Integrates with OpenAI-compatible /chat/completions endpoints to delegate coding tasks to language models and retrieve validated unified diffs.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Model Worker MCP fix the bug in src/utils.js in C:\dev\app and run npm test"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
本機、受限範圍的 coding worker MCP。它只接受明確的 cwd、read_paths、write_paths，將 provider 回傳的 unified diff 在套用前驗證，並可執行指定驗證命令。
在使用者環境變數設定 MODEL_WORKER_API_KEY，或執行 npm run credentials:set -- worker-primary（Windows DPAPI 加密儲存）。
設定 MODEL_WORKER_BASE_URL（任何 OpenAI-compatible /chat/completions endpoint，預設為阿里雲百煉 https://dashscope.aliyuncs.com/compatible-mode/v1；若使用百煉專屬 workspace，改成自己的 workspace endpoint）與 MODEL_WORKER_MODEL。預設主力是 qwen3.7-plus；單檔小修改可切換為 qwen3.6-flash。deepseek-flash-0731 會自動用於中低風險程式邏輯、bug 修復、測試與後端小功能，也支援手動指定。模型名稱與價格表在 worker/router.js、worker/usage-store.js，換 provider 時一併調整。
.mcp.json 以相對路徑啟動 server/server.js；若你的 MCP client 不支援 cwd，把 args 改成此目錄的絕對路徑。
需求：Node.js 18 以上、Git（diff 以 git apply 套用，cwd 必須是 Git repository）；驗證命令與 credential 加密目前透過 Windows PowerShell 執行。
Related MCP server: ForgeGuard MCP
node server/server.jsMCP 工具：route_code_task、delegate_code_task、get_task_status、cancel_task、get_usage_summary。優先呼叫 route_code_task：CSS／文案／文件等低複雜度任務走 qwen3.6-flash；中低風險程式邏輯、bug 修復、測試與後端小功能走 deepseek-flash-0731；一般或跨檔 coding 走 qwen3.7-plus；審查走 glm-5.2。涉及 auth、payment、secret、migration、database、部署或正式環境時只回傳 guarded，不會自動委派。每個任務的 token、估算費用與失敗錯誤摘要會持久化到 %LOCALAPPDATA%\CodexModelWorker\usage.json，可用 get_usage_summary 查詢。DeepSeek 價格尚未填入，因此其費用會標為未知，不會猜算。錯誤內容會遮罩 Bearer 與 sk- 字串，API key 不會出現在設定檔、任務參數、diff 或 log 中。
Cancel a running delegated task.
Inputs: task_id (required).
Run a bounded coding task through the configured provider.
Inputs: cwd (required), task (required), read_paths (required), write_paths (required), +4 more.
Get status, diff and validation output for a delegated task.
Inputs: task_id (required).
Get persisted token usage and estimated CNY cost, optionally filtered by model or time range.
Inputs: model, since, until.
Classify a coding task by risk and automatically delegate safe work to the discounted model tier.
Inputs: cwd (required), task (required), read_paths (required), write_paths (required), +4 more.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 5 tools
route_code_task and delegate_code_task both initiate delegated coding work, which could cause some initial confusion, but the descriptions clarify that one performs risk classification and auto-routing while the other directly runs a bounded task. The remaining tools (status, cancel, usage) are clearly distinct.
Most tools follow a verb_noun pattern (route_code_task, delegate_code_task, get_task_status, get_usage_summary), but cancel_task breaks the pattern by omitting the 'code' qualifier used by the delegation tools. The set is still readable and predictable overall.
Five tools is well-scoped for a task delegation worker: routing, execution, status, cancellation, and usage reporting. Each tool clearly earns its place with no redundancy.
The core lifecycle is covered: initiate/route, run, check status, cancel, and inspect usage. Minor gaps exist, such as no list/history operation to enumerate past tasks or a retry/resume capability, but these are workable around.
Security reviews for coding agents: diffs checked against your org policy and live infrastructure.
Supervised API-write gateway for AI agents with policy, human approval and execution receipts.
Lets coding agents check their own code for leaked secrets, risky dependencies and AI-code mistakes
Guardian agent for AI coding: four frontier models review risky diffs and commits before they ship.