MakerPortal compute
by makerportal.ai · remote · local (npm) · no sign-in to list tools · v0.1.1 · published by ai.makerportal
Deterministic engineering solvers: biquad filter design, room eigenmodes, LLM VRAM fit.
Changes · 8
8 tools: 8 change things.
Scanned Oct 21, 2026
- Deletes or cancels0Claude Code: deny
- Can't be undone0Claude Code: ask
- Changes things8Claude Code: ask: see these tools
- Only reads0Claude Code: allow
No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.
claude mcp add --transport http compute https://makerportal.ai/api/mcpTools
Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.
8 tools
Changes things 8Claude Code: ask
biquadDesignDesign one RBJ-cookbook biquad and report its numerical behaviour.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Design one RBJ-cookbook biquad and report its numerical behaviour. The identical function behind the /lab/biquad coefficient tables. Returns coefficients at the requested sample rate, coefficients at every other rate whose Nyquist limit clears the corner, pole/zero geometry, the −3 dB points solved by bisection, a Q sweep, a gain sweep where the type uses gain, and the quantised forms. The 240-point response curve is omitted unless include=curve is passed. Non-finite values (a notch is −∞ at f0; a low-pass is −∞ at Nyquist) are encoded as the strings "Infinity", "-Infinity" and "NaN" — JSON has no other honest option, and null would be a different answer. Every result carries provenance.canonicalUrl — the published page for these exact inputs, or the lane hub when they are off the published grid.
gaussianBeamSolve an ideal Gaussian laser beam: Rayleigh range, divergence, radius at a distance, and the waist behind a focusing lens.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Solve an ideal Gaussian laser beam: Rayleigh range, divergence, radius at a distance, and the waist behind a focusing lens. The identical function behind the worked examples on /lab/gaussian-beam-calculator, built from the same q-propagation the calculator runs. Give a wavelength and a 1/e^2 waist radius to get the Rayleigh range, the far-field half-angle divergence and the depth of focus. Add `distance` (metres from the waist) for the beam radius and phase-front curvature there. Add `focal` (millimetres) to put a thin lens at the waist and get the focused waist radius, its distance behind the lens and its Rayleigh range. Every result carries provenance.canonicalUrl — the published page for these exact inputs, or the lane hub when they are off the published grid.
llmVramFitDecide whether one LLM fits one accelerator, at every quantization.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Decide whether one LLM fits one accelerator, at every quantization. The identical function behind the /lab/llm-vram instrument. Returns one row per quantization (FP16 through Q3_K_M) with weight bytes and their basis, headroom, the largest context that fits, and the bandwidth-limited decode ceiling; plus the chosen best-fitting quant, the full-precision row, and a five-state verdict. Model geometry comes from each repo’s own config.json and tensor-shape index; accelerator capacity and bandwidth come from the site’s device table. Every result carries provenance.canonicalUrl — the published page for these exact inputs, or the lane hub when they are off the published grid.
opticsResonatorSolve a two-mirror laser cavity: g-parameters, stability, and the TEM00 waist and mirror spot sizes.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Solve a two-mirror laser cavity: g-parameters, stability, and the TEM00 waist and mirror spot sizes. The identical function behind the worked examples on /lab/optics-bench, built from the resonator code the bench runs. Give the mirror spacing `l` (cm), each mirror radius `r1`, `r2` (cm; positive is concave toward the cavity, negative convex, omitted means flat) and the wavelength `w` (nm). Returns g1, g2, their product, the round-trip half-trace and whether the cavity is stable; when it is, `mode` holds the waist radius (um), its distance from mirror 1 (cm) and the spot radius on each mirror (mm). `mode` is null for an unstable cavity or one on the g1*g2 = 0 or 1 boundary. Every result carries provenance.canonicalUrl — the published page for these exact inputs, or the lane hub when they are off the published grid.
portLengthSolve a vented loudspeaker box for the length of round port to cut, with both end corrections, the smallest workable diameter and the peak port air speed.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Solve a vented loudspeaker box for the length of round port to cut, with both end corrections, the smallest workable diameter and the peak port air speed. The identical function behind the worked examples on /lab/port-length-calculator and the calculator itself. Give the net box volume `vol` (litres), the port inside diameter `dia` (cm) and the tuning `fb` (Hz); `temp` (deg C, default 20) sets the speed of sound. Returns the length to cut (cm), the acoustic length and the end correction it contains, the port area, length/diameter, the air volume the port displaces, and the smallest diameter that can reach the tuning. When the port is too narrow, `tooNarrow` is true and `cutLengthCm` is negative: the end corrections alone already exceed the acoustic length the tuning needs. Add `sd` (cone area, cm^2) and `xmax` (peak excursion, mm) together for the peak port air speed. Every result carries provenance.canonicalUrl — the published page for these exact inputs, or the lane hub when they are off the published grid.
roomModesSolve the eigenmodes of a rectangular room.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Solve the eigenmodes of a rectangular room. The identical function behind the /lab/room-modes instrument. Dimensions are in feet and are converted at 0.3048 m/ft. Returns every mode below maxFreq, the three axial fundamentals, mode pile-ups (three or more modes within 5 Hz, capped at 200 Hz because dense modes above the Schroeder crossover are desirable rather than a defect), the widest axial gap below 200 Hz, and Schroeder frequencies at RT60 = 0.3 s and 0.6 s. The full mode list is omitted unless include=modes is passed; counts are always present. Every result carries provenance.canonicalUrl — the published page for these exact inputs, or the lane hub when they are off the published grid.
roomShapeBandSolve the best rectangular room proportions for a given volume.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Solve the best rectangular room proportions for a given volume. The identical function that renders /lab/room-shape/{lo}-{hi}. Give a room volume in cubic feet and get the proportions to build: the length and width as multiples of the ceiling height, the exact dimensions at your volume, the widest axial gap they leave, and how far those proportions sit from a full solve at your exact volume. Also returns the band the volume falls in, that band's guarantee across its whole range, and which Bolt constraints are active at the answer. Five bands cover 800-5,000 cubic feet; a volume outside that range is refused rather than served from the nearest band. Every result carries provenance.canonicalUrl — the published page for these exact inputs, or the lane hub when they are off the published grid.
solenoidFieldSolve the on-axis magnetic field of an air-core solenoid.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Solve the on-axis magnetic field of an air-core solenoid. The identical function behind the /lab/solenoid table. Returns the centre field per amp-turn and at the requested turns and current, the on-axis profile out to three half-lengths, the span over which the field holds to within 1% and 5% of its centre value, the field at the coil mouth as a fraction of the centre, how far the infinite-solenoid shortcut mu0*n*I overstates the answer, and the turn count below which the closed form should not be used on this geometry. Dimensions are in millimetres. The field is exactly linear in turns x current, so only that product changes the answer. Every result carries provenance.canonicalUrl — the published page for these exact inputs, or the lane hub when they are off the published grid.
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Install
Pinned to version 0.1.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http compute https://makerportal.ai/api/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [],
"ask": [
"mcp__compute__biquadDesign",
"mcp__compute__roomModes",
"mcp__compute__llmVramFit",
"mcp__compute__solenoidField",
"mcp__compute__roomShapeBand",
"mcp__compute__gaussianBeam",
"mcp__compute__opticsResonator",
"mcp__compute__portLength"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as compute. Review it before you use it.