Engineering MCP is a repository-aware AI engineering control plane for orchestrating trusted coding workers through MCP, with lifecycle management, execution isolation, and verifiable task handoff.
View on GitHub ↗A repository-aware AI engineering control plane for coordinating trusted coding workers through the Model Context Protocol (MCP).
Engineering MCP lets an OWNER delegate bounded engineering work to trusted worker Harnesses while keeping repository ownership, task lifecycle, execution authority, and verification under explicit control.
Workers perform bounded execution. The control plane owns engineering state.
Engineering MCP is not a model router. It does not let task text choose arbitrary providers, models, executables, manifests, or credentials. Instead, it provides the coordination and safety layer around native coding-agent Harnesses.
Coding agents are good at implementation, but reliable multi-agent engineering needs more than simply sending prompts to another model.
- repository-bound task management; - controlled Worker delegation; - persistent task and dispatch lifecycle; - trusted Worker Profile selection; - Worker result validation; - Git HEAD and scope verification; - explicit recovery and cancellation; - durable execution records; - compatibility with native and Generic CLI Harnesses.
Engineering truth remains in durable project state — the repository, Git history, tests, and Engineering MCP ledger — rather than depending on temporary conversation history.
Requires Node.js 24 or newer and Git on PATH. The repository must have an initial commit. Creating, claiming, and resuming tasks requires a clean working tree on a named branch. Install and authenticate the selected Harness separately; installing Engineering MCP does not install or authenticate Codex or
From the project README.
Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:
[](https://mcp.liqiwa.com/s/yunuo110--engineering-mcp.html)
Local-first MCP plugin for continuous software-quality review by AI coding agents, powered by Jev.
nassim-arifette/jevgrepJev-powered semantic code search for coding agents — find behavior across repositories via CLI or MCP, with exact source excerpts and line numbers.
LilithGames/a2waveTurn the agent CLIs you already use into shared services your whole team can call. Natural-language-driven agent orchestration for Claude Code, Cursor Agent, and OpenAI Codex.
zriyox/codex-supervisor-mcpCodex MCP server: run parallel Codex CLI workers in isolated git worktrees, state on disk, web dashboard, auto-update.
herry2059/project-os-for-codexOpen-source control plane for Codex projects: Git-backed context, visible agent progress, scoped MCP access, resumable work, and safe handoffs.
pranee54/AgentDoctorLocal CLI that audits coding-agent configuration for security, instructions, context, and MCP — no API key or code upload by default.
The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.