taste-mcp
MCP server that indexes and serves design skills, guides, and patterns from the taste-skill library, enabling structured retrieval and workflow prompts for design, redesign, and image generation.
README
taste-mcp
Production-grade MCP server for the taste-skill skill library.
Instead of manually pasting SKILL.md files into an LLM context, taste-mcp turns the repository into a structured MCP server with:
- Resources for skills, sections, guides, templates, and pattern vocabulary
- Prompts for design, redesign, image-generation, and Stitch workflows
- Tools for discovery, search, brief analysis, and compact context composition
- Modern MCP transport via Streamable HTTP
- Local stdio support for spawn-based MCP clients
What It Solves
The original taste-skill repo is a high-value prompt corpus, but it is optimized for manual or semi-manual loading:
- copy
SKILL.mdinto chat - install one skill at a time with
npx skills add - rely on the agent to discover the right markdown itself
taste-mcp removes that friction by indexing the repository once and exposing only the relevant parts to MCP clients on demand.
Features
- Indexes
skills/*/SKILL.mdinto a normalized in-memory catalog - Uses canonical skill IDs from frontmatter
name, not folder names - Resolves aliases from:
README.mdskills/llms.txtskill.sh
- Splits large skills into section resources for targeted retrieval
- Extracts the taste-skill pattern vocabulary as searchable MCP resources
- Includes secondary guides:
CHANGELOG.mdresearch/**.github/copilot-instructions.md.claude-plugin/*.jsonskills/stitch-skill/DESIGN.md
- Supports compact retrieval so clients do not receive the entire repository by default
- Ships with tests, Dockerfile, and CI workflow
MCP Surface
Resources
catalog://skillscatalog://guidescatalog://patternsskill://<skill-id>skill://<skill-id>/section/<section-slug>pattern://<pattern-id>guide://<guide-id>
Prompts
design-tastefrontend-reviewlanding-page-contextimage-generation-contextstitch-design-system
Tools
list_skillsget_skillsearch_contentrecommend_skillsreview_briefcompose_contextlist_patternsget_pattern
Project Structure
src/
app/ config, logger, bootstrap
bin/ http and stdio entrypoints
content/ loader, indexer, search, retrieval
domain/ shared domain types
lib/ markdown and text helpers
mcp/ MCP resource/tool/prompt registration
transport/ Streamable HTTP transport wiring
test/
indexer.test.ts
retrieval.test.ts
http.test.ts
Requirements
- Node.js 20.11+
- npm
Installation
npm install --no-package-lock
Development
Run the HTTP server in watch mode:
npm run dev:http
Run the stdio server in watch mode:
npm run dev:stdio
Build
npm run build
Test
npm test
Run
Streamable HTTP
npm run start:http
Default endpoints:
- MCP:
http://127.0.0.1:3000/mcp - Health:
http://127.0.0.1:3000/healthz
stdio
npm run start:stdio
Environment Variables
Copy .env.example if needed.
Available configuration:
REPOSITORY_ROOTMCP_HOSTMCP_PORTMCP_ENDPOINTLOG_LEVELMAX_CONTEXT_CHARSMAX_SEARCH_RESULTSSESSION_TTL_MS
Defaults are tuned for local use and deployment simplicity.
Example Tool Calls
Review a brief
{
"brief": "Redesign my existing SaaS landing page without changing the stack. Keep it calm and premium.",
"target": "auto"
}
Compose compact context
{
"brief": "Create a premium 8-section fintech landing page with strong proof and restrained motion.",
"target": "web-implementation",
"maxChars": 12000,
"includePatterns": true,
"includeGuides": true,
"includeChecklists": true
}
Recommend skills
{
"brief": "Generate a 5-screen onboarding flow for a fitness app inside clean iPhone mockups.",
"target": "auto"
}
Deployment
Docker
Build:
docker build -t taste-mcp .
Run:
docker run --rm -p 3000:3000 taste-mcp
GitHub Actions
CI is included at .github/workflows/ci.yml.
It runs:
npm run buildnpm test
Design Notes
Why Streamable HTTP
This server uses modern MCP Streamable HTTP instead of legacy HTTP+SSE transport.
Reasons:
- it is the current recommended MCP transport for remote servers
- it supports the standard POST/GET/DELETE session model
- it works cleanly with modern MCP clients
- SSE remains available internally as part of Streamable HTTP where needed, without implementing the deprecated legacy transport
Why stable SDK v1
The implementation uses the latest stable production SDK:
@modelcontextprotocol/sdk@^1.29.0
This keeps the server deployable today while still using Streamable HTTP and the current production MCP feature set.
Important Limitation
The original taste-skill repository defines a future block-library contract, but it does not yet ship an actual blocks/ corpus.
Because of that:
taste-mcpexposes pattern vocabulary today- it does not fake a
get_blockimplementation for non-existent block files
Roadmap
- Semantic search with embeddings
- Vector retrieval for sections and patterns
- Persisted index snapshots for faster startup
- Optional auth for public HTTP deployments
- File watching / hot reload in development
- Multi-repository support
- Real block resources when the upstream repo adds concrete block files
Source Lineage
This project is built on top of the upstream content repository:
- Upstream corpus:
Leonxlnx/taste-skill - This repo: MCP packaging, indexing, retrieval, transport, tests, and deployment support
License
The original content repository is MIT-licensed. Review upstream licensing and attribution requirements if you publish derived distributions.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。