# MakerPortal compute (remote · makerportal.ai)

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

- Trust score: 74/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-25

## Components

- remote · `makerportal.ai`: 74/100 (this document), [markdown](https://verifymcp.io/servers/ai-makerportal-compute/api-mcp.md), [page](https://verifymcp.io/servers/ai-makerportal-compute/api-mcp)
- npm · `@makerportal/mcp`: 44/100, [markdown](https://verifymcp.io/servers/ai-makerportal-compute/makerportal-mcp.md), [page](https://verifymcp.io/servers/ai-makerportal-compute/makerportal-mcp)

## Channel facts

- Endpoint: `https://makerportal.ai/api/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 2026-09-25.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 5 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - 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**: 64/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1578 tokens (~315/item across 5 items; 5 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 67/100
  - Stability observed for 20 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.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 5 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the MakerPortal compute MCP server?

MakerPortal compute is a hosted endpoint at https://makerportal.ai/api/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

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

### Cursor

```json
{
  "mcpServers": {
    "ai-makerportal-compute": {
      "url": "https://makerportal.ai/api/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ai-makerportal-compute": {
      "type": "http",
      "url": "https://makerportal.ai/api/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.ai-makerportal-compute]
url = "https://makerportal.ai/api/mcp"
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add ai-makerportal-compute --url 'https://makerportal.ai/api/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ai-makerportal-compute:
    url: "https://makerportal.ai/api/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "ai-makerportal-compute": {
      "Transport": "http",
      "Url": "https://makerportal.ai/api/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add ai-makerportal-compute -t streamable-http -u 'https://makerportal.ai/api/mcp'
```

### Other

```json
{
  "mcpServers": {
    "ai-makerportal-compute": {
      "type": "http",
      "url": "https://makerportal.ai/api/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.

### 2026-09-25 (score 74, 0)

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

### 2026-09-24 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 60 to 63. That category is still filling its 30-day observation window: 18 days of observed history at the previous scan, 19 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-22 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-20 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-18 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-16 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-13 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-11 (score 68, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (5)

### `biquadDesign` (~336 tokens)

Design one RBJ-cookbook biquad and report its numerical behaviour.

Design one RBJ-cookbook biquad and report its numerical behaviour.

The identical function that renders /lab/biquad/{type}/{freq}. 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.

Input parameters:

- `freq` (number, required): Corner (or centre) frequency f0 in Hz. Must be below Nyquist.
- `fs` (number): Sample rate in Hz. Defaults to 48000.
- `gain` (number): Peak/shelf gain in dB. Ignored by types that do not use gain.
- `include` (string): Optional heavy block to include, omitted by default. "curve": The 240-point log-spaced magnitude response, and one per sweep row.
- `q` (number): Filter Q. Defaults to the type’s own default. Shelves ignore it (S is fixed at 1, matching Web Audio).
- `type` (string, required): Filter type.

Output parameters:

- `inputs` (object): The parsed inputs, echoed back with defaults filled in.
- `license` (string)
- `provenance` (object)
- `result` (object): The solved analysis. Shape is per-tool.

### `roomModes` (~318 tokens)

Solve the eigenmodes of a rectangular room.

Solve the eigenmodes of a rectangular room.

The identical function that renders /lab/room-modes/{w}x{l}x{h}. 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.

Input parameters:

- `height` (number, required): Ceiling height in feet.
- `include` (string): Optional heavy block to include, omitted by default. "modes": Every solved mode and the axial subset, with their (nx, ny, nz) orders.
- `length` (number, required): Room length in feet.
- `maxFreq` (number): Highest mode frequency to solve for, in Hz. Defaults to 300. Mode count scales with volume × frequency³, so a large room and a high maxFreq together are refused with a 400 once the enumeration would…
- `width` (number, required): Room width in feet.

Output parameters:

- `inputs` (object): The parsed inputs, echoed back with defaults filled in.
- `license` (string)
- `provenance` (object)
- `result` (object): The solved analysis. Shape is per-tool.

### `llmVramFit` (~279 tokens)

Decide whether one LLM fits one accelerator, at every quantization.

Decide whether one LLM fits one accelerator, at every quantization.

The identical function that renders /lab/llm-vram/{model}/{gpu}. 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.

Input parameters:

- `batch` (integer): Concurrent sequences sharing the cache. Omit it for the published page's 1.
- `context` (integer): Context length in tokens used for the headline verdict. Omit it and the solver takes its own default of 8192, which is what the published page states.
- `gpu` (string, required): Accelerator slug.
- `kvBytes` (integer): Bytes per KV cache element: 2 for FP16/BF16 cache, 1 for an 8-bit cache. Omit it for the published page's 2.
- `model` (string, required): Model slug.

Output parameters:

- `inputs` (object): The parsed inputs, echoed back with defaults filled in.
- `license` (string)
- `provenance` (object)
- `result` (object): The solved analysis. Shape is per-tool.

### `solenoidField` (~290 tokens)

Solve the on-axis magnetic field of an air-core solenoid.

Solve the on-axis magnetic field of an air-core solenoid.

The identical function that renders /lab/solenoid/{diameter}x{length}mm. 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.

Input parameters:

- `current` (number): Winding current in amperes. Defaults to 1. Only the product of turns and current changes the answer.
- `diameter` (number, required): Mean winding diameter in millimetres.
- `length` (number, required): Winding length along the axis, in millimetres.
- `turns` (integer): Number of turns. Defaults to 1, which is what the published pages state (their figures are per amp-turn). The field is exactly linear in turns x current.

Output parameters:

- `inputs` (object): The parsed inputs, echoed back with defaults filled in.
- `license` (string)
- `provenance` (object)
- `result` (object): The solved analysis. Shape is per-tool.

### `roomShapeBand` (~214 tokens)

Solve the best rectangular room proportions for a given volume.

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.

Input parameters:

- `volume` (number, required): Room volume in cubic feet. Five bands cover 800–5000 ft³; anything outside that is a 400 naming the range, never an answer from the nearest band.

Output parameters:

- `inputs` (object): The parsed inputs, echoed back with defaults filled in.
- `license` (string)
- `provenance` (object)
- `result` (object): The solved analysis. Shape is per-tool.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/ai-makerportal-compute/api-mcp#diagnostics

## Score history

- 2026-09-25: 74
- 2026-09-24: 74
- 2026-09-23: 73
- 2026-09-22: 73
- 2026-09-21: 72
- 2026-09-20: 72
- 2026-09-19: 71
- 2026-09-18: 71
- 2026-09-17: 70
- 2026-09-16: 70
- 2026-09-15: 69
- 2026-09-14: 69
- 2026-09-13: 69
- 2026-09-12: 68
- 2026-09-11: 68
- 2026-09-10: 67
- 2026-09-09: 67
- 2026-09-08: 66
- 2026-09-07: 66
- 2026-09-06: 65
- 2026-09-05: 65

## Common questions

### What is the MakerPortal compute MCP server?

MakerPortal compute is an MCP server listed in the public MCP registry as ai.makerportal/compute. Deterministic engineering solvers: biquad filter design, room eigenmodes, LLM VRAM fit. This page covers its hosted endpoint (https://makerportal.ai/api/mcp).

### Is the MakerPortal compute MCP server safe to use?

MakerPortal compute scores 74 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the MakerPortal compute MCP server expose?

MakerPortal compute exposes 5 tools: biquadDesign, roomModes, llmVramFit, solenoidField, roomShapeBand. Their descriptions and schemas cost roughly 1,437 tokens of context every time the server is loaded.

### Does the MakerPortal compute MCP server require authentication?

No. We connected to MakerPortal compute without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the MakerPortal compute MCP server still maintained?

MakerPortal compute is still listed as active in the MCP registry. We last reached this channel on 25 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://makerportal.ai/api/mcp
- Website: https://makerportal.ai/lab
- Changelog RSS feed: https://verifymcp.io/servers/ai-makerportal-compute/api-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-makerportal-compute/api-mcp.json
- HTML version of this page: https://verifymcp.io/servers/ai-makerportal-compute/api-mcp