# AI Architectures (remote · mcp.ai-architectures.com)

Search ~500 free house plans and have AI-drafted CAD floor plans (DXF, DWG, PDF) drawn and changed.

- Trust score: 80/100 (high trust)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-06

## Components

- remote · `mcp.ai-architectures.com`: 80/100 (this document), [markdown](https://verifymcp.io/servers/com-ai-architectures-mcp/mcp.md), [page](https://verifymcp.io/servers/com-ai-architectures-mcp/mcp)

## Channel facts

- Endpoint: `https://mcp.ai-architectures.com/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 2026-11-06.

- **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. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation.
  - 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**: 82/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1529 tokens (~127/item across 12 items; 11 tools + 1 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 37/100
  - Stability observed for 11 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 95/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 82% 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 11 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 13 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.
  - Supports UI / widget rendering.

## Install

### How do I install the AI Architectures MCP server?

AI Architectures is a hosted endpoint at https://mcp.ai-architectures.com/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 com-ai-architectures-mcp 'https://mcp.ai-architectures.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-ai-architectures-mcp": {
      "url": "https://mcp.ai-architectures.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-ai-architectures-mcp": {
      "type": "http",
      "url": "https://mcp.ai-architectures.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-ai-architectures-mcp]
url = "https://mcp.ai-architectures.com/mcp"
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add com-ai-architectures-mcp --url 'https://mcp.ai-architectures.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-ai-architectures-mcp:
    url: "https://mcp.ai-architectures.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-ai-architectures-mcp": {
      "Transport": "http",
      "Url": "https://mcp.ai-architectures.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-ai-architectures-mcp -t streamable-http -u 'https://mcp.ai-architectures.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-ai-architectures-mcp": {
      "type": "http",
      "url": "https://mcp.ai-architectures.com/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.

### 2026-11-06 (score 80, +1)

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

### 2026-11-04 (score 79, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-02 (score 78, +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.

### 2026-10-31 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-29 (score 76, +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.

### 2026-10-27 (score 75, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-10-26 (score 74)

First indexed and scored.

## MCP tools (11)

### `search_house_plans` (~270 tokens)

Search free house plans

Use this when the user wants ready-made house plans, floor plan ideas or downloadable plans (for example "3 bedroom ranch under 2,000 sq ft", "small ADU", "barndominium"). Searches a library of about 500 free house plans by AI Architectures, each with a floor plan image, room sizes and free PDF, DXF, IFC and GLB downloads. Returns plan cards with links to the plan page and to change the plan in the CAD studio. Filters are optional; leave out what the user did not ask for.

Input parameters:

- `bathrooms` (number): Minimum number of bathrooms.
- `bedrooms` (integer): Exact number of bedrooms (0 = studio).
- `garage` (boolean): true = only plans with a garage, false = only without.
- `limit` (integer)
- `max_sqft` (integer): Largest living area in square feet.
- `min_sqft` (integer): Smallest living area in square feet (1 m² = 10.76 sq ft).
- `query` (string): Style or type words, e.g. "modern farmhouse", "ranch", "ADU", "barndominium", "narrow lot", "30x40".
- `stories` (integer): Number of storeys.

Output parameters:

- `kind` (string)

### `get_house_plan` (~65 tokens)

Get a house plan

Use this to show one house plan from search_house_plans in detail: description, every floor plan image and all free download links (PDF plan set, DXF per level, IFC, GLB).

Input parameters:

- `slug` (string, required): The plan slug from search_house_plans.

Output parameters:

- `kind` (string)

### `show_community_cad_drawings` (~113 tokens)

Show community CAD drawings

Use this when the user wants to see what the AI drafter draws, or examples of AI-made CAD floor plans. Lists published drawings from the Plan Chat CAD studio (real, unretouched output), each with a preview, the brief it was drawn from, a free DXF download and a link to draw a similar one.

Input parameters:

- `limit` (integer)
- `query` (string): Optional words to filter by, e.g. "townhouse", "office", "3 bedrooms".

Output parameters:

- `kind` (string)

### `prepare_cad_drawing_link` (~117 tokens)

Prepare a CAD studio link

Use this when the user wants a floor plan drawn as CAD (DXF/DWG) but is not signed in to an AI Architectures account here, or prefers to continue on the website, or wants to attach a sketch there. Returns a link that opens the Plan Chat CAD studio with the request already typed in; nothing is drawn or charged until the user presses send on the site.

Input parameters:

- `brief` (string, required): The building in the user's words: type, rooms, sizes, storeys, plot. Any language.

Output parameters:

- `kind` (string)

### `get_design_tool_link` (~118 tokens)

Link to an AI Architectures design tool

Use this when the user wants something AI Architectures does on its website from a photo or image: a remodel preview on a photo of their own home, a photoreal render from a sketch or model view, a render from a description, virtual staging, a listing photo kit, a clean floor plan image from a sketch or scan, a CAD drawing from a sketch, or before/after examples. Returns the page that does it; the user uploads the photo there.

Input parameters:

- `task` (string, required): What the user wants to do.

Output parameters:

- `kind` (string)

### `start_cad_drawing` (~282 tokens)

Start a CAD drawing

Use this when the user asks to draw or design a floor plan as a real CAD drawing and wants it made now. The AI drafter of the Plan Chat CAD studio draws a layered, dimensioned plan (walls, doors, windows, furniture, dimensions, room names and areas) from the description and, if attached, a sketch or photo of a plan. Needs the user's AI Architectures account and spends credits from it (usually 700 to 1,800 credits per drawing; get_credit_balance shows the balance). Drawing takes 1 to 5 minutes; then call get_cad_drawing with the returned drawing_id. Confirm the brief with the user before starting.

Input parameters:

- `brief` (string, required): The building: type, rooms with sizes if known, storeys, overall size or plot, style. Any language. With a sketch, say what it shows.
- `sketch` (object): A sketch, photo or screenshot of a floor plan the user attached in the chat.
- `sketch_url` (string): Optional https URL of a sketch, photo or screenshot of a floor plan (JPG, PNG, WebP, HEIC; up to 15 MB), if no file was attached.
- `units` (string): m = metres and m², ft = feet-inches and sq ft. Use ft for US users.

Output parameters:

- `kind` (string)

### `get_cad_drawing` (~141 tokens)

Get a CAD drawing

Use this to check a drawing started with start_cad_drawing (or one of list_my_cad_drawings): status, what the drafter says, room names, a preview image, the studio link and, when the account allows, DXF, DWG and PDF download links (valid for 10 minutes; call again for fresh ones). While it is still drawing this waits up to wait_seconds for it to finish.

Input parameters:

- `drawing_id` (string, required): The id from start_cad_drawing or list_my_cad_drawings.
- `wait_seconds` (integer): How long to wait for a running drawing to finish before answering.

Output parameters:

- `kind` (string)

### `change_cad_drawing` (~124 tokens)

Change a CAD drawing

Use this when the user asks to change one of their CAD drawings in words ("make the kitchen 4.2 m wide", "move the garage to the left", "add a window to bedroom 2"). The drafter makes the change as a new version (earlier versions stay in the studio). Spends credits from the user's AI Architectures account (usually 60 to 600 per change). Then call get_cad_drawing.

Input parameters:

- `change` (string, required): What should change, in the user's words.
- `drawing_id` (string, required)

Output parameters:

- `kind` (string)

### `list_my_cad_drawings` (~56 tokens)

List my CAD drawings

Use this when the user asks about their own drawings in the Plan Chat CAD studio. Lists them newest first with id, title, number of versions and whether one is being drawn now.

Input parameters:

- `limit` (integer)

Output parameters:

- `kind` (string)

### `get_credit_balance` (~32 tokens)

Get credit balance

Use this when the user asks how many AI Architectures credits their account has left before starting or changing a drawing.

Output parameters:

- `kind` (string)

### `get_profile` (~43 tokens)

Get profile

Return the AI Architectures account behind this connection. The opaque id is the account id, unique and unchanged across token refresh, reconnection and changes to the email or name.

Output parameters:

- `email` (string): Email address for display; not used as the profile identity.
- `id` (string): Opaque, stable AI Architectures account id.
- `name` (string): Display name for the authenticated profile.
- `nickname` (string): A useful label that helps users distinguish connected profiles.

## Diagnostics

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

## Score history

- 2026-11-06: 80
- 2026-11-05: 79
- 2026-11-04: 79
- 2026-11-03: 78
- 2026-11-02: 78
- 2026-11-01: 77
- 2026-10-31: 77
- 2026-10-30: 76
- 2026-10-29: 76
- 2026-10-28: 75
- 2026-10-27: 75
- 2026-10-26: 74

## Common questions

### What is the AI Architectures MCP server?

AI Architectures is an MCP server listed in the public MCP registry as com.ai-architectures/mcp. Search ~500 free house plans and have AI-drafted CAD floor plans (DXF, DWG, PDF) drawn and changed. This page covers its hosted endpoint (https://mcp.ai-architectures.com/mcp).

### Is the AI Architectures MCP server safe to use?

AI Architectures scores 80 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 AI Architectures MCP server expose?

AI Architectures exposes 11 tools: search_house_plans, get_house_plan, show_community_cad_drawings, prepare_cad_drawing_link, get_design_tool_link, and 6 more. Their descriptions and schemas cost roughly 1,361 tokens of context every time the server is loaded.

### Does the AI Architectures MCP server require authentication?

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

### Is the AI Architectures MCP server still maintained?

AI Architectures is still listed as active in the MCP registry. We last reached this channel on 6 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the AI Architectures MCP server?

VerifyMCP ran 14 checks on AI Architectures, covering TLS certificate, Authorization, HTTPS, HSTS header and 10 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://mcp.ai-architectures.com/mcp
- Website: https://plans.ai-architectures.com/ai-assistants
- Changelog RSS feed: https://verifymcp.io/servers/com-ai-architectures-mcp/mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-ai-architectures-mcp/mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/com-ai-architectures-mcp/mcp.json
- HTML version of this page: https://verifymcp.io/servers/com-ai-architectures-mcp/mcp