Durable MCP server for delegating background coding tasks to local OMP workers with DAG orchestration, path ownership isolation, and structured result inspection.
- ✓Open-source license (MIT)
- ✓Actively maintained (<30d)
- ✓Clear description
- ✓Topics declared
- ✓Documented (README)
claude mcp add omp-worker-mcp -- npx -y omp-worker-mcp{
"mcpServers": {
"omp-worker-mcp": {
"command": "npx",
"args": ["-y", "omp-worker-mcp"]
}
}
}Resumen de MCP Servers
<div align="center">
# omp-worker-mcp
**Durable Model Context Protocol (MCP) server for delegating background coding tasks and DAG workflows to local Oh My Pi (OMP) CLI sub-agents.**
<p align="center">
English •
<a href="README.zh-CN.md">简体中文</a> •
<a href="docs/README.md">Documentation Hub</a>
</p>
[](LICENSE)
[](https://www.npmjs.com/package/omp-worker-mcp)
[](package.json)
[](https://github.com/divenire990/omp-worker-mcp/actions/workflows/ci.yml)
<br />
<img src="assets/orchestration.gif" alt="Async DAG Orchestration Flow" width="800" />
<p align="center">
<em>Asynchronous task execution, DAG dependency resolution, path ownership isolation, and structured result verification.</em>
</p>
[Quick Start](#installation-quick-start) • [Entrypoints](#recommended-entrypoints) • [Safety Contract](#task-safety-ownership) • [Platform Support](#platform-support-boundaries) • [Docs Hub](docs/README.md)
</div>
---
## Value & Operating Model
`omp-worker-mcp` implements an outcome-led **Supervisor-Worker** pattern that decouples high-level planning from concrete implementation:
- **Main Agent Remains in Control**: The primary host harness (e.g., Codex, Claude Code) retains full authority over architecture, task decomposition, trade-off decisions, and final acceptance review.
- **Durable Local Background Execution**: Concrete, long-running coding, refactoring, and exploratory tasks are offloaded to local OMP worker processes running in the background without blocking conversational turns.
- **Topological DAG Orchestration**: Independent work units can be orchestrated as a directed acyclic graph (DAG) with automated dependency resolution, concurrency limits, and failure containment.
- **Explicit Path Ownership Boundaries**: Write tasks must declare explicit write-path ownership. The server validates and rejects overlapping concurrent write scopes in batch DAGs, supplying declared boundaries as worker constraints to prevent write collisions.
- **Structured Results & Supervised Resumption**: Workers report deliverables via the structured `OMP_WORKER_RESULT` envelope (status, summary, artifacts, verification checks, remaining items). Supervisors can inspect logs in real time and inject corrective guidance via `omp_continue` to retry within the same session.
---
## Installation & Quick Start
### 1. Install OMP
Install [Oh My Pi (OMP) from its official project](https://github.com/can1357/oh-my-pi). (Note: running `omp-worker-mcp` requires local Node.js `>= 22.0.0`.)
### 2. Verify OMP Reachability
Verify that the OMP CLI is reachable in your environment:
```bash
omp --version
```
*Troubleshooting: If `omp` is not on your `PATH`, set `OMP_WORKER_OMP_COMMAND` to its executable path in your MCP configuration.*
### 3. Configure OMP & Default Worker Model
Run `omp setup` in your terminal to authenticate, configure your local OMP environment, and select your default worker model. This default model is what background OMP workers use during task execution.
*(Optional advanced configuration)*: You can specify your default model via `modelRoles.default: <provider>/<model>` in `~/.omp/agent/config.yml`. For upstream configuration options, see [Oh My Pi](https://github.com/can1357/oh-my-pi).
### 4. Install / Register omp-worker-mcp from npm via npx & Restart Host
Add `omp-worker-mcp` to your host harness's stdio `mcpServers` configuration. The host runs the published npm package using `npx -y omp-worker-mcp`, which downloads and caches it on first use; ordinary users do not need `git clone` or `npm install -g`. Keep the JSON configuration below as the executable setup and restart your host harness:
```json
{
"mcpServers": {
"omp-worker": {
"command": "npx",
"args": ["-y", "omp-worker-mcp"],
"env": {
"OMP_WORKER_OMP_COMMAND": "omp"
}
}
}
}
```
*For detailed client configurations covering Codex (`config.toml`), Claude Code, Cursor, VS Code / GitHub Copilot, Windsurf Cascade, and Continue, see [Client Configurations](docs/client-configurations.md).*
### 5. Send Your First Prompt
After restarting your host harness, paste a read-only inspection prompt directly into your conversation to verify the full delegation chain:
```text
Please use the configured omp-worker-mcp to perform a read-only inspection of the current workspace, review the project structure and dependencies, and provide a concise summary report. Do not modify any files.
```
---
### For Contributors / Local Development: Building from Source
```bash
git clone https://github.com/divenire990/omp-worker-mcp.git
cd omp-worker-mcp
npm ci
npm run build
npm test
```
## Recommended Entrypoints
While MCP registration and policy heuristics guide host harnesses to select high-level entrypoints based on task complexity, automatic invocation is not guaranteed. Users may also explicitly request omp-worker-mcp in prompts when delegation is critical or if the host falls back to direct execution:
- **`omp_run_compact` (Single Task)**: High-level single-task entrypoint selected by the host to delegate a discrete coding or research assignment, wait up to `wait_seconds` for execution, and return a compact structured summary and artifact list.
- **`omp_run_batch_compact` (Multi-Task / DAG)**: High-level multi-task entrypoint selected by the host to dispatch interdependent tasks with explicit dependency graphs and concurrency limits, waiting for aggregated results.
*For lower-level primitives (`omp_delegate`, `omp_wait`, `omp_result`, `omp_continue`, `omp_cancel`, `omp_wait_group`, `omp_cancel_group`) and complete schemas, consult the [Tool Reference](docs/tool-reference.md).*
---
## Task Safety & Ownership
1. **Declared Write Ownership in Batch DAGs**: In batch DAG tasks (`omp_run_batch_compact`), `write` task items must explicitly declare the workspace paths they own via `ownership`, while `read_only` task items declare no write scope. For single-task execution (`omp_run_compact`), read-only and no-modification constraints are expressed directly in `goal` and `acceptance`.
2. **DAG Overlap Validation**: The server validates batch groups and rejects concurrent tasks with overlapping write scopes; tasks operating on shared paths must declare sequential `depends_on` dependencies.
3. **Structured Verification Contract**: Subagents deliver results using the structured `OMP_WORKER_RESULT` envelope (status, summary, artifacts, verification checks, remaining items).
*High-impact operations (e.g., `npm publish`, `git push`, production deployments, secret modification) must always remain under direct host harness and human supervision.*
---
## Platform Support & Boundaries
- **Upstream Engine**: Interfaces with the [Oh My Pi (OMP)](https://github.com/can1357/oh-my-pi) CLI (MIT License). The upstream binary is **not bundled** and must be installed separately in your local runtime `PATH`.
- **Runtime Requirement**: Node.js **>= 22.0.0** (native ECMAScript Modules and modern Node.js APIs).
- **Operating Systems**:
- **Windows** and **macOS (Apple Silicon)**: Verified with Node.js 22+ and real OMP CLI end-to-end testing.
- **Linux**: Supported by the architecture, but awaiting broader production verification.
- **Support Tiers**:
- **Author-Verified**: Codex (author's daily local workflow; not a cross-platform CI guarantee).
- **Documented / Reproducible**: Claude Code, Cursor, VS Code / GitHub Copilot, Windsurf Cascade, Continue (*not CI integration-tested*).
- **Cloud / Remote Hosts**: Conditional (*requires complete runtime, OMP CLI in PATH, writable workspace, and process spawning permissions*).
---
## Documentation Hub
Detailed documentation is organized in the [`docs/`](docs/README.md) directory:
- [**Documentation Index**](docs/README.md): Overview of documentation layout and responsibilities.
- [**Author Workflow Enablement & Architecture**](docs/author-workflow.md): Enablement tutorial, policy templates, host-worker supervision loop, and authoring guidelines.
- [**Client Configurations**](docs/client-configurations.md): Documented and reproducible configuration guidance for Codex, Claude Code, Cursor, VS Code / GitHub Copilot, Windsurf Cascade, and Continue.
- [**Operations & State Lifecycle**](docs/operations.md): Environment variables, state directory layout, retention policies, and recovery.
- [**Tool Reference & Safety Contract**](docs/tool-reference.md): Full MCP tool specifications and safety boundaries.
- [**Benchmark Protocol**](benchmarks/README.md): Reproducible evaluation protocol comparing direct host execution against supervisor-worker delegation.
- [**Official MCP Registry Publishing Guide**](docs/registry-publishing.md): Step-by-step maintainer release workflow for npm and the Official MCP Registry.
---
## Compatibility & Changelog
- **Public Contract & Deprecation**: Review [COMPATIBILITY.md](COMPATIBILITY.md) for versioning guarantees.
- **Release History**: Review [CHANGELOG.md](CHANGELOG.md) for notable updates.
---
## License
This project is licensed under the [MIT License](LICENSE).
Lo que la gente pregunta sobre omp-worker-mcp
¿Qué es divenire990/omp-worker-mcp?
+
divenire990/omp-worker-mcp es mcp servers para el ecosistema de Claude AI. Durable MCP server for delegating background coding tasks to local OMP workers with DAG orchestration, path ownership isolation, and structured result inspection. Tiene 1 estrellas en GitHub y su última actualización registrada es del 2026-08-27.
¿Cómo se instala omp-worker-mcp?
+
Puedes instalar omp-worker-mcp clonando el repositorio (https://github.com/divenire990/omp-worker-mcp) o siguiendo las instrucciones del README en GitHub. ClaudeWave también te ofrece bloques de instalación rápida en esta misma página.
¿Es seguro usar divenire990/omp-worker-mcp?
+
Nuestro agente de seguridad ha analizado divenire990/omp-worker-mcp y le ha asignado un Trust Score de 95/100 (tier: Verified). Revisa el desglose completo de comprobaciones superadas y flags en esta página.
¿Quién mantiene divenire990/omp-worker-mcp?
+
divenire990/omp-worker-mcp es mantenido por divenire990. La última actividad registrada en GitHub es del 2026-08-27, con 0 issues abiertos.
¿Hay alternativas a omp-worker-mcp?
+
Sí. En ClaudeWave puedes explorar mcp servers similares en /categories/mcp, ordenados por popularidad o actividad reciente.
Despliega omp-worker-mcp en tu cloud
Lleva este repo a producción en minutos. Cada plataforma genera su propio entorno con variables de entorno editables.
¿Mantienes este repo? Añade un badge a tu README
Pega el badge en tu README de GitHub para mostrar que está auditado por ClaudeWave. Cada badge enlaza de vuelta a esta página y muestra el Trust Score actual.
[](https://claudewave.com/repo/divenire990-omp-worker-mcp)<a href="https://claudewave.com/repo/divenire990-omp-worker-mcp"><img src="https://claudewave.com/api/badge/divenire990-omp-worker-mcp" alt="Featured on ClaudeWave: divenire990/omp-worker-mcp" width="320" height="64" /></a>Más MCP Servers
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
An open-source AI agent that brings the power of Gemini directly into your terminal.
Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface
The fastest path to AI-powered full stack observability, even for lean teams.
🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl!