Yasin-MCP
Yasin-MCP
面向独立 AI/Agent 的 MCP(Model Context Protocol)访问与集成层,用于 Yasin 生态系统。
使命
Yasin-MCP 通过 MCP 协议提供对 Yasin 生态系统信息的只读、结构化访问(项目注册表、文档、GitHub 仓库状态、运行时诊断),使 AI 代理和 MCP 客户端能够查询生态系统的状态,而无需直接、无限制地访问任何单个仓库或服务。
Related MCP server: conda-meta-mcp
状态
仅 Phase 0、Issue #1(仓库引导与工程基线)。 尚不存在 MCP 服务器运行时。尚不存在领域适配器(YASIN-DOCS、GitHub、Yasin-Operations)。本 issue 仅建立包结构、工具链以及安全原语(错误模型、默认拒绝策略、机密信息处理),后续所有工作都将在此基础上构建。
关于架构来源的说明
本项目的原始任务描述指出,YASIN-DOCS 是 Yasin-MCP 的“规范架构与边界”。针对 yusi20006-max/YASIN-DOCS 仓库的直接核验(既包括对“Yasin-MCP”/“MCP”的代码搜索,也包括对 PROJECT_REGISTRY.yaml 和 ECOSYSTEM.md 的直接检查)发现,截至本 issue,该仓库中没有任何地方提到 Yasin-MCP。
这意味着此处实现的架构直接源自本项目自身的 Issue #1–#10 描述(这些描述详细且自洽),而非源自目前尚不存在的 YASIN-DOCS 文档。如果/当 YASIN-DOCS 更新为包含 Yasin-MCP 时,该文档应成为权威来源,本说明应被移除或更新,以反映其当前所在位置。
架构边界
Yasin-MCP 不取代 YASIN-DOCS、Yasin-Core、Yasin-Agent、Yasin-AI、YasinHub、YasinCLI 或 Yasin-Operations。
Phase 1 严格为只读:不进行仓库变更、不进行部署、不进行生命周期变更(启动/停止/重启)、不进行内存变更、不执行任意 shell/命令。
不允许私有的跨仓库导入。集成使用公共 API、SDK、契约或明确的只读适配器。
现有 Yasin 项目不得依赖 Yasin-MCP。
默认拒绝的策略边界(
policies/policy.py)会拒绝任何名称匹配禁止模式(exec、shell、command、request、arbitrary、filesystem、deploy、delete、start_/stop_/restart_)的能力,或任何在 Phase 1 生效期间声明自身为可变(mutating)的能力——该策略在构造时强制执行,而不仅仅在注册时。
包结构
src/yasin_mcp/
server/ MCP server runtime (Issue #4)
protocol/ MCP protocol types/boundary (Issue #2)
capabilities/ capability descriptor + discovery (Issue #2)
tools/ MCP tool implementations (Issue #4+)
resources/ MCP resource implementations (Issue #4+)
adapters/ domain adapters: YASIN-DOCS, GitHub, Yasin-Operations (Issue #5-7)
policies/ deny-by-default policy boundary
errors/ structured error model (McpError + ErrorCategory)
audit/ structured logging, correlation IDs
config/ configuration model, secret handling
version.py package version, EvidenceStatus enum证据模型
报告生态系统状态的响应应使用以下之一标记信息:
CONFIRMED— 直接观察自实时、权威来源TARGET— 已记录的目标/架构,尚未针对运行中的系统进行验证PROPOSED— 建议或计划,尚未在任何地方实现UNRESOLVED— 无法确定;不得作为事实呈现
开发
pip install -e ".[dev]"
pytest
ruff check .
ruff format --check .
mypy src
bandit -q -r srcMaintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceA read-only MCP server for AI coding agents to inspect repositories, audit code quality, route engineering skills, and plan safe issue/PR workflows.1MIT
- AlicenseNot gradedqualityAmaintenanceAn MCP server that exposes authoritative, read-only Conda ecosystem metadata for AI agents, enabling package search, dependency resolution, and other packaging queries without side effects.6BSD 3-Clause
- AlicenseNot gradedqualityAmaintenanceA read-only MCP server that provides AI agents with live, structured workspace awareness, including project listing, git status, and budgeted context packing, minimizing token usage.62MIT
- AlicenseAqualityCmaintenanceRead-only MCP server providing AI access to verifiable web, GitHub, and local sources, plus a managed fantasy entity catalog, with strong security and provenance tracking.10MIT
Related MCP Connectors
Agent-native MCP server over the public saagarpatel.dev corpus. Read-only, stateless.
An MCP server that gives your AI access to the source code and docs of all public github repos
Read-only Remote MCP for externally grounded AI agent trust receipts.
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/yusi20006-max/Yasin-MCP'
If you have feedback or need assistance with the MCP directory API, please join our Discord server