@crewone/mcp-server
MCP server for CrewOne that enables AI agents to query Taiwan film equipment rates, studio rentals, and photographer/director style references, and optionally generate full pre-production packages with an API key.
README
@crewone/mcp-server
MCP (Model Context Protocol) server for CrewOne. Lets Claude Desktop, Cursor, Continue, Cline, and any other MCP-aware AI agent query Taiwan film equipment rates, studio rentals, photographer style references, MV/commercial director references, and (with API key) generate full pre-production packages.
What is this
CrewOne maintains a structured database of:
- 1,187 real Taipei film equipment rental rates (cameras, lenses, lighting, grip, sound)
- 561 real Taiwan studio rates with size, ceiling, lighting, power, parking
- 69 commercial / fashion / portrait photographer style references with on-set lighting hallmarks and AI prompt tokens
- 30+ MV and commercial director style references with prompt tokens for video generation models
This MCP server exposes that data (and the generative pipeline) to AI agents. When you ask Claude Desktop "how much does an FX6 rent for in Taipei" or "give me a Tim Walker–style lighting setup", the agent calls this server, gets a real answer, and replies.
Two tiers of tools
Free (no API key required)
These work as soon as the server is installed. Rate-limited server-side.
search_equipment(query, category)— find Taipei rental ratessearch_studios(size_pings, max_budget_per_4h, amenities, location)— find Taiwan studiosget_photographer(name)— pull style reference for a specific photographerlist_photographers(region, cluster)— browse the 69-photographer libraryget_director(name)— director referencelist_directors(region, genre)— browse the director library
Paid (requires CREWONE_API_KEY)
These consume credits from your CrewOne plan.
create_project(brief, type, photographer_references?)— full package generation, 1 creditget_project(project_id)— fetch existing projectexport_pdf(project_id)— get PDF download URL
Get your API key at https://crewone.ai/dashboard/settings/api after signing up.
Install
Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) / %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"crewone": {
"command": "npx",
"args": ["-y", "@crewone/mcp-server"],
"env": {
"CREWONE_API_KEY": "your-key-here-or-omit-for-free-tools-only"
}
}
}
}
Restart Claude Desktop. CrewOne tools will appear in the tool palette.
Cursor
Add to ~/.cursor/mcp.json:
{
"mcpServers": {
"crewone": {
"command": "npx",
"args": ["-y", "@crewone/mcp-server"],
"env": { "CREWONE_API_KEY": "..." }
}
}
}
Continue
In ~/.continue/config.json, add to the experimental.modelContextProtocolServers array:
{
"transport": { "type": "stdio", "command": "npx", "args": ["-y", "@crewone/mcp-server"] },
"env": { "CREWONE_API_KEY": "..." }
}
Cline / any other MCP client
Same npx -y @crewone/mcp-server command pattern. Set CREWONE_API_KEY if you want paid tools.
Example prompts
After installing, try these in your AI chat:
Free tier
- "How much does a Sony FX6 rent for per day in Taipei?"
- "Find me a 8-ping studio in Taipei under NT$ 4,000 per 4 hours with cyc wall."
- "Give me Tim Walker's lighting hallmarks and AI prompt tokens for a fashion editorial shoot."
- "List all Japanese photographers in CrewOne's library that lean into surreal high-saturation."
Paid tier (needs API key)
- "Create a CrewOne project: 30-second commercial for a Taiwan coffee brand, hero shot pour, three location options."
- "Get my CrewOne project abc-123 and summarise the call sheet."
Configuration
| Env var | Default | Purpose |
|---|---|---|
CREWONE_API_KEY |
(none) | Required for paid tools. Generate at https://crewone.ai/dashboard/settings/api. |
CREWONE_API_BASE |
https://crewone.ai |
Override for local dev / staging. |
Privacy
The MCP server runs entirely on your local machine. Your prompts go from the AI client to this server (stdio) to crewone.ai HTTPS endpoints. CrewOne does not log MCP-originated requests differently from web requests. Free-tier tool calls are anonymous (no auth). Paid-tier calls are tied to your account via the API key.
Source
Open-source MIT, https://github.com/tzipway-dotcom/crewone-mcp-server
Pricing
CrewOne plans:
- Free trial: 2 generations
- Project Pack: $12 one-time, 1 credit
- Director: $24-29 / month, 4 credits / month
- Studio: $89-109 / month, 20 credits / month
- Founding Member: $15.84 / month lifetime (limited to first 25 sign-ups)
Free MCP tools (search_equipment, search_studios, get_photographer, etc.) do not consume credits. Only create_project and other generative tools do.
Troubleshooting
- Tools don't appear in Claude Desktop — verify
claude_desktop_config.jsonJSON is valid; restart Claude Desktop fully. Error: 401— API key invalid; regenerate at https://crewone.ai/dashboard/settings/api.Insufficient credits— top up via https://crewone.ai/pricing.- Free tools work but paid tools fail — confirm
CREWONE_API_KEYis set in theenvblock of your MCP config.
License
MIT — © Way Directs.
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。