Apache-2.0 的模型無關 MCP 伺服器，向 DeepSeek Harness 以 MCP 用戶端方式提供 18 個編碼工具（檔案、修補、執行、git）——每台伺服器一個工作區，由權限模式控管。
DSH 整合
相容
作者聲明
安全稽核
未稽核
最後核實
2026-08-21
授權條款
Apache-2.0
01它能幫你完成什麼？
Turn a DeepSeek Harness chat into a coding agent with real repository access
File reading and search, structured multi-file patches, command execution, interactive sessions and git operations — all confined to one workspace
Developers who want to give an existing chat/agent subscription real repo access without an extra product
Let an agent work on untrusted code inside a disposable sandbox
A containerized Docker server with toolchains and caches preconfigured, bounded to one workspace and gated by permission modes
Engineers reviewing sketchy PRs or running genuinely untrusted workloads safely
Code on your own machine from anywhere via an authenticated tunnel
Loopback-bound server exposed over an authenticated HTTPS tunnel (cloudflared / ngrok / Microsoft Dev Tunnel) with bearer tokens and OAuth 2.1 + PKCE
Developers who want to drive their home workstation from a phone or another device
02如何將外掛接入 DeepSeek Harness？
先決條件
- Python ≥ 3.11 (the server is published on PyPI), or a Node toolchain to use the npm launcher
- An MCP client (e.g. DeepSeek Harness) able to consume the standard mcpServers JSON config
安裝步驟
- 01
Start the server with the Python toolchain: `uvx coding-tools-mcp --stdio --workspace /path/to/repo`
- 02
Or with the Node toolchain: `npx coding-tools-mcp --stdio --workspace /path/to/repo` (a thin launcher that starts it via `uv` or `pipx`)
$ npx coding-tools-mcp --stdio --workspace /path/to/repo
- 03
Add the MCP client config: `{ "mcpServers": { "coding-tools": { "command": "uvx", "args": ["coding-tools-mcp", "--stdio", "--workspace", "/path/to/repo"] } } }`
- 04
Optional HTTP: drop `--stdio` and the server speaks Streamable HTTP on `http://127.0.0.1:8765/mcp`
驗證整合成功
作者未說明
03DSH 整合程度與能力邊界
Model-neutral MCP server (stdio or Streamable HTTP) that DeepSeek Harness drives as an MCP client to get coding tools
File & search tools with atomic patching
a single workspace root→read_file · list_dir · list_files · search_text · apply_patch · view_image
apply_patch writes files — it is the sole file-mutation primitive, staged, baseline-checked, atomic across files, with rollbackCommand execution with interactive sessions
workspace-bound commands→exec_command · write_stdin · read_output · kill_command · request_permissions, with PTY REPL/debugger support
runs shell commands with workspace-bound cwd, scrubbed environment, timeouts and output caps; network/shell-expansion gated by permission modesGit inspection tools
the workspace repository→git_status · git_diff · git_log · git_show · git_blame
Safety boundary with permission modes
a chosen mode — safe (default) / trusted / dangerous→command policy gating network access, shell expansion, inline scripts and destructive commands; path boundaries enforced
sends anonymous usage telemetry by default (disable with CODING_TOOLS_MCP_TELEMETRY=off or DO_NOT_TRACK=1)
04適合誰？何時不該用？
適合
- Developers who want to give an existing chat/agent subscription real repo access without an extra product
- Engineers reviewing sketchy PRs or running genuinely untrusted workloads safely
- Developers who want to drive their home workstation from a phone or another device
不適合
- The safety boundary is not a complete OS sandbox. On Linux, Landlock adds kernel-level filesystem confinement, but other platforms only get an explicit warning — use the Docker image or a VM for genuinely untrusted work.
05相容性、維護與安全提醒
- The safety boundary is not a complete OS sandbox. On Linux, Landlock adds kernel-level filesystem confinement, but other platforms only get an explicit warning — use the Docker image or a VM for genuinely untrusted work.
- Requires Python ≥ 3.11 at runtime; the npm package is only a launcher that starts the Python server via uv or pipx, so a Python toolchain (or one it installs) is still needed.
- The server sends anonymous usage telemetry (per-tool success/latency counters and version/platform dimensions — never paths, arguments, commands or file contents) unless disabled.
Apache-2.0 · actively maintained (latest release v0.3.0, 2026-08-13)
06常見問題
DeepSeek Harness 如何接入 Coding Tools MCP？
以 MCP 用戶端方式接入。用 `uvx coding-tools-mcp --stdio --workspace /path/to/repo`（或 `npx`）啟動伺服器，然後在用戶端設定裡加上標準的 mcpServers JSON 區塊。任何 MCP 用戶端——包括 DeepSeek Harness——都能取得相同的 18 個工具。
這是原生整合還是 MCP？
是 MCP。它是一個模型無關的 MCP 伺服器，透過 stdio 或 Streamable HTTP 提供服務；DeepSeek Harness 像驅動其他 MCP 用戶端一樣驅動它，並沒有 dsh 專屬的原生執行環境。
執行它需要什麼？
來自 PyPI 的 Python ≥ 3.11（透過 uvx/pipx），或用 npm 啟動器經 uv 或 pipx 拉起。若要用 HTTP，去掉 --stdio，它會監聽 http://127.0.0.1:8765/mcp。
它是如何沙箱化的，有什麼限制？
每台伺服器一個工作區根目錄；拒絕絕對路徑、.. 目錄穿越和符號連結逃逸，權限模式控管網路、shell 展開、內嵌腳本和破壞性指令。在 Linux 上，Landlock 提供核心級檔案系統隔離。它不是完整的作業系統沙箱，處理不可信程式碼請用 Docker 或虛擬機器。
它會把我的資料傳到別處嗎？
只有匿名使用遙測（每個工具的成功率/延遲計數，以及版本/平台維度——絕不包含路徑、指令或檔案內容）。用 CODING_TOOLS_MCP_TELEMETRY=off 或 DO_NOT_TRACK=1 關閉；在 CI 中預設關閉。
07相關的 DSH 工作流程
ruflo
作者 ruvnet
原版智慧體元框架（meta-harness）：支援多智慧體叢集部署、自主工作流編排與對話式 AI 系統構建，內建自適應記憶、自學習智慧與 RAG 檢索，原生整合 Claude Code / Codex / Hermes 等大量工具。
app
作者 reactive-resume
隱私優先的開源簡歷製作外掛，支援自定義、便攜部署和永久免費使用，適合直接生成並管理求職簡歷。
everos
作者 evermind-ai
為所有 AI 智慧體提供的便攜統一記憶層，本地優先、Markdown 原生、資料歸使用者所有，跨應用與工作流自進化。
yao
作者 yaoapp
在桌面、移動端、瀏覽器或 API 上統一管理你的智慧體與工作區，看板式任務追蹤，支援自託管。
08資料與來源
file reading and search, structured multi-file patches, command execution, interactive sessions, and git — one server th…
Wire it into Claude Desktop, Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, or Cline — the JSON is the same…
此頁面根據專案公開文件、儲存庫中繼資料與 DSH Plugins 的結構化解析所產生；最後核實於 2026-08-21。發現錯誤？提交更正。
最佳 DeepSeek Harness 外掛
從全目錄挑出的 12 個值得優先安裝的外掛，涵蓋各個分類。