MCP HeartbeatTHE MCP OBSERVATORY
Public workspace

Explore

Evidence for your next connection.

Independent measurements of remote MCP servers. Every observation has a timestamp.

Read-only probes

MCP server · AI / LLM tooling

MakerPortal compute

Deterministic engineering solvers: biquad filter design, room eigenmodes, LLM VRAM fit.

Checks passed
12 / 22

2 failed · 8 not measured

Median response
494 ms

Median of successful probes over 7 days

30-day uptime
Not measured

Share of countable probes over 30 days, including daily rollups. Auth challenges are excluded.

Discovered tools
8

Tool definitions returned by this server

Independent monitoring

Health & checks

Status history

Outdated check

Last connection measurement is over 24 hours old. Current availability is unknown.

Last checked
Check summary by test group
Test areaPassedFailedUnmeasured
ConnectionCan a client connect and discover tools?
500
Reliability & speedDoes it respond consistently and quickly?
004
Access & authenticationWhat is required to use this server?
102
Tool qualityAre the tool definitions usable by an agent?
310
Publisher identityCan the publisher be traced to its source?
312

Unmeasured means there is not enough evidence to decide. How these checks work

Inspect individual checks 22 recorded

Core

  • Pass
    Reachable

    Latest probe returned HTTP 200 in 494 ms.

  • Pass
    Valid handshake

    protocolVersion 2025-11-25, serverInfo.name makerportal.

  • Pass
    Lists tools

    tools/list returned 8 tools.

  • Pass
    Current protocol

    Negotiated 2025-11-25. The bar is 2025-06-18 or newer.

  • Pass
    HTTPS

    The endpoint URL is https.

Performance

  • Not measured
    Fast (p50)

    Median latency 494 ms over 1 samples in 7 days. The bar is 1000 ms. Need at least 5 samples.

  • Not measured
    Consistent (p95)

    95th percentile 494 ms over 1 samples in 7 days. The bar is 3000 ms. Need at least 20 samples.

  • Not measured
    Reliable (uptime)

    1 of 1 attempts returned a tool list in 30 days (100%). The bar is 99%. Need at least 30 samples.

  • Not measured
    Stable tool list

    Fewer than two successful probes in 30 days, so tool-list stability is not measured.

Access

  • Pass
    Open access

    tools/list succeeded with no credential, and the record declares none.

  • Not measured
    Standard auth

    Auth is not required, so the OAuth metadata check does not apply.

  • Not measured
    Free tier cited

    No publisher quote has been checked.

Tools

  • Pass
    Tools described

    Every tool description is at least 20 characters.

  • Pass
    Valid input schemas

    Every inputSchema is a JSON Schema object.

  • Pass
    Parameters documented

    35 of 35 parameters have a description (100%). The bar is 80%.

  • Fail
    Safety hints

    8 tools set neither readOnlyHint nor destructiveHint.

Publisher

  • Pass
    Verified namespace

    Listed in the Official MCP Registry.

  • Pass
    Website matches publisher

    The website host matches the reverse-domain namespace.

  • Fail
    Source repo linked

    No repository URL is on file.

  • Not measured
    Repo owner matches

    This namespace is not an io.github login, so the owner comparison does not apply.

  • Pass
    Recently updated

    Updated 2026-09-04T23:30:52.499931Z, within 180 days.

  • Not measured
    Open-source licence

    No GitHub repository to ask about a licence.

Start using MakerPortal compute

Connect to this server

Choose your client, copy the configuration, then enable the server in your client’s MCP settings.

Run this command in your terminal, then restart Claude Code.

Claude Code

claude mcp add --transport http makerportal-compute https://makerportal.ai/api/mcp

Capabilities

Tools 8

biquadDesign

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.

Discovered
gaussianBeam

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.

Discovered
llmVramFit

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.

Discovered
opticsResonator

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.

Discovered
portLength

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.

Discovered
roomModes

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.

Discovered
roomShapeBand

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.

Discovered
solenoidField

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.

Discovered

Recent measurements

Probe history

View status
Latest stored probes. Raw probe rows are kept for 14 days.
CheckedResultResponseTools
Connected494 ms8