Apache-2.0, model-neutral MCP server exposing 18 coding tools (files, patches, exec, git) to DeepSeek Harness as an MCP client — one workspace per server, gated by permission modes.
DSH integration
Compatible
Author-claimed
Safety audit
Unaudited
Last verified
2026-08-21
License
Apache-2.0
01What can it help you accomplish?
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
02How to install into DeepSeek Harness
Prerequisites
- 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
Installation steps
- 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`
Verify the integration
Not specified by the author
03DSH integration and capability boundaries
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)
04Who is it for? When not to use it?
Good for
- 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
Not for
- 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.
05Compatibility, maintenance and safety notes
- 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)
06Frequently asked questions
How does DeepSeek Harness connect to Coding Tools MCP?
As an MCP client. Start the server with `uvx coding-tools-mcp --stdio --workspace /path/to/repo` (or `npx`), then add the standard mcpServers JSON block to your client config. Any MCP client — including DeepSeek Harness — gets the same 18 tools.
Is this a native integration or MCP?
MCP. It's a model-neutral MCP server served over stdio or Streamable HTTP; DeepSeek Harness drives it like any other MCP client. There is no dsh-specific native runtime.
What do I need to run it?
Python ≥ 3.11 from PyPI (via uvx/pipx), or the npm launcher which starts it through uv or pipx. For HTTP, drop --stdio and it listens on http://127.0.0.1:8765/mcp.
How is it sandboxed, and what are the limits?
One workspace root per server; absolute paths, .. traversal and symlink escapes are rejected, and permission modes gate network, shell expansion, inline scripts and destructive commands. On Linux, Landlock adds kernel-level confinement. It is not a complete OS sandbox, so use Docker or a VM for untrusted code.
Does it send my data anywhere?
Only anonymous usage telemetry (per-tool success/latency counters and version/platform dimensions — never paths, commands or file contents). Disable it with CODING_TOOLS_MCP_TELEMETRY=off or DO_NOT_TRACK=1; it is off in CI.
07Related DSH workflows
ruflo
by ruvnet
🌊 The original agent meta-harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, RAG integration, and native Claude Code / Codex / Hermes and many more Integrated
reactive-resume
by amruthpillai
A one-of-a-kind resume builder that keeps your privacy in mind. Completely secure, customizable, portable, open-source and free forever. Try it out today!
everos
by evermind-ai
One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.
yao
by yaoapp
✨ All your agents and workspaces in one place, on every device you own. Track tasks on a board, accessible from desktop, mobile, browser, or API. Self-hosted.
08Data and sources
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…
This page is generated from the project’s public documentation, repository metadata and a structured parse of DSH Plugins; last verified on 2026-08-21. Found an error? Submit a correction.
Best DeepSeek Harness Plugins
Twelve plugins worth installing first — picked from the whole catalog, across every category.