Skip to main content
Glama

omp-worker-mcp

持久化模型上下文协议(MCP)服务器,用于将异步编码任务和 DAG 工作流委托给本地 Oh My Pi(OMP)CLI 子代理。

MIT License Node.js MCP Protocol

快速开始 • 配置 • 可用工具 • 安全契约 • 上游归属与免责声明


核心亮点

  • ⚡ 异步委托执行:将繁重的编码、重构和探索任务卸载到后台 OMP worker 实例,而不会阻塞您的主对话会话。

  • 🔀 拓扑 DAG 编排:通过自动拓扑排序、并发控制和依赖传播来执行相互依赖的批量任务。

  • 🛡️ 工作区路径隔离:强制执行显式写入路径边界,防止并发任务之间重叠的文件修改。

  • 🔍 监督恢复与信封:实时检查中间日志,提取结构化 JSON 结果信封,并提供监督指导以重试或调整任务。


Related MCP server: claude-orchestrator

上游归属与免责声明

  • 外部上游 CLI:本项目与 Oh My Pi (OMP) 交互,后者是根据 MIT License 发布的开源工具。

  • 用户先决条件:

    • Node.js >= 22.0.0。

    • 用户必须自行安装并配置本地 OMP CLI 实例。

    • 用户有责任遵守适用于其环境的 OMP CLI 许可证和条款。


功能特性

  • 异步委托执行:启动独立的子代理编码任务,而不会阻塞主对话会话。

  • DAG 与批量编排:通过拓扑依赖排序、并发限制和自动依赖传播来运行相互依赖的批量任务。

  • 严格的任务安全与所有权:内置验证检查可防止多个并发任务写入重叠的文件路径或在同一工作区内冲突。

  • 持续监督与反馈:检查中间输出、流式日志、检索结构化 JSON 信封,并提供监督反馈以继续或重试尝试。

  • 跨平台设计:专为 Windows、macOS 和 Linux 上的本地 Node.js 环境设计;请验证 OMP CLI 在您平台上的可用性。


安装与快速开始

# 1. Clone the repository
git clone https://github.com/divenire990/omp-worker-mcp.git
cd omp-worker-mcp

# 2. Install dependencies
npm ci

# 3. Build TypeScript to dist/
npm run build

# 4. Run test suite
npm test

配置

配置通过环境变量管理(或直接在您的 MCP 客户端中配置)。

变量

描述

默认值

OMP_WORKER_OMP_COMMAND

OMP CLI 二进制的路径或可执行文件名称。

omp

OMP_WORKER_OMP_PREFIX_ARGS

前置到 OMP CLI 调用的参数 JSON 数组。

[]

OMP_WORKER_STATE_DIR

用于存储作业状态、尝试、日志和工件的目录。

~/.codex/state/omp-worker

OMP_WORKER_BROWSER_RULES

可选的自定义浏览器自动化指令,注入到任务提示中。

(无)

跨平台环境示例

Windows (cmd / PowerShell)

set OMP_WORKER_OMP_COMMAND=omp
set OMP_WORKER_STATE_DIR=C:\Users\YourUser\.codex\state\omp-worker

macOS / Linux (bash / zsh)

export OMP_WORKER_OMP_COMMAND=/usr/local/bin/omp
export OMP_WORKER_STATE_DIR=/home/youruser/.codex/state/omp-worker

Codex MCP 客户端配置示例

将服务器添加到您的 Codex MCP 配置中(例如在 config.toml 中):

Windows 示例

[mcp_servers.omp-worker]
command = "node"
args = ["C:/path/to/omp-worker-mcp/dist/index.js"]

[mcp_servers.omp-worker.env]
OMP_WORKER_OMP_COMMAND = "omp"
OMP_WORKER_STATE_DIR = "C:/Users/YourUser/.codex/state/omp-worker"

macOS / Linux 示例

[mcp_servers.omp-worker]
command = "node"
args = ["/path/to/omp-worker-mcp/dist/index.js"]

[mcp_servers.omp-worker.env]
OMP_WORKER_OMP_COMMAND = "/usr/local/bin/omp"
OMP_WORKER_STATE_DIR = "/home/youruser/.codex/state/omp-worker"

可用 MCP 工具

工具

用途

omp_run_compact

便捷工具:委托单个任务并在一次交互中最多等待 wait_seconds 秒完成。

omp_delegate

为编码任务生成异步后台 worker,并立即返回 job_id。

omp_wait

等待运行中的后台作业完成,或轮询直至超时。

omp_result

获取作业的完整尝试历史、日志、输出以及解析后的结构化信封。

omp_continue

将监督更正/指导反馈到失败或阻塞的作业中,以进行新的尝试。

omp_cancel

优雅地终止正在运行的作业及其子进程树。

omp_run_batch_compact

生成并行/顺序批量任务的依赖图(DAG)并等待完成。

omp_wait_group

等待异步批量任务组取得进展或完成。

omp_cancel_group

取消批处理组内所有正在运行和排队的任务。


任务安全与所有权契约

  1. 写入与只读隔离:

    • write 任务必须声明它们拥有的具体文件路径。

    • read_only 任务严格限制不得修改工作区。

  2. DAG 重叠验证:

    • 并行运行的任务不能声明重叠的写入边界。

    • 修改共享路径的任务必须声明显式的线性 DAG 依赖(depends_on)。

  3. 结构化验证契约:

    • 每个完成的子任务都应返回结构化验证详情和更新后的工件描述。


许可证

本项目基于 MIT License 许可。

Available Tools

9 tools
omp_cancelStop OMP TaskA
DestructiveIdempotent

Request immediate cancellation of one exact delegated OMP job. The detached runner owns the OMP child PID and terminates that process tree safely. Call this immediately when the user asks to stop; do not inspect PIDs or manually kill processes first.

Inputs: job_id (required), reason. Returns: error, job_id, status, attempt, +7 more

omp_cancel_groupCancel Batch Task GroupA
DestructiveIdempotent

Request immediate cancellation of a running batch task group and its child tasks. Writes a cancellation request that the detached group coordinator handles safely. Call this immediately when the user asks to stop a batch.

Inputs: group_id (required), reason. Returns: tasks, status, summary, group_id, +6 more

omp_continueSend Supervisory Feedback to Same OMP SessionA
Destructive

Resume the same OMP session with targeted supervisory feedback to correct specific acceptance defects without starting a fresh task from scratch. Bounded to remaining attempts within max_attempts.

Inputs: job_id (required), feedback (required), timeout_minutes. Returns: error, job_id, status, attempt, +7 more

omp_delegateDelegate Complete Task to OMP (Low-level)A
Destructive

Low-level background delegation entrypoint. Transfers ownership of an execution task to OMP and returns immediately with job_id. Prefer omp_run_compact for standard workflows to avoid separate delegate/wait round trips.

Inputs: cwd (required), goal (required), acceptance, max_attempts, +2 more. Returns: error, job_id, status, attempt, +7 more

omp_resultInspect Complete OMP Task ResultA
Read-onlyIdempotent

Retrieve full details of a terminal OMP job, including finalResponse and attempt logs. Call this only when minimal acceptance check fails, high-risk operations occurred, or the user explicitly asks for full inspection; do not call this after every successful compact run.

Inputs: job_id (required). Returns: cwd, goal, error, job_id, +11 more

omp_run_batch_compactRun Batch OMP Tasks with DAG and Compact Aggregated Result (Preferred for Multi-task)A
Destructive

Submits a decomposed group of OMP tasks to execute concurrently in the server-side bounded rolling pool (max_parallel 1-10) using a detached group runner. Enforces dependency DAG and write-ownership safety, waits up to wait_seconds (0-240, default 60s) for batch completion, and returns stable compact aggregated results. If still running when deadline elapses, returns group_id and minimal progress counts for subsequent omp_wait_group.

Inputs: cwd (required), tasks (required), max_parallel, wait_seconds, +4 more. Returns: tasks, status, summary, group_id, +6 more

omp_run_compactRun OMP Task with Compact Result (Preferred for Single Task)A
Destructive

Preferred entrypoint for single substantive execution tasks. Creates a delegated OMP task, launches the detached runner, and waits up to wait_seconds (default 60s) for completion in a single MCP call. If finished, returns a compact summary, artifacts, verification, and details_path without dumping the full final response. If still running at the deadline, returns job_id and status running for subsequent omp_wait.

Inputs: cwd (required), goal (required), acceptance, max_attempts, +3 more. Returns: error, job_id, status, attempt, +7 more

omp_waitWait for OMP TaskA
Read-onlyIdempotent

Wait for an existing OMP job to reach a terminal status, polling up to wait_seconds (default 30s, max 60s). Returns the current status and summary once terminal or when the wait deadline elapses. Avoid polling in a tight loop.

Inputs: job_id (required), wait_seconds. Returns: error, job_id, status, attempt, +7 more

omp_wait_groupWait for Batch Task GroupA
Read-onlyIdempotent

Wait for an existing OMP task group to reach a terminal status, polling up to wait_seconds (0-240, default 60s). If completed, returns full aggregated compact results in original input order. If still running when deadline elapses, returns minimal progress counts without leaking task summaries.

Inputs: group_id (required), wait_seconds. Returns: tasks, status, summary, group_id, +6 more

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.3/5.0

    Scored across 9 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose: batch vs single, delegate vs wait vs cancel vs result retrieval vs continue. No two tools overlap in function—omp_run_compact and omp_delegate differ by synchronous vs asynchronous, and omp_wait_group vs omp_wait serve batch vs single jobs.

    Naming Consistency5/5

    All tools follow a consistent `omp_<verb>[_<noun>]` pattern where the verb describes the action (run, wait, cancel, result, continue) and optional noun specifies the target (batch, group, compact). Perfectly predictable and uniform.

    Tool Count5/5

    9 tools precisely cover the lifecycle of both single and batch task execution: submission, waiting, cancellation, result retrieval, and continuation. No tool is superfluous, and the count is tight for the complexity of the domain.

    Completeness5/5

    The tool surface covers every stage of task management: submission (run/delegate), monitoring (wait), cancellation (cancel), post-hoc inspection (result), and iterative correction (continue). No obvious gaps—both single and batch workflows are fully supported.

    Maintenance

    ActivityMaintained
    ResponsivenessLimited data

    Related MCP Connectors

    Related MCP Servers