.
        CI reflects estimated-from-residuals noise.

    Only Float constants in the expression become free parameters.
    Integers stay structural (the 2 in x**2 is a function-class choice,
    not a fit constant). Expressions with no Float constants
    (e.g. "x + y") will be rejected with a validation error.

    Expression grammar: the `expression` string is parsed by sympy.
    Accepted operators are the same set pysr_run emits: unary `sin`,
    `cos`, `tan`, `exp`, `log`, `log2`, `log10`, `sqrt`, `abs`, `sinh`,
    `cosh`, `tanh`; binary `+`, `-`, `*`, `/`, `^` (or `**`). Whitespace
    and parenthesization are free. Every free symbol in the expression
    must correspond to an entry in `feature_names` — an unrecognised
    symbol is silently treated as a fresh sympy Symbol and the fit will
    fail downstream rather than reject early. Parse failures (syntax
    errors, malformed operators) surface as tool errors.

    If `feature_names` is supplied, its length must equal the number of
    columns in `X`; a mismatch is rejected with a validation error.…

Input parameters:

- `X` (array, required): 2D array of input features. Each row is an observation, each column is a feature. Free tier: 100 rows, 8 features. Paid tier: up to 50,000 rows, 20 features.
- `alpha` (number): Significance level. 0.05 → 95%% CI. Default 0.05.
- `expression` (string, required): The expression to bootstrap, as returned by pysr_run (`best_expression` or a `pareto_front[i].expression`). Only numeric Float constants are treated as free parameters — integers in the expression (e…
- `feature_names`: Names for each variable/feature column. Defaults to x0, x1, ...
- `n_resamples` (integer): Number of bootstrap resamples. Higher = tighter CIs, more compute. Default 100.
- `x_grid`: Optional 2D grid of feature values at which to report a prediction band. Must have the same number of columns as X. Omit to skip prediction-band computation.
- `y` (array, required): Target values, one per row of X.
- `y_sigma`: Optional per-point measurement standard deviations, or a single scalar applied to all points. When supplied, the helper uses parametric bootstrap (y_b = y + Normal(0, y_sigma)); otherwise it uses res…

Output parameters:

- `alpha` (number)
- `bootstrap_method` (string)
- `coefficients` (array)
- `n_requested_resamples` (integer)
- `n_successful_resamples` (integer)
- `note` (string)
- `prediction_ci`

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/fit-occam-occam/occam#diagnostics

## Score history

- 2026-08-03: 75
- 2026-08-02: 75
- 2026-08-01: 74
- 2026-07-31: 74
- 2026-07-30: 71
- 2026-07-29: 70
- 2026-07-28: 69
- 2026-07-27: 69
- 2026-07-26: 68

## Links

- Remote endpoint: https://occam.fit/mcp/
- Website: https://occam.fit/
- Changelog RSS feed: https://verifymcp.io/servers/fit-occam-occam/occam/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/fit-occam-occam/occam/changelog.json
- HTML version of this page: https://verifymcp.io/servers/fit-occam-occam/occam