
用DSH做MCP,让你的Claude代码或Codex等更快、更强大、更经济!
概览
代理编码工具之所以昂贵且速度慢,有一个原因:父型号是逐个读取文件。DSH-MCP则是——:批量读取、编辑和命令运行,价格为DeepSeek-V4-Flash速率,适用于你的机器。 长视野、多文件工作是代理工具耗费时间和金钱的地方:父模型会逐个文件进行处理——每个文件一次读取,探索循环,上下文不断增长和漂移。你支付父模型的每标记费率,等待模型串行完成。 一个调用delegate_to_dsh将整个令牌繁重的子任务交给一个新兴、专注的DeepSeek Harness代理,运行在你的工作区内。所有文件I/O都在那里完成——批量、本地、廉价。父文件保持在需要大脑的循环中:。
概述(AI 翻译)
快速且廉价——重度工作运行在deepseek-v4-flash上。
MCP特工的执行层——由本地DeepSeek线束驱动。
代理编码工具之所以昂贵且速度慢,只有一个原因:父模型
逐个读取文件。dsh-mcp 将它翻转——父代理保留
推理是本地的DeepSeek安全带承担了繁重的工作:批次读道,
编辑和命令运行,按 deepseek-v4-flash 速率定价,在你的机器上进行。
可支持任何MCP客户端·通过Claude代码端到端测试
** 🌐 英语 ·简体中文 ·日本語**
为什么:设计成快速又便宜
**痛苦。。长远、多档案的工作是精致工具流失资金的地方
以及时间:父模型会直接处理每个文件——每个Read一个
文件、探索循环、不断增长和漂移的上下文。你支付父母的费用
每个令牌的速率,等待模型完成
串贯。
修复。 一个调用 delegate_to_dsh 将整个标记重的子任务交给
一个新鲜、专注的DeepSeek安全带特工在内部运行着deepseek-v4-flash
你的工作区。所有文件的输入输出都在那里完成——批处理、本地化、廉价。这个
本页由 AI 翻译,技术细节请以原文为准。
README
以下为原文 README 节选,完整内容请查看原文。
Why: fast and cheap, by design
The pain. Long-horizon, multi-file work is where agentic tools bleed money
and time: the parent model grinds through every file itself — one Read per
file, exploration loops, context that grows and drifts. You pay the parent’s
per-token rates for the reading, and you wait for the model to do it
serially.
The fix. One delegate_to_dsh call hands the whole token-heavy subtask to
a fresh, focused DeepSeek Harness agent running deepseek-v4-flash inside
your workspace. All the file I/O happens there — batched, local, cheap. The
parent stays in the loop for what actually needs a brain: planning,
diagnosis, decisions, verification.
Measured on 100 SWE-bench-style long-horizon tasks (heterogeneous model setup: parent = deepseek-v4-pro, DSH = deepseek-v4-flash; arm B runs the same parent model without the plugin):
with dsh-mcp |
raw agent | |
|---|---|---|
| Accuracy | 100/100 · 100% | 89/100 · 89% |
| Avg. wall time | 76s | 120s |
| Statistical significance | — | Fisher p < 0.001 |
Faster, more accurate — and the accuracy gap is now statistically significant (p = 3.7×10⁻⁴ at n=100), not just directional. The expensive reads now run on deepseek-v4-flash. Full report · Reproduce it
How it works
The prompt used to generate this is in
docs/architecture-image-prompt.md.
- A standard MCP stdio server. Any client that speaks MCP can use it — Claude Code is the client we validated end-to-end (real API calls, subdir launches, Chinese, spaces in paths).
- Parent-agent model. Each delegation is one self-contained subtask; DSH is a stateless worker (fresh process per call — no session to corrupt).
- Zero config, works out of the box. The DSH CLI is auto-discovered (env override →
sibling checkout → child checkout → installed under
%USERPROFILE%\.dsh). - Windows-first.
process.execPath+ explicit argv,shell: false— no
安装
This server does not publish a one-line install command.
Open the repository installation guide 新手?先看 mcpskill.org 教程 →配置
{
"mcpServers": {
"dsh": {
"command": "node",
"args": ["D:\\path\\to\\dsh-mcp\\dist\\index.js"],
"env": { "DEEPSEEK_API_KEY": "sk-..." }
}
}
}