# dev.brandpilot/brandpilot-mcp (npm · brandpilot-mcp)

BrandPilot design systems for coding agents: tokens, design handoff bundle, prompt pack, import.

- Trust score: 69/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-17

## Components

- remote · `brandpilot.dev`: 36/100, [markdown](https://verifymcp.io/servers/dev-brandpilot-brandpilot-mcp/api-mcp.md), [page](https://verifymcp.io/servers/dev-brandpilot-brandpilot-mcp/api-mcp)
- npm · `brandpilot-mcp`: 69/100 (this document), [markdown](https://verifymcp.io/servers/dev-brandpilot-brandpilot-mcp/brandpilot-mcp.md), [page](https://verifymcp.io/servers/dev-brandpilot-brandpilot-mcp/brandpilot-mcp)

## Channel facts

- Registry: `npm`
- Package: `brandpilot-mcp`
- Version: `0.3.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, 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 2026-10-17.

- **Supply Chain Security**: 98/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 31 of 93 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 3 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 72/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 973 tokens (~121/item across 8 items; 8 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 95/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 86% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 8 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 8 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.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the dev.brandpilot/brandpilot-mcp server?

dev.brandpilot/brandpilot-mcp runs locally as an npm package, launched with npx -y brandpilot-mcp. 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 dev-brandpilot-brandpilot-mcp -- npx -y brandpilot-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "dev-brandpilot-brandpilot-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "brandpilot-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "dev-brandpilot-brandpilot-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "brandpilot-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add dev-brandpilot-brandpilot-mcp -- npx -y brandpilot-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "dev-brandpilot-brandpilot-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "brandpilot-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add dev-brandpilot-brandpilot-mcp --command npx --arg -y --arg brandpilot-mcp
```

### Hermes

```yaml
mcp_servers:
  dev-brandpilot-brandpilot-mcp:
    command: "npx"
    args: ["-y", "brandpilot-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "dev-brandpilot-brandpilot-mcp": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "brandpilot-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add dev-brandpilot-brandpilot-mcp -t stdio -c npx -a -y brandpilot-mcp
```

### Other

```json
{
  "mcpServers": {
    "dev-brandpilot-brandpilot-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "brandpilot-mcp"
      ]
    }
  }
}
```

## 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.

### 2026-10-14 (score 69, +31)

- [security improvement] Injection markers: unverified → pass
- [security] First check of Judged manipulation: pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] MCP protocol: unverified → pass
- [functional] First check of Schema quality: fail
- [functional] First check of Destructive annotations: pass
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: good
- [functional] First check of Tool coverage: 86
- [functional] Package version: 0.3.0 → 0.3.1

### 2026-10-13 (score 38)

First indexed and scored.

## MCP tools (8)

### `list_systems` (~32 tokens)

List the public design systems in the BrandPilot pool (name, slug, brand color, token count, status).

### `get_system_adoption` (~55 tokens)

Full adoption manifest for a public system: tokens, components, pages, brand asset URLs and the binding design-direction block.

Input parameters:

- `name` (string, required): System name, public slug or alias (e.g. "launchwp")

### `get_system_tokens` (~118 tokens)

Export a public system's tokens in one format: globals-css, colors-ts, spacing-ts, typography-ts, tailwind-theme or brand-manifest. Calls the legacy /api/systems/export endpoint, not a v1 path - the export route has no v1 equivalent yet.

Input parameters:

- `format` (string): One of globals-css, colors-ts, spacing-ts, typography-ts, tailwind-theme, brand-manifest (default globals-css)
- `name` (string, required): System name, public slug or alias (e.g. "launchwp")

### `get_agent_prompt` (~62 tokens)

Markdown onboarding doc for a public system: the two copy-paste prompts an external AI coding agent uses to bootstrap a design package and sync it to Claude Design.

Input parameters:

- `name` (string, required): System name, public slug or alias (e.g. "launchwp")

### `get_design_handoff` (~117 tokens)

The design's continuation bundle as JSON: brief, tokens, board digest, the continuation contract (hard floor first, then the latitude level), live inventory, coherence audit and the import contract. Available mid-flow (project paused at EXTERNAL_DESIGN) and post-completion.

Input parameters:

- `designId` (string, required): The Design id (cuid) - shown on the design page URL and in the continuation card
- `handoffKey` (string): Design handoff key; falls back to the DESIGNFLOW_HANDOFF_KEY environment variable

### `get_design_prompt_pack` (~290 tokens)

The app-authored sequential Claude Design prompt pack (markdown): anchor sheet first, then template-aware component sheets and page prompts, each embedding the latitude contract in force. Regenerated from live data on every call. Without pass it returns the v1 pack; pass=explore then pass=lock with the chosen direction return the v2 two-pass pack, and format=copy-map returns the copy map the v2 pack lists as a project file.

Input parameters:

- `designId` (string, required): The Design id (cuid) - shown on the design page URL and in the continuation card
- `direction` (string): The direction chosen from the explore pass, max 2000 characters. Required with pass "lock"; only valid with a pass
- `format` (string): markdown (default), json for the structured pack, or copy-map for the copy map the v2 pack lists as a project file
- `handoffKey` (string): Design handoff key; falls back to the DESIGNFLOW_HANDOFF_KEY environment variable
- `pass` (string): v2 pass: "explore" asks for 2-3 directions per surface, "lock" builds every surface in the chosen direction (needs direction). Omit for the v1 pack
- `with3d` (boolean): Add one 3D Objects prompt to a v2 pack (only valid with a pass)

### `import_design_artifacts` (~177 tokens)

Import externally designed work back into BrandPilot. Rows land as DRAFT on the carrier project's Deliverables tab for human review - nothing auto-approves. Components: self-contained HTML with inline styles. Pages: standalone HTML documents. Assets: PNG (base64 or URL) with optional sourceCode.

Input parameters:

- `assets` (array)
- `components` (array)
- `designId` (string, required): The Design id (cuid) - shown on the design page URL and in the continuation card
- `handoffKey` (string): Design handoff key; falls back to DESIGNFLOW_HANDOFF_KEY
- `pages` (array)
- `source` (string): Producer label for the Pending review queue: "harness" when archiving from an external build harness onto a harness carrier (default external-design-late)

### `finish_external_design` (~122 tokens)

Validates that components and pages were imported, optionally accepts every pending imported draft, then resumes the pipeline at the coherence audit toward Design Review. Only valid while the project is paused at EXTERNAL_DESIGN.

Input parameters:

- `acceptAll` (boolean): Accept all pending external-import drafts in one stroke (default false)
- `designId` (string, required): The Design id (cuid) - shown on the design page URL and in the continuation card
- `handoffKey` (string): Design handoff key; falls back to the DESIGNFLOW_HANDOFF_KEY environment variable

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/dev-brandpilot-brandpilot-mcp/brandpilot-mcp#diagnostics

## Score history

- 2026-10-17: 69
- 2026-10-16: 69
- 2026-10-15: 69
- 2026-10-14: 69
- 2026-10-13: 38

## Common questions

### What is the dev.brandpilot/brandpilot-mcp server?

dev.brandpilot/brandpilot-mcp is listed in the public MCP registry as dev.brandpilot/brandpilot-mcp. BrandPilot design systems for coding agents: tokens, design handoff bundle, prompt pack, import. This page covers its npm package (brandpilot-mcp).

### Is the dev.brandpilot/brandpilot-mcp server safe to use?

dev.brandpilot/brandpilot-mcp scores 69 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 17 October 2026. It declares no install or post-install scripts. 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 dev.brandpilot/brandpilot-mcp server expose?

dev.brandpilot/brandpilot-mcp exposes 8 tools: list_systems, get_system_adoption, get_system_tokens, get_agent_prompt, get_design_handoff, and 3 more. Their descriptions and schemas cost roughly 973 tokens of context every time the server is loaded.

### Is the dev.brandpilot/brandpilot-mcp server still maintained?

dev.brandpilot/brandpilot-mcp is still listed as active in the MCP registry. We last reached this channel on 17 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the dev.brandpilot/brandpilot-mcp server under?

dev.brandpilot/brandpilot-mcp declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/brandpilot-mcp
- Socket report: https://socket.dev/npm/package/brandpilot-mcp
- Repository: https://github.com/aquaminh/brandpilot-mcp
- Website: https://brandpilot.dev/docs
- Changelog RSS feed: https://verifymcp.io/servers/dev-brandpilot-brandpilot-mcp/brandpilot-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/dev-brandpilot-brandpilot-mcp/brandpilot-mcp.json
- HTML version of this page: https://verifymcp.io/servers/dev-brandpilot-brandpilot-mcp/brandpilot-mcp