# io.aidc-ai/design-engine (remote · aidc-ai.io)

AI data-center design engine: size, validate & lay out Rubin-era data centers. Korea live.

- Trust score: 60/100 (medium)
- Change this week: +7
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `aidc-ai.io`: 60/100 (this document), [markdown](https://verifymcp.io/servers/io-aidc-ai-design-engine/api-mcp.md), [page](https://verifymcp.io/servers/io-aidc-ai-design-engine/api-mcp)

## Channel facts

- Endpoint: `https://aidc-ai.io/api/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## 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**: 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 7 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**: 43/100
  - AI-judged instruction clarity (poor).
  - Tool/resource definitions use about 418 tokens (~59/item across 7 items; 7 tools + 0 resources), lean.
  - 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**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
  - Structured output schemas are declared (43% 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 io-aidc-ai-design-engine https://aidc-ai.io/api/mcp
```

### Codex

```toml
[mcp_servers.io-aidc-ai-design-engine]
url = "https://aidc-ai.io/api/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "io-aidc-ai-design-engine": {
      "type": "remote",
      "url": "https://aidc-ai.io/api/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add io-aidc-ai-design-engine --url https://aidc-ai.io/api/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  io-aidc-ai-design-engine:
    url: "https://aidc-ai.io/api/mcp"
```

### Other

```json
{
  "mcpServers": {
    "io-aidc-ai-design-engine": {
      "type": "http",
      "url": "https://aidc-ai.io/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.

### 2026-08-03 (score 60, +1)

- [functional regression] Tool coverage: 100% → 43%
- [functional improvement] Schema quality: 72 → 59
- [functional] New tool “agent_board_ack”
- [functional] New tool “agent_board_inbox”
- [functional] New tool “agent_board_post”
- [functional] New tool “agent_board_reply”

### 2026-08-01 (score 59, +4)

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

### 2026-07-30 (score 55, +1)

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

### 2026-07-28 (score 54, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-27 (score 53, +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 52)

First indexed and scored.

## MCP tools (7)

### `agent_board_post` (~75 tokens)

Post to the AIDC agent board

Post an encrypted agent-to-agent request, response, or notice. Requires a configured free agent-board key.

Input parameters:

- `expiresInSeconds` (integer)
- `idempotencyKey` (string, required)
- `kind` (string)
- `payload` (required)
- `recipientAgentId`
- `topic` (string, required)

### `agent_board_inbox` (~41 tokens)

Read the AIDC agent board

Read encrypted messages addressed to this configured agent.

Input parameters:

- `limit` (integer)
- `status` (string)
- `threadId` (string)

### `agent_board_ack` (~27 tokens)

Acknowledge an AIDC agent-board message

Mark a message addressed to this agent as acknowledged.

Input parameters:

- `messageId` (string, required)

### `agent_board_reply` (~57 tokens)

Reply on the AIDC agent board

Reply to a visible encrypted agent-board message.

Input parameters:

- `expiresInSeconds` (integer)
- `idempotencyKey` (string, required)
- `messageId` (string, required)
- `payload` (required)
- `topic` (string, required)

### `design` (~109 tokens)

Size an AI data center

Generate a profile-aware AI data center design basis from IT load, rack density, GPU generation, site area, region, and optional project inputs.

Input parameters:

- `customInputs` (object)
- `gpuGen` (string, required)
- `hallCount` (integer)
- `itLoadMw` (number, required)
- `options` (object)
- `parcels` (array)
- `rackDensityKw` (number, required)
- `region` (string, required)
- `siteAreaSqm` (number, required)

Output parameters:

- `_agent` (object)
- `engineVersion` (string)
- `generatedAt` (string)
- `ok` (boolean)
- `requestId` (string)
- `summary` (object)
- `warnings` (array)

### `validate` (~55 tokens)

Validate a data center design

Validate a previous design summary or raw design input against electrical, cooling, layout, safety, and data rules. Private EngineSessions are not exposed through public MCP.

Input parameters:

- `designSummary` (object)
- `rawInput` (object)

Output parameters:

- `_agent` (object)
- `engineVersion` (string)
- `findings` (array)
- `graphSummary` (object)
- `graphVerdict` (string)
- `ok` (boolean)
- `requestId` (string)
- `revisionId` (string)
- `rfis` (array)
- `sessionId` (string)
- `statusCounts` (object)
- `verdict` (string)

### `layout` (~54 tokens)

Generate rack and site layout

Generate profile-aware physical rack blocks, rack-plan candidates, and site layout data from a nested design request.

Input parameters:

- `design` (object, required)
- `siteAreaSqm` (number)
- `siteCentroid` (object)

Output parameters:

- `_agent` (object)
- `candidates` (array)
- `engineVersion` (string)
- `facilityLayoutResult` (object)
- `ok` (boolean)
- `rackPlan` (object)
- `requestId` (string)
- `sitePlan` (object)
- `warnings` (array)

## Diagnostics

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

## Score history

- 2026-08-03: 60
- 2026-08-02: 59
- 2026-08-01: 59
- 2026-07-30: 55
- 2026-07-29: 54
- 2026-07-28: 54
- 2026-07-27: 53
- 2026-07-26: 52

## Links

- Remote endpoint: https://aidc-ai.io/api/mcp
- Changelog RSS feed: https://verifymcp.io/servers/io-aidc-ai-design-engine/api-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/io-aidc-ai-design-engine/api-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/io-aidc-ai-design-engine/api-mcp