declaude

io.github.tenkenco由 GitHub 账号 tenkenco 发布v1.0.0更新于 Oct 24, 2026

Rewrites Claude-English into plain English, preserving meaning, code and structure.

已验证Streamable HTTP可网页运行效率与工作流AI 与机器学习

概览

AI 生成的概览

把冗长、奉承式的 Claude 风格回复改写成平实英文,同时保留原意、代码和结构。

可以做什么
这是一个远程 MCP 服务器,用于去除文本中的奉承式开场、空洞的溢美之词和含糊的填充语。它提供 translate 和 usage 两个工具,也可通过 Claude Code 钩子、REST API、兼容 OpenAI 的接口或文档上传页面使用。README 称改写由自托管的开源模型完成,且模型服务器已关闭提示日志记录。
适用场景
当你希望把助手输出或文档改写成直接、平实的英文,且不丢失代码和结构,并愿意把这些文本发送给第三方服务时适用。
运行要求
通过 streamable HTTP 连接 speak-english.tenken.co 远程端点。需要客户端通过 OAuth 登录;使用 MCP 服务器时无需粘贴 API 密钥。若走 Claude Code 插件方式,则会配置一个 dk_ 密钥。有免费额度,含每月翻译和文档次数限制;付费方案需要绑定银行卡。
安装前请注意
提交的文本会发送到服务商服务器处理,请勿发送机密材料。付费方案每月 5 美元且需要银行卡。插件会把 dk_ API 密钥存入 Claude Code 插件配置,一旦存在密钥,钩子会自动改写回复。

安装

在 SourceWeft 中

  1. 打开 控制台中的 declaude,将其添加到工作区。
  2. 连接 所需的 凭据。它们会被私密存储,绝不会在公开页面上展示。
  3. 为需要使用其工具的对话启用该服务。

Web executable,通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体,或 SourceWeft 对话中。智能体会读取该服务器的安装指南,先向你展示发布者、端点和登录方式,经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/io.github.tenkenco%2Fdeclaude/install.md,并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前,先告诉我它的发布者、端点和登录方式,等我确认。不要把 API 密钥写进命令或我会提交的文件;问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。 客户端会在首次连接时完成 OAuth 登录。

{
  "mcpServers": {
    "declaude": {
      "type": "http",
      "url": "https://speak-english.tenken.co/mcp"
    }
  }
}

README

declaude

Claude-English → plain English, as a service.
Strips sycophantic openers, hollow superlatives and hedging filler.
Meaning, code and structure survive intact.

[CI] [Security] [Daily checks] [Coverage]

[MCP registry] [Live] [License] [Python]


Before  "Great question! Before I answer, let me make sure I understand what        you're asking. You want to know why the build is failing. Let me walk        through my thinking, and then I'll give you the answer."
After   "I understand you want to know why the build is failing. Here's what        I think is happening."
Before  "One thing I didn't touch, but you won't want to leave hanging, is the        migration script. I'd be happy to walk you through it whenever you're        ready!"
After   "One thing I didn't cover is the migration script. When you're ready,        I can go through it with you."

Runs on an open-source model (Qwen2.5-14B-AWQ) on our own L4 GPUs, so your text never reaches a commercial AI provider. Prompt logging is disabled at the model server: text is processed in memory and discarded, never written to disk, a database, or logs.

Live: speak-english.tenken.co · Get an API key · Translate a document

Free$5 / month
Translations100 / monthUnlimited
Documents5 / month, 200 KB500 / month, 2 MB
Card requiredNoYes

Quick start

In Claude Code, install the plugin. It brings the skill and registers the hook:

/plugin marketplace add tenkenco/declaude/plugin install declaude@tenken

Then run /declaude:setup. It safely migrates any manual hook and configures a dk_ key. Claude Code stores the key in secure plugin configuration. The hook rewrites replies as soon as a key exists. Set the hook_enabled option to false to stop it. The hook stays silent without a key, and it never blocks a session.

For the MCP server on its own, in Claude Code or any other MCP client:

bash
claude mcp add --transport http declaude https://speak-english.tenken.co/mcp

No API key to paste: your client discovers OAuth, opens a browser sign-in, and holds the token. That is the whole setup.

SurfaceUse it forDocs
MCP serverClaude Code, Cursor, any MCP client. Tools: translate, usageskill
Claude Code hookRewrites replies as they render, costs zero Claude tokens. The plugin registers ithook/
DocumentsDrop a .md/.txt, get it back rewrittenweb
REST APIPOST /v1/translate, /v1/documents, /v1/usageskill
OpenAI-compatiblePOST /v1/chat/completions — point any OpenAI client at /v1skill

Full usage, authentication and quota behaviour live in skills/declaude/SKILL.md — installable as an agent skill, so your agent can read it directly.

Architecture

client ── API key / OAuth / Clerk JWT ──> Cloud Run gateway ── VPC ──> internal LB ──> vLLM GPU MIG                                              │                                    (Qwen2.5-14B, spot L4)                                              ├─> Firestore (usage, paid flags, key hashes)                                              └─> Stripe (payment link + signed webhooks)
  • gateway/ — FastAPI. Every boundary is injectable, which is why the suite runs without network, GPU or cloud credentials.
  • infra/ — Terraform, state in GCS, plan converges to zero diff. The GPU tier is private-IP spot instances behind an internal L7 load balancer.
  • hook/ — Claude Code hook client. Fails open; never blocks a session.
  • hooks/ — hooks.json, the plugin registration Claude Code reads on install.
  • CI — lint, tests and coverage on every PR; security scans and a production smoke test daily.
Operating notes
  • /healthz is reserved by Google Frontend on run.app — use /health.
  • Model swaps are one Terraform variable; 32B needs 2×L4 (quota bump), 14B fits one L4.
  • MIG template rollouts are deliberate (OPPORTUNISTIC): a proactive policy turned benign template edits into surprise 15-minute outages.
  • Secrets live in Secret Manager only. API keys are stored as SHA-256 digests, so a database leak yields no usable credential.
  • Prompt logging is disabled at the model server; request text is processed in memory and discarded.
  • Developed test-first. Every production defect found while dogfooding became a regression test before its fix.

Development

bash
cd gatewayuv sync --devuv run pytest -q          # 197 testsuv run ruff check .

Credit

Grew out of gvzdv/claudish-to-english, the original local-Ollama hook. Licensed MIT; upstream notice in THIRD_PARTY_LICENSES.md.

来源:README.md,提交 68ae4d9

工具

0
该服务器需要登录,因此 SourceWeft 无法在没有账号的情况下读取其工具,也未收录。已连接账号所能看到的内容可能因账号及其权限而异。

版本历史

1
  1. v1.0.0最新Sep 16, 2026

评分

已满足适用检查项的 85%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 已列出工具15 分

    请让服务器在无凭据时响应 tools/list,或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分