footon
Turns Claude and Codex JSONL transcripts into sanitized, unlisted links with explicit approval, exposing share management via OAuth-protected MCP endpoints.
README
footon
footon turns Claude and Codex JSONL transcripts into sanitized, unlisted links. Raw transcripts remain local. Only user and assistant prose from an explicitly approved draft can be published.
raw JSONL -> Rust draft + local scanners -> explicit approval -> Cloudflare edge rescan -> unlisted link
The remote MCP endpoint is https://footon.dev/mcp. It uses OAuth 2.1 with
passwordless email sign-in and exposes only share_create, share_list, and
share_revoke.
CLI
cargo install --git https://github.com/douglance/footon footon
footon draft thread.jsonl --title "Public title" --output footon-draft.json
FOOTON_TOKEN=... footon publish footon-draft.json
Drafting makes no network request. Publishing is a separate command and refuses plain HTTP except for localhost tests. See cli/README.md for the full contract.
Development
npm install
npm run check
npm run test:e2e
cargo fmt --check
cargo test
npm run check runs strict TypeScript and Rust linting. The Worker limits
complexity to 8, functions to 45 lines, and files to 220 lines. The Rust crate
denies Clippy all, pedantic, cognitive complexity, large functions,
warnings, and unsafe code across the workspace, all targets, and all features.
The Worker E2E uses Cloudflare's local test harness with isolated D1, KV, and simulated email. It covers dynamic client registration, PKCE authorization, Turnstile's localhost boundary, email capture, magic-link verification, consent without a session cookie, token exchange, and authenticated MCP create, list, and revoke calls. It never sends a real email or writes production data.
Safety boundary
The official CLI combines redact-core with independent credential, key,
connection-string, path, and metadata removal. The Worker validates the exact
footon.share.v2 shape and rejects remaining high-signal secrets and personal
data. No scanner can prove arbitrary text is secret-free, so explicit local
review remains mandatory.
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。