engineering-mcp
Click on "Install 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., "@engineering-mcpCreate a task to fix the test failure in auth and delegate it to the codex worker profile."
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.
Engineering MCP
Engineering MCP is an AI engineering control plane built on the Model Context Protocol (MCP).
It coordinates trusted coding workers such as Codex-based workers and Generic Harness integrations while keeping repository ownership, task lifecycle, and execution authority under explicit control.
Unlike a model router, Engineering MCP does not decide which model should solve a problem or expose provider credentials to tasks. Instead, it provides the engineering coordination layer:
repository-bound task management;
controlled worker delegation;
lifecycle tracking and recovery;
worker result validation;
execution records;
trusted worker profile selection;
compatibility with multiple worker harnesses.
The system is designed around a simple principle:
Workers perform bounded execution. The control plane owns engineering state.
Engineering MCP keeps durable engineering truth in the repository, Git history, tests, and controlled ledger state rather than relying on temporary AI conversation context.
Installation
npm install -g engineering-mcp-clior:
npm install -g engineering-mcp-cli@betaRelated MCP server: lattice
Architecture
MCP Host / OWNER
↓
Engineering MCP
lifecycle · ledger · repo safety
↓
Trusted Worker Runner
↓
Native Harness Adapter
↓
Harness-managed Provider / ModelHarness-Native Execution Principle
Engineering MCP standardizes:
WHAT must be done(task contract)lifecycle ownership
repository binding and Git verification
final Engineering Worker Protocol result contract
Native Harnesses decide:
HOW to reasontool use
context management
model/provider selection
execution strategy
Engineering MCP is not a model router, universal model API, replacement Harness, or autonomous scheduler.
Quick start
npm install -g engineering-mcp-cli
engineering-mcp --help
engineering-mcp setup
engineering-mcp doctor
engineering-mcp profiles --worker-profiles /absolute/path/to/profiles.yamlFrom inside a Git repository, start an OWNER server:
cd /path/to/repo
engineering-mcp --role ownerFor local development from this repository:
npm ci
npm run typecheck
npm test
npm run build
node dist/cli.js --helpVerified capability matrix
Hosts
Host | Support |
Grok CLI |
|
Codex CLI |
|
Grok CLI evidence includes real MCP OWNER use, cwd/subdirectory behavior, automatic repository binding, and real worker handoff. Codex CLI is verified for MCP startup and automatic repository discovery; do not treat broader Codex host scenarios as verified unless explicitly tested.
What it provides
Persistent task lifecycle and SQLite ledger Automated Worker Runner handoff Trusted Named Worker Profiles Codex CLI worker integration Generic CLI Harness Adapter Engineering Worker Protocol (engineering-worker/1) Automatic Git repository/worktree binding Git HEAD and scope verification Recovery and dispatch tracking Current-writer fencing across task, dispatch, and event state
Community / unverified
Harness | Label |
Claude Code |
|
Qwen Code |
|
Kimi Code |
|
Other Harnesses |
|
Automatic repository binding
Default public story:
engineering-mcp --role ownerResolution precedence:
1. --repo
2. ENGINEERING_MCP_REPO
3. launch cwd → git rev-parse --show-toplevel
4. fail closedProperties:
a repo subdirectory resolves to the Git root;
a linked worktree resolves to its own worktree root;
outside Git fails with
REPOSITORY_NOT_FOUND;binding is immutable after process startup;
no ledger is opened on failed auto-discovery.
OWNER workflow
An OWNER process creates tasks, delegates to a Worker Harness, awaits the terminal result, and can recover or cancel a stuck task. The Worker Runner owns claim-time repository checks, process execution, result schema validation, and Git verification.
Core OWNER tools include:
create_taskget_tasklist_active_taskslist_worker_profilesdelegate_taskawait_delegationrecover_taskresume_taskcancel_taskclose_task
Worker Harnesses
Workers claim tasks through the trusted Worker Runner. Harnesses never own Engineering MCP lifecycle state. A Harness may be a native adapter (for example Codex CLI) or a declarative Generic CLI adapter.
Worker Profiles
Worker Profiles are trusted operator configuration that select a preconfigured Harness execution profile. They are loaded once at process startup and are immutable for the process lifetime.
OWNER
→ delegate_task(worker_profile = "my-generic-worker")
→ trusted Worker Profile registry
→ adapter + manifest + opaque Harness config
→ Worker Runner
→ native HarnessUse:
engineering-mcp --role owner --worker-profiles /absolute/path/to/profiles.yamlOWNER can list trusted profiles with list_worker_profiles, and can select one with delegate_task(worker_profile = "...").
Without a profile file, the built-in codex-luna default preserves existing behavior. Worker Profiles do not allow task text to choose arbitrary models, providers, executables, or credentials. See Worker Profiles.
GenericCliAdapter
GenericCliAdapter executes a local Harness from a declarative engineering-cli-adapter/1 manifest. Manifests are shell-free: command, arguments, working directory, prompt transport, and result transport are explicit. Task text cannot select executables or argv.
Use:
engineering-mcp adapter validate manifest.yaml
engineering-mcp adapter probe manifest.yamladapter probe validates the manifest and then runs the equivalent of <command> --version with a bounded timeout and local execution only. It does not invoke a model or perform an authenticated smoke. adapter smoke, if exposed, is explicitly opt-in and may consume model quota.
Safety model
Engineering MCP is not an OS sandbox.
Trusted operator configuration can intentionally launch local Harness executables. External Harnesses run with the user's OS permissions. Engineering MCP control mechanisms include:
persistent task lifecycle;
one RUNNING slot;
execution-instance ownership;
writer-generation fencing;
repository binding;
HEAD verification;
allowed/forbidden scope verification;
explicit recovery;
fail-closed worker protocol.
Worker testimony is not Git authority. The Runner independently verifies Git state.
Recovery
Recovery is explicit and OWNER-only. If a Worker Runner disappears or a dispatch becomes orphaned, recover_task terminates the active dispatch atomically and returns the task to a delegable state. cancel_task performs a similar termination for cancellation.
Support tiers
VERIFIED — maintainer real authenticated E2E.
VERIFIED CORE — core mechanism has real E2E evidence, but not every third-party Harness.
COMMUNITY — recipe/config exists but maintainer has no authenticated E2E.
EXPERIMENTAL — evidence exists but upstream interface is unstable/developer-preview.
PLANNED — not implemented or not validated.
Limitations
one RUNNING task slot;
no autonomous scheduler;
no parallel RUNNING;
no auto commit/merge;
no remote runners or cloud service;
no provider router;
no web UI;
no heartbeat/lease subsystem yet.
Validation
Release validated with:
TypeScript build
complete automated test suite
Linux / Windows / macOS CI
npm packed artifact installation test
Contribution / docs
See:
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
No tool schema history has been recorded yet.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Control plane for autonomous software labor. Agents claim objectives over MCP with audit trail.
AI-native git hosting — repos, PRs, issues, CI gates, and AI code review over MCP (60 tools).
Persistent memory and cross-session learning for AI coding assistants (hosted remote MCP).
Hosted MCP memory and agent control plane for durable conversations, jobs, and operations.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables safe repository inspection and Docker-sandboxed command execution via MCP, with optional Codex handoff for implementation tasks.1Apache 2.0
- AlicenseNot gradedqualityAmaintenanceProvides bounded repository context and edit-grant MCP tools to coding agents such as Codex, indexing local repositories and enabling fingerprint-checked patch application.15Apache 2.0
- AlicenseNot gradedqualityCmaintenanceEnables AI coding agents and hosts to enforce deterministic repository boundaries via MCP, providing structured reads, supervised edits, snapshots, audits, and recovery with machine-readable evidence.MIT
- AlicenseNot gradedqualityAmaintenanceEnables AI clients to securely operate isolated coding workspaces with file, command, Git, and deployment tools via authenticated remote MCP.8MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/yunuo110/engineering-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server