# TheDesignAgent (remote · www.thedesignagent.ai)

A design agent in your coding agent's loop: briefs each screen, reviews UX and visual quality.

- Trust score: 38/100 (low)
- Change this week: 0
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-24

## Components

- remote · `www.thedesignagent.ai`: 38/100 (this document), [markdown](https://verifymcp.io/servers/ai-thedesignagent-mcp/www.md), [page](https://verifymcp.io/servers/ai-thedesignagent-mcp/www)
- npm · `@thedesignagent/mcp`: 28/100, [markdown](https://verifymcp.io/servers/ai-thedesignagent-mcp/thedesignagent-mcp.md), [page](https://verifymcp.io/servers/ai-thedesignagent-mcp/thedesignagent-mcp)

## Channel facts

- Endpoint: `https://www.thedesignagent.ai/mcp`
- Transports: `streamable-http`
- Auth: `required`
- Version: `0.5.3`

## 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 2026-10-24.

- **Endpoint Security**: 94/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - The endpoint enforces authorisation, advertised via RFC 9728 protected-resource metadata.
  - 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.
  - The authorisation server offers only Dynamic Client Registration (RFC 7591), which MCP 2026-07-28 deprecated in favour of Client ID Metadata Documents.
- **Transport & Reachability**: 0/100
  - Transport blocked by authentication: the endpoint requires auth we don't have to verify streamable-http.
- **Schema Quality & AI Usability**: 0/100
  - Schema blocked by authentication: the endpoint requires auth we don't have to read it.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 0/100
  - Tool coverage blocked by authentication: the endpoint requires auth we don't have to read its tools.
- **Tool Safety**: 0/100
  - Tool safety blocked by authentication: the endpoint requires auth we don't have to read its tools.
- **Capabilities**: 0/100
  - Capabilities blocked by authentication: the endpoint requires auth we don't have to read them.

**Unverified: 6 categories.** Categories scored 0 because we could not verify them: authentication we do not have, an unreachable endpoint, or not enough scan history. We only credit what we can confirm.

## Install

### How do I install the TheDesignAgent MCP server?

TheDesignAgent is a hosted endpoint at https://www.thedesignagent.ai/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-thedesignagent-mcp 'https://www.thedesignagent.ai/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "ai-thedesignagent-mcp": {
      "url": "https://www.thedesignagent.ai/mcp"
    }
  }
}
```

### VS Code

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

### Codex

```toml
[mcp_servers.ai-thedesignagent-mcp]
url = "https://www.thedesignagent.ai/mcp"
```

### opencode

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

### OpenClaw

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

### Hermes

```yaml
mcp_servers:
  ai-thedesignagent-mcp:
    url: "https://www.thedesignagent.ai/mcp"
```

### Netclaw

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

### Vellum

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

### Other

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

### 2026-10-08 (score 38, −34)

- [security regression] Endpoint reachability: reachable → behind authorisation
- [security regression] Stability: 0.07 → unverified
- [security regression] Transport: pass → unverified
- [security regression] Tool safety: pass → unverified
- [security improvement] Authorization: partial → pass
- [security] First check of Authorization: partial
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Capabilities: pass → unverified
- [functional] First check of Schema quality: unverified

### 2026-10-05 (score 72, +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.

### 2026-10-04 (score 71, +10)

- [security improvement] Authorization: unverified → partial
- [functional improvement] Stability: unverified → 0.03
- [functional improvement] MCP protocol: fail → pass
- [functional] First check of Tool coverage: 100

### 2026-10-03 (score 61)

First indexed and scored.

## MCP tools (3)

### `Discover` (~401 tokens)

Design brief

Get a build brief calibrated to your project, persona, and the specific screen you're building.

Call this BEFORE building any screen. Returns:
\- The active Job-to-be-Done for the task
\- Relevant heuristics, cognitive guidance, and patterns from the corpus
\- A focused build brief (~600 tokens) to inject into your build context

CALL LIFECYCLE:
\- First call for a new project (no project_id): returns _meta.tda_status='setup_required' with an extraction task. Scan the repo's schema/types/migrations (or, with no repo, ask the user for a short product description as the task explains) and resubmit with project_model populated.
\- Subsequent calls: send ONLY task + project_id. project_model is cached server-side from the first call; resending it wastes ~2–4k tokens per call and re-runs validation. Resend project_model ONLY when a response returns _meta.tda_status='setup_required' or 'model_stale'.

Use project_id from .thedesignagent or memory across calls. Pass repo_hash (SHA256 of git remote origin URL) only as a fallback if no project_id is known yet.

Input parameters:

- `codebase_context` (string): Surrounding code snippet for context
- `project_id` (string): project_id from .thedesignagent file
- `project_model` (object): Project model. Send ONLY on first call (no project_id yet) OR when a prior response returned _meta.tda_status="setup_required" or "model_stale". Do NOT resend on routine subsequent calls — it is cach…
- `repo_hash` (string): SHA256 of git remote origin URL
- `schema_hash` (string): SHA256 of schema/type files — triggers model refresh if stale
- `skills` (array): Per-call skill selection (overrides project defaults)
- `task` (string, required): Describe the screen you're about to build

Output parameters:

- `project_id` (string): Persist in .thedesignagent and send on later calls
- `retry_ok` (boolean): Whether the same call can safely be retried
- `score` (number): Overall 0–10 score (Ux and Visual)
- `status` (string): healthy | degraded:stage3 | degraded:other | setup_required | model_stale | local_install_required | login_required | auth_failed | insufficient_credits | rate_limited | pipeline_error

### `Ux` (~254 tokens)

UX review

Evaluate a built UI artifact for JTBD fit, heuristic compliance, cognitive load, and pattern conformance.

Call this AFTER building a screen. TheDesignAgent scores:
\- Heuristics: violations against Nielsen's heuristics + project-specific anti-patterns
\- Cognitive: load profile against the stored persona
\- Patterns: conformance to established project pattern decisions
\- JTBD fit: does the artifact serve the resolved job?

Returns ux_score (0–10) + findings + prioritised recommendations.

Stores new anti-patterns to project context — future builds benefit automatically.

Input parameters:

- `artifact` (string, required): The UI description or component code to evaluate
- `codebase_context` (string): Optional surrounding code context
- `project_id` (string): project_id from .thedesignagent file in project root
- `repo_hash` (string): SHA256 of git remote origin URL (fallback if no .thedesignagent)
- `route` (string): URL path of the page under review, e.g. /orders. Reviews judge it against that page's own job.
- `stages` (array): Run only named stages (omit to run all)
- `task` (string, required): Describe the workflow or screen you're building

Output parameters:

- `project_id` (string): Persist in .thedesignagent and send on later calls
- `retry_ok` (boolean): Whether the same call can safely be retried
- `score` (number): Overall 0–10 score (Ux and Visual)
- `status` (string): healthy | degraded:stage3 | degraded:other | setup_required | model_stale | local_install_required | login_required | auth_failed | insufficient_credits | rate_limited | pipeline_error

### `Visual` (~235 tokens)

Visual review

Evaluate a built UI artifact for visual design quality — brand compliance, visual cognitive load, and aesthetic quality.

Pass render_url to review a real screenshot. This hosted server screenshots public pages and preview deploys (pass vercel_bypass_token for a protected Vercel preview). It cannot reach localhost or private networks: for those, it returns instructions for the local MCP server. With no render_url, the review runs from the artifact code alone.

If the page redirects to login, no review runs and nothing is charged.

Input parameters:

- `artifact` (string, required): The UI description or component code to evaluate
- `project_id` (string): project_id from .thedesignagent file in project root
- `render_url` (string): Public or preview URL to screenshot, e.g. https://my-app-git-feature.vercel.app/checkout
- `repo_hash` (string): SHA256 of git remote origin URL
- `task` (string, required): Describe the workflow or screen you're building
- `vercel_bypass_token` (string): Optional. Vercel 'Protection Bypass for Automation' secret, for a protected preview deploy.

Output parameters:

- `project_id` (string): Persist in .thedesignagent and send on later calls
- `retry_ok` (boolean): Whether the same call can safely be retried
- `score` (number): Overall 0–10 score (Ux and Visual)
- `status` (string): healthy | degraded:stage3 | degraded:other | setup_required | model_stale | local_install_required | login_required | auth_failed | insufficient_credits | rate_limited | pipeline_error

## Diagnostics

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

## Score history

- 2026-10-24: 38
- 2026-10-23: 38
- 2026-10-22: 38
- 2026-10-21: 38
- 2026-10-20: 38
- 2026-10-19: 38
- 2026-10-18: 38
- 2026-10-17: 38
- 2026-10-16: 38
- 2026-10-15: 38
- 2026-10-14: 38
- 2026-10-13: 38
- 2026-10-12: 38
- 2026-10-10: 38
- 2026-10-08: 38
- 2026-10-05: 72
- 2026-10-04: 71
- 2026-10-03: 61

## Common questions

### What is the TheDesignAgent MCP server?

TheDesignAgent is an MCP server listed in the public MCP registry as ai.thedesignagent/mcp. A design agent in your coding agent's loop: briefs each screen, reviews UX and visual quality. This page covers its hosted endpoint (https://www.thedesignagent.ai/mcp).

### Is the TheDesignAgent MCP server safe to use?

TheDesignAgent scores 38 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 TheDesignAgent MCP server expose?

TheDesignAgent exposes 3 tools: Discover, Ux, Visual. Their descriptions and schemas cost roughly 890 tokens of context every time the server is loaded.

### Does the TheDesignAgent MCP server require authentication?

Yes. TheDesignAgent asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

### Is the TheDesignAgent MCP server still maintained?

TheDesignAgent is still listed as active in the MCP registry. We last reached this channel on 24 October 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://www.thedesignagent.ai/mcp
- Website: https://www.thedesignagent.ai/
- Changelog RSS feed: https://verifymcp.io/servers/ai-thedesignagent-mcp/www.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-thedesignagent-mcp/www.json
- HTML version of this page: https://verifymcp.io/servers/ai-thedesignagent-mcp/www