carry
Enables syncing a context pack between Claude Code and Claude mobile via a remote MCP server, allowing users to push instructions from their repo and read them on mobile.
README
carry
Carry a context pack between your Claude surfaces. Push your voice rules, system facts, or style guide from Claude Code at your desk; read them from Claude mobile on the go. One small remote MCP server, always live, no manual re-sync.
carry exists because there is no public API to write Claude Project knowledge, so keeping your mobile Claude in sync with the instructions you maintain in a repo means either re-uploading files by hand (which drifts the moment you do) or this: a server both surfaces attach to, holding one current pack per namespace.
Claude Code (your repo) Claude mobile app
compiles + pushes the pack connector attached once via web
│ │
│ push_context (write token) │ get_context (read token)
▼ ▼
┌─────────────────────────────────────────────────────┐
│ carry — the current pack for your namespace │
└─────────────────────────────────────────────────────┘
Because Claude mobile can use remote MCP connectors (you add the URL once on claude.ai web; it syncs to your phone), your phone reads the live pack every time you draft. Update the pack from your desk, and mobile has it on the next call.
Status
Early. Slices 1 and 2 are done and verified: a runnable, auth-gated MCP server
(Slice 1, in-memory store) now backed by durable libSQL storage that survives a
restart (Slice 2). See docs/build-plan.md for what is built
and what is next.
What it exposes (MCP)
get_context— return the current pack for your namespace. Read this before drafting.push_context— replace the pack. Requires a write token.carry://context— the same pack as an MCP resource.
Auth model
A namespace owns two secrets: a read token (what your mobile connector presents) and a write token (what Claude Code / CI presents to push). They must differ, so a leaked read connector can never overwrite your pack. The token is the namespace: the model never supplies one, so it cannot touch anyone else's pack.
Run locally
npm install
cp .env.example .env # then set CARRY_NAMESPACES with your own tokens
npm run dev # starts on :8080
Verify:
npm run smoke # storage + auth cores, no network
npm run typecheck
# end-to-end (server must be running): CARRY_URL, then tsx scripts/http-smoke.ts
Roadmap
A carry CLI + pack compiler (repo files → stamped pack), a Render one-click
Blueprint, and optional multi-tenant signup. Tracked in
docs/build-plan.md.
License
Apache-2.0.
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。