About AI Project Os MCP
AI Project Os MCP is an MCP server published by wuxiaolong123121 in the Productivity category: enterprise-grade AI engineering governance MCP server.
The repository has 1 stars and 0 forks, with the last commit 10 months ago. Six months or more without a commit doesn't mean the server is broken, but check the open issues before depending on it in production.
Install
git clone https://github.com/wuxiaolong123121/ai-project-os-mcpThis server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Ask AI
Ask AI about AI Project Os MCP
Powered by Claude · Grounded in docs
Security checks
Static checks derived from the repository yesterday. Heuristics on the source, not an audit.
- ✓README presentThe repository ships documentation.
- ✓License declaredUsable under a stated license.
- ✓Tests presentA test suite exists in the repository.
- !Dependencies pinnedNo lockfile. Installs can pull different code over time.
- !No dynamic code executionSource scan found eval or shell execution. Review how tool inputs reach it before granting credentials.
- !Scoped permissionsDoesn't declare a permission scope. Assume it can do anything its process can.
Releases
README
AI Project OS
AI Project Operating System
Turn AI coding into real, auditable software engineering.
Quick Start
Installation
pip install ai-project-os-mcp
Usage
-
Initialize a new project:
ai-project-os init my-project cd my-project -
Start with S1 Scope stage:
ai-project-os s1 -
Follow the 5S workflow:
# After completing S1, move to S2 ai-project-os s2 # Then S3, S4, and finally S5 ai-project-os s3 ai-project-os s4 ai-project-os s5 -
Check project status:
ai-project-os status
For Non-Technical Users
If you don't want to use the command line, check out our Zero-Code Guide to use AI Project OS with just your AI tool.
Status
⚠️ AI Project OS v2.5 is currently in Spec-Frozen / Implementation-in-Progress state.
- Architecture and module design are frozen
- Core governance engine implementation is ongoing
- APIs, modules, and governance behaviors may change until v2.5.0 release
- Not yet suitable for production use
For stable v1.x version, please check the v1 branch.
What is this?
AI Project OS is an engineering-grade operating system for AI-driven software projects.
It does not try to make AI "smarter".
It makes AI obedient to real-world engineering rules.
AI Project OS enforces:
- Clear project stages
- Frozen decisions
- Guarded code generation
- Mandatory audit trails
No freeze, no code.
No audit, no ship.
What AI Project OS is NOT
- ❌ Not an AI code quality checker
- ❌ Not responsible for business logic correctness
- ❌ Not a replacement for human review
Why AI Project OS?
AI coding fails in real projects because:
- AI skips steps
- AI rewrites architecture
- AI patches instead of redesigning
- Humans cannot tell when AI crossed the line
AI Project OS fixes this by introducing engineering governance.
Core Concepts
1. State over Prompt
Project truth lives in state.json, not in conversation memory.
2. Freeze over Generate
All decisions must be frozen before execution.
3. Audit over Output
Code without audit is not considered done.
The 5S Workflow
| Stage | Meaning | Code Allowed |
|---|---|---|
| S1 | Scope | ❌ |
| S2 | Spec | ❌ |
| S3 | Structure | ❌ |
| S4 | Schedule | ❌ |
| S5 | Ship | ✅ |
MCP-Based Governance
AI Project OS is implemented as a Model Context Protocol (MCP) server.
This allows:
- Claude
- Cursor
- Trae
- Local agents
To act as governed engineering executors, not free-form chatbots.
S5 Stability Guard (Mandatory)
Every S5 task must include:
- Context Refresh
- Change Fuse
- Pseudo-TDD
- Audit Record
No exception.
Approval Field
Approval MUST be provided by a human reviewer. In audit logs:
- AI may suggest content
- Human reviewer must explicitly sign off
AI self-approval is forbidden for compliance reasons.
Who is this for?
- Non-technical founders
- Product managers using AI coding
- Teams tired of AI-generated mess
- Anyone who wants AI to behave like a real engineer
License
MIT License
MCP Server Runtime Modes
| Mode | Usage | Security Features |
|---|---|---|
| STDIO | Claude / Cursor / Trae | Lightweight, for development |
| HTTP | Dashboard / Enterprise | Supports authentication, for production |
Core Principle
拒绝违规执行 比勉强完成任务更正确
AI Project OS believes that refusing to execute violations is more correct than勉强 completing tasks.
Version Semantics
We follow Semantic Versioning:
- MAJOR (x.0.0): Governance model or MCP protocol changes
- MINOR (1.x.0): New governance capabilities, backward compatible
- PATCH (1.0.x): Bug fixes, documentation, or non-behavioral changes
Release & Rollback Policy
- Release: Git tags trigger GitHub Actions for automatic PyPI publishing
- Rollback: Never delete published versions, only release fix versions (e.g., v1.0.1)
LTS Support
v2.5.x will maintain backward compatibility for governance schemas.
Enterprise Edition Roadmap
The following capabilities are reserved for future enterprise editions:
- Multi-project isolation
- Centralized audit logging
- Private MCP Registry
- SSO / RBAC support
Philosophy
AI should not be creative about structure.
AI should be creative only within frozen boundaries.
README fetched from the repository yesterday. The original is authoritative.