protoos-mcp
ProtoOS v0.2.0 — 统一自主协议操作系统
参考实现:一个受策略治理的控制平面,将现有智能体协议 — MCP、A2A、AP2 授权、x402、MPP、UCP/ACP 风格商务、AG-UI、ANP/DID 风格身份 — 组合成一个统一环境,在此环境中智能体被构建、发现、协调、授权、付费并接受审计。
纯 Python 3.12 标准库(外加用于 Ed25519 的可选 cryptography,并带有操作系统验证的 HMAC 回退)。无需网络。
相关: OpenMesha · rui · server-os
接入方式
接入方式 | 入口 |
CLI |
|
SDK |
|
MCP Server |
|
HTTP/JSON-RPC + SSE |
|
多智能体工作流 | 发现 + 带预算的 |
技能 |
|
Constellation + Vault |
|
CI |
|
AGENTS.md | 位于仓库根目录的编码智能体契约 |
需求审计 |
|
Related MCP server: Agorus MCP Server
0.2.0 新特性 — Constellation 与 Obsidian vault
整个世界现在都是一等图(first-class graph),与 Web 控制台的 Constellation 标签页对齐。
protoos.graph.build_graph(os)生成实时对象图 — 主体、预算、MCP 服务器/工具、AP2 授权链、收据、任务、待审批项 — 使用与浏览器构建版本相同的节点类型/边种类词汇表(一致性校验:MATCH)。protoos.graph.layout(graph, seed=…)是确定性力导向布局。导出:to_json、to_dot、to_svg。protoos.vault.write_vault[_zip](os, dest)写出一个由 wikilink 笔记组成的 Obsidian vault;unresolved_links()证明完整性。加固:
AuditLog.append深拷贝载荷;TraditionalRail保留收据。
python3 -m protoos.graph out/ # constellation.{json,dot,svg}
python3 -m protoos.vault vault.zip # Obsidian vault
python3 demo.py # also writes both artifacts
python3 -m protoos.cli status快速开始
python3 -m unittest discover -s tests # 95 tests
python3 demo.py # end-to-end scenario
python3 -m protoos.verify # traceability audit + live smoke
pip install -e ".[crypto]" # optional Ed25519
protoos statusfrom protoos import ProtoOS, Catalog
from protoos.sdk import ProtoOSClient
os_ = ProtoOS()
os_.engine.add_rule("user", "allow", ["payment.settle"], "amount <= 200")
os_.engine.add_rule("org", "require_approval", ["payment.settle"], "amount > 50")
casey = os_.create_user("casey")
shop = os_.create_merchant("shop")
budget = os_.wallet.create_budget(casey.did, 500.0, window=(300.0, 86400))
catalog = Catalog(shop.did, "shop")
catalog.add("bk1", "Distributed Systems 101", 10.00, "USD", "digital")
receipt = os_.purchase(casey.did, catalog, [{"sku": "bk1", "qty": 2}],
intent_text="buy two intro ebooks", max_amount=100,
budget_id=budget.id, categories=["digital"])
# Intent Mandate -> checkout -> Cart Mandate -> Payment Mandate
# -> policy + budget -> x402 settle -> hash-chained audit规范 → 模块映射
规范项 | 模块 |
策略引擎 + 授权存储 |
|
编排器 / 任务图 |
|
身份与凭据服务 |
|
发现与注册表 |
|
可观测性与审计 |
|
钱包 / 支出控制器 |
|
MCP 适配器(+OpenAPI→MCP、联邦、缓存) |
|
A2A 适配器 + AG-UI 事件总线 |
|
UCP/ACP 风格商务 |
|
HTTP/JSON-RPC + SSE 传输层 |
|
控制平面门面( |
|
CLI |
|
SDK |
|
Constellation 图 |
|
Obsidian vault 导出 |
|
Kubernetes CRDs + 部署 |
|
技能 |
|
需求审计 |
|
这里的“参考实现”是什么意思
规范中提到的每个协议表面都在进程内可运行并通过测试:带付费工具的 JSON-RPC MCP、A2A 任务生命周期、完整的 AP2 Intent→Cart→Payment 授权链、经由进程内 facilitator 的 x402 挑战/结算、MPP 预付费会话、基于 SSE 的 AG-UI 事件流、DID 文档和 well-known 发布。此沙盒没有网络出口、没有 Kubernetes 集群、也没有外部 SDK,因此任何需要开放互联网的功能都以本地/回环等效方式实现,并在 traceability.json 中明确标记为 partial 或 deferred — 不会静默遗漏任何内容。
生产加固路径
Rust 控制平面 (X1): 这里的模块边界镜像了预期的服务;Python 构建版就是可执行的规格说明。
存储 (X3): 内存 + JSONL → etcd/Postgres / 对象存储 / 向量数据库。
轨道 (M1/X6): 官方 x402/MPP/AP2 SDK 嵌入现有的轨道接缝。
传输 (X4/X5): 在
httpapi.py之外增加 gRPC/QUIC。沙箱化 (G4): 用容器/microVM 隔离取代
SandboxedExecutor。
设计原则
组合而非替换
策略优先的自治(每个敏感操作均受门控)
加密授权 + 哈希链审计
人机回环作为一等原语
一切多轨(工具、消息、支付、身份)
离线优先的参考实现,如实标记 partial/deferred
许可证
Apache-2.0。治理章程草案:GOVERNANCE.md。
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 Servers
- AlicenseNot gradedqualityDmaintenanceA production-grade MCP server designed for multi-tenant, authenticated, and observable AI agent systems, enabling secure tool execution across heterogeneous data sources.57MIT

Agorus MCP Serverofficial
AlicenseNot gradedqualityDmaintenanceMCP server for the Agorus AI agent marketplace, exposing API operations as tools for LLMs to discover, contract, and interact with agents and services.15MIT- AlicenseNot gradedqualityCmaintenanceEnables AI agents to discover and execute tools via a secure MCP server with JWT authentication, RBAC, rate limiting, and audit logging.1MIT
- AlicenseNot gradedqualityCmaintenanceAn MCP server that exposes a suite of developer tools and apps via a shared tool registry, enabling agents to list and call tools through the MCP protocol.MIT
Related MCP Connectors
Hosted AgentLux MCP server for marketplace, identity, creator, services, and social flows.
MCP server exposing the Backtest360 engine API as tools for AI agents.
Hosted MCP with 91 agent tools: X, domains, SEO, Maps, Trends, Search, YouTube, TikTok, and more.
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/ANAMIZED/Proto-OS'
If you have feedback or need assistance with the MCP directory API, please join our Discord server