智能协议
经 AI Skill Hub 精选评估，智能协议 获评「推荐使用」。这款MCP工具在功能完整性、社区活跃度和易用性方面表现出色，AI 评分 7.5 分，适合有一定技术背景的用户使用。
📚 深度解析
通过安装 智能协议，你的 AI 助手将获得额外的工具调用能力，可以用自然语言直接操控该工具的功能，无需学习复杂的命令行语法。MCP 工具的核心价值在于"一次配置，永久增强"——配置完成后，每次与 AI 对话时都可以无缝调用这些工具。
在技术实现上，MCP 工具通过标准的 JSON-RPC 协议与 AI 客户端通信，工具的功能以"工具列表"的形式暴露给 AI 模型，AI 可以按需调用。智能协议 提供了结构化的工具调用接口，使 AI 模型能够精确地理解和使用每个功能点，显著降低 AI 在工具使用上的错误率。
与传统的 API 集成相比，MCP 工具的优势在于无需编写代码——用户只需在配置文件中添加几行 JSON，即可让 AI 获得全新能力。AI Skill Hub 将 智能协议 评为 AI 评分 7.5 分，属于同类工具中的优质选择。
📋 工具概览
智能协议 是一款遵循 MCP（Model Context Protocol）标准协议的 AI 工具扩展。通过 MCP 协议，它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务，实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用，都可以通过自然语言在 AI 对话中直接触发，极大提升生产效率。
📖 中文文档
智能协议 是一款遵循 MCP（Model Context Protocol）标准协议的 AI 工具扩展。通过 MCP 协议，它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务，实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用，都可以通过自然语言在 AI 对话中直接触发，极大提升生产效率。
- 通过标准 MCP 协议与 Claude、Cursor 等主流 AI 客户端深度集成
- 提供结构化工具调用接口，显著降低 AI 集成复杂度
- 支持 Claude Desktop 和 Claude Code 无缝接入，开箱即用
- 可与其他 MCP 工具组合叠加，构建完整 AI 工作站
- 轻量无侵入设计，不影响现有系统架构
- 在 Claude Desktop 对话中直接调用本地工具，实现 AI 与系统的深度联动
- 通过自然语言驱动复杂的多步骤自动化任务，代替繁琐手动操作
- 将多个 MCP 工具组合使用，构建个人专属 AI 工作站
# 方式一：通过 Claude Code CLI 一键安装
claude skill install https://github.com/sint-ai/sint-protocol
# 方式二：手动配置 claude_desktop_config.json
{
"mcpServers": {
"----": {
"command": "npx",
"args": ["-y", "sint-protocol"]
}
}
}
# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
- 确认已安装 Node.js（v18 或以上版本）
- 打开 Claude Desktop 或 Claude Code 的 MCP 配置文件
- 按「交给 Agent 安装 → Claude Desktop」标签中的 JSON 配置填入 mcpServers 字段
- 保存配置文件并重启 Claude 客户端
- 重启后，在对话中即可使用本工具
# 安装后在 Claude 对话中直接使用 # 示例： 用户: 请帮我用 智能协议 执行以下任务... Claude: [自动调用 智能协议 MCP 工具处理请求] # 查看可用工具列表 # 在 Claude 中输入："列出所有可用的 MCP 工具"
// claude_desktop_config.json 配置示例
{
"mcpServers": {
"____": {
"command": "npx",
"args": ["-y", "sint-protocol"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
SINT Protocol
Security, permission, and economic enforcement layer for physical AI.
SINT is the missing governance layer between AI agents and the physical world. Every tool call, robot command, and actuator movement flows through a single Policy Gateway that enforces capability-based permissions, graduated approval tiers, and tamper-evident audit logging.
The next upgrade lane is factory control. As prompt-to-hardware and prompt-to-factory tooling gets better at generating industrial plans, SINT is expanding toward the control layer that decides what can be simulated, approved, executed, audited, and settled before AI-generated factory actions touch real machines. See docs/roadmaps/factory-action-pack-upgrade-sprints.md. Sprint 1 now ships a control-standard pack with an industrial action profile, factory intent and cell graph schemas, a robot action schema, a simulation receipt schema, an industrial policy pack, and a refusal-first demo narrative.
Academic grounding: SINT is designed with reference to IEC 62443 FR1–FR7, EU AI Act Article 13, and NIST AI RMF. The evaluation framework references the ROSClaw empirical safety study (arXiv:2603.26997) and MCP security analysis (arXiv:2601.17549).
Agent ──► SINT Bridge ──► Policy Gateway ──► Allow / Deny / Escalate
│
Evidence Ledger (SHA-256 hash-chained)
│
ProofReceipt (pluggable attestation)Prerequisites: Node.js >= 22, pnpm >= 9
pnpm install pnpm run build pnpm run test # full workspace test suite ```
Install the MCP server
The installable server entrypoint is sint-mcp.
npx -y sint-mcp --stdio
npx -y sint-mcp --config ./sint-mcp.config.example.json --stdioIf you prefer containers, build and run the repo root Dockerfile:
docker build -t sint-mcp .
docker run --rm -i sint-mcpDeployment
Docker Compose
```bash docker-compose up
Quick Start
```bash
SINT Operator Interface
A voice-first, HUD-based control surface for SINT operators. Every command flows through the Policy Gateway.
```bash pnpm run stack:interface # starts gateway + interface + postgres + redis
Reference Capsules
| Package | Description | Tests |
|---|---|---|
[@sint/capsule-navigation](capsules/navigation) | Waypoint following navigation reference capsule | 11 |
[@sint/capsule-inspection](capsules/inspection) | Visual anomaly detection for manufacturing QA | 8 |
[@sint/capsule-pick-and-place](capsules/pick-and-place) | Gripper control for pick-and-place tasks | 12 |
Apps & SDKs
| Package | Description | Tests |
|---|---|---|
[@sint/gateway-server](apps/gateway-server) | Hono HTTP API with approvals, SSE streaming, A2A routes | — |
[sint-mcp](apps/sint-mcp) | Security-first multi-MCP proxy server | — |
[@sint/dashboard](apps/dashboard) | Real-time approval dashboard with operator auth | 29 |
[@sint/client](packages/client) | TypeScript SDK for the Gateway API (delegation, SSE) | — |
[@sint/sdk](sdks/typescript) | Zero-dependency public TypeScript SDK aligned to gateway v0.2 contracts | 9 |
[@sint/conformance-tests](packages/conformance-tests) | Security regression suite — all phases | — |
Total: 49 repo packages, apps, examples, and capsules · CI-backed full-suite and conformance coverage
Note: Run pnpm test to get the current exact passing test count.
API Endpoints
| Method | Endpoint | Description |
|---|---|---|
GET | /.well-known/sint.json | Public protocol discovery (version, bridges, profiles, schemas) |
GET | /v1/health | Health check |
POST | /v1/intercept | Evaluate a single request |
POST | /v1/intercept/batch | Evaluate multiple requests (207 Multi-Status) |
POST | /v1/tokens | Issue a capability token |
POST | /v1/tokens/delegate | Delegate (attenuate) a token |
POST | /v1/tokens/revoke | Revoke a token |
GET | /v1/ledger | Query audit ledger events |
GET | /v1/approvals/pending | List pending approval requests |
POST | /v1/approvals/:id/resolve | Approve or deny a request (M-of-N quorum) |
GET | /v1/approvals/events | SSE stream for real-time approval events |
GET | /v1/approvals/ws | WebSocket stream for low-latency approval events |
POST | /v1/a2a | JSON-RPC 2.0 A2A protocol endpoint |
GET | /v1/metrics | Prometheus metrics |
GET | /v1/openapi.json | OpenAPI surface for gateway integration |
GET | /v1/compliance/tier-crosswalk | SINT tier mapping to NIST AI RMF / ISO 42001 / EU AI Act controls |
POST | /v1/economy/route | Cost-aware route selection with optional x402 pay-per-call quotes |
References
- ROSClaw: Empirical safety analysis of LLM-controlled physical AI — arXiv:2603.26997 (IROS 2026)
- MCP Security Analysis: Architectural vulnerabilities in the Model Context Protocol — arXiv:2601.17549
- IEC 62443: Industrial automation and control systems cybersecurity standard
- EU AI Act Article 13: Transparency requirements for AI systems
- NIST AI RMF: AI Risk Management Framework
- W3C DID Core: Decentralized Identifiers specification
Run a Single Package
pnpm --filter @sint/gate-policy-gateway test
pnpm --filter @sint/bridge-mcp testPackages
SINT vs. Other Frameworks
| Capability | **SINT Protocol** | Microsoft AGT | MCP Baseline | SROS2 |
|---|---|---|---|---|
| Physical constraint enforcement (velocity, force, geofence) | ✅ In token | ❌ | ❌ | ❌ |
| Tier-based human oversight (T0–T3) | ✅ 4-tier | ⚠️ Execution rings | ❌ | ❌ |
| Append-only hash-chained audit | ✅ SHA-256 | ⚠️ Logging | ❌ | ❌ |
| ROS 2 / MAVLink / industrial bridges | ✅ 12 bridges | ❌ Digital only | ❌ | ⚠️ ROS only |
| Consumer smart home governance | ✅ Home Assistant + Matter | ❌ | ❌ | ❌ |
| HIPAA + GDPR health data access | ✅ FHIR + HealthKit | ❌ | ❌ | ❌ |
| OWASP ASI01–ASI10 coverage | ✅ 10/10 Full | ✅ 10/10 | ❌ | ❌ |
| Economic routing + budgets | ✅ bridge-economy | ❌ | ❌ | ❌ |
| Swarm collective constraints | ✅ SwarmCoordinator | ❌ | ❌ | ❌ |
| E-stop / CircuitBreaker | ✅ EU AI Act Art. 14 | ✅ Kill switch | ❌ | ❌ |
| Caregiver delegation + consent | ✅ FHIR Consent tokens | ❌ | ❌ | ❌ |
| Differential privacy ledger | ✅ Per-query epsilon budget | ❌ | ❌ | ❌ |
SINT is the only framework purpose-built for physical AI and personal data governance — where actions are irreversible and have real-world consequences. Microsoft AGT targets digital/software agents; SINT targets robots, drones, smart homes, health fabric, and critical infrastructure.
The empirical case for SINT: - ROSClaw (IROS 2026): Up to 4.8× spread in out-of-policy LLM action proposals across frontier models under identical safety envelopes. The 3.4× divergence between frontier backends is measurable, reproducible, and persistent. - MCP security (arXiv:2601.17549): 10 documented real-world MCP breaches in under 8 months, including a CVSS 9.6 command injection affecting 437,000 downloads. - SROS2: Formally demonstrated to contain 4 critical vulnerabilities at ACM CCS 2022, including access-control bypasses permitting arbitrary command injection. - Unitree BLE worm (September 2025): Hardcoded crypto keys enabled wormable BLE/Wi-Fi command injection across robot fleets — precisely the scenario SINT's per-agent token scoping and real-time revocation prevent.
Core guarantees: - No agent action ever bypasses the Policy Gateway (invariant I-G1: No Bypass) - Every decision is recorded in a tamper-evident SHA-256 hash-chained ledger (invariant I-G3: Ledger Primacy) - Physical constraints (velocity, force, geofence) are enforced at the protocol level — in the token, not in config - Tier-gated verifiable compute hooks support provable-execution evidence on critical actions - E-stop is universal across all non-terminal DFA states (invariant I-G2: E-stop Universality) - Per-agent capability tokens with real-time revocation
APS vs SINT Primitives
| APS Concept | SINT Implementation |
|---|---|
| Principal | agentId (Ed25519 public key) + W3C DID identity |
| Capability | SintCapabilityToken (Ed25519-signed, scoped, attenuatable) |
| Authority | PolicyGateway.intercept() — single choke point |
| Confinement | Per-token resource scope + physical constraints (velocity, force, geofence) |
| Revocation | RevocationStore + ConsentPass endpoint (real-time) |
| Audit | EvidenceLedger — append-only, SHA-256 hash-chained |
高质量的开源MCP工具，提供了代理意图和物理执行之间的开放协议和运行时治理层
- 需要让 Claude / Cursor 操作本地工具的 AI 工程师
- 构建多智能体协作系统的 Agent 开发者
- 配置 MCP 服务器时建议使用 stdio 传输 + JSON-RPC，避免暴露公网
- 生产部署优先使用 Docker Compose 隔离依赖，并挂载 volume 持久化数据
- Agent 任务先做 dry-run 验证工具调用链，再开启自主执行
- API key 直接提交到 git 仓库（请用 .env 并加入 .gitignore）
- MCP 配置路径拼错或权限不足，重启 Claude Desktop 才生效
- 容器内无法访问宿主机 localhost — 使用 host.docker.internal
- Docker：sint-protocol 提供官方镜像，docker compose up 一键启动
- CLI：直接 npm install -g / pip install，命令行调用
- 云端托管：可放在 Vercel / Railway / Fly.io 等 PaaS 平台
⚡ 核心功能
- 通过标准 MCP 协议与 Claude、Cursor 等主流 AI 客户端深度集成
- 提供结构化工具调用接口，显著降低 AI 集成复杂度
- 支持 Claude Desktop 和 Claude Code 无缝接入，开箱即用
- 可与其他 MCP 工具组合叠加，构建完整 AI 工作站
- 轻量无侵入设计，不影响现有系统架构
- 需要让 Claude / Cursor 操作本地工具的 AI 工程师
- 构建多智能体协作系统的 Agent 开发者
- 配置 MCP 服务器时建议使用 stdio 传输 + JSON-RPC，避免暴露公网
- 生产部署优先使用 Docker Compose 隔离依赖，并挂载 volume 持久化数据
- Agent 任务先做 dry-run 验证工具调用链，再开启自主执行
- API key 直接提交到 git 仓库（请用 .env 并加入 .gitignore）
- MCP 配置路径拼错或权限不足，重启 Claude Desktop 才生效
- 容器内无法访问宿主机 localhost — 使用 host.docker.internal
👥 适合人群
🎯 使用场景
- 在 Claude Desktop 对话中直接调用本地工具，实现 AI 与系统的深度联动
- 通过自然语言驱动复杂的多步骤自动化任务，代替繁琐手动操作
- 将多个 MCP 工具组合使用，构建个人专属 AI 工作站
⚖️ 优点与不足
- +Apache-2.0 协议，可免费商用
- +标准化 MCP 协议，生态互联性强
- +与 Claude 官方生态无缝对接
- +即插即用，配置简单快捷
- −依赖 Claude 客户端，非 Claude 用户无法使用
- −MCP 协议仍在持续演进，接口可能变更
- −需要一定的配置步骤
AI Skill Hub 为第三方内容聚合平台，本页面信息基于公开数据整理，不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后，再部署至生产环境，并做好必要的安全评估。
✅ Apache 2.0 — 宽松开源协议，可商用，需保留版权声明和 NOTICE 文件，含专利授权条款。
❓ 常见问题 FAQ
AI Skill Hub 点评：智能协议 的核心功能完整，质量良好。对于Claude Desktop / Claude Code 用户来说，这是一个值得纳入个人工具库的选择。建议先在非生产环境试用，再逐步推广。
| 原始名称 | sint-protocol |
| 原始描述 | 开源MCP工具：Open protocol and runtime governance layer between agent intent and physical exe。⭐8 · TypeScript |
| Topics | mcpa2aagent-securityai-governanceai-safety |
| GitHub | https://github.com/sint-ai/sint-protocol |
| License | Apache-2.0 |
| 语言 | TypeScript |
收录时间：2026-05-25 · 更新时间：2026-05-30 · License：Apache-2.0 · AI Skill Hub 不对第三方内容的准确性作法律背书。