correctover-mcp-server
correctover-mcp-server
CCS 原生 MCP 服务器 — 6 维运行时验证,带故障关闭保证
这是什么?
correctover-mcp-server 是一个 MCP(模型上下文协议)服务器,它将 CCS(Correctover Conformance Standard)运行时验证直接嵌入协议层。每次工具调用在执行之前都会经过 6 个维度的验证——如果验证失败,该操作永远不会执行(故障关闭)。
这不是观察者模式的治理钩子。这是一个协议级别的保证。
Related MCP server: agent-trust-firewall
架构
┌─────────────────────────────────────────────────────┐
│ MCP Client │
│ (any MCP 2026-07-28 compliant client) │
├─────────────────────────────────────────────────────┤
│ Streamable HTTP Transport │
│ (POST /mcp, _meta version negotiation) │
─────────────────────────────────────────────────────┤
│ CCS Runtime Verification │
│ ┌──────────┬──────────┬──────────┬──────────┐ │
│ │ Structure│ Schema │ Latency │ Cost │ │
│ │ Verifier │ Validator│ Monitor │ Monitor │ │
│ ├──────────┼──────────┼──────────┼──────────┤ │
│ │ Identity │ Integrity│ Policy │ Failover │ │
│ │ Tracker │ Checker │ Engine │ Engine │ │
│ └──────────┴──────────┴──────────┴──────────┘ │
│ ANY dimension fails → Action BLOCKED (never runs) │
├─────────────────────────────────────────────────────┤
│ Tool Execution │
│ (only reached if ALL 6 dimensions pass) │
└─────────────────────────────────────────────────────┘6 维验证
维度 | 验证内容 | 失败模式 |
结构 | 请求具有有效的结构、协议版本和方法 | 格式错误的请求被拒绝 |
模式 | 输入与预期的工具模式匹配 | 无效输入被拒绝 |
延迟 | 验证在预算内(P50<10μs,P99<25μs) | 超时 → 故障关闭 |
成本 | 资源使用在限制内 | 超出预算 → 被阻止 |
身份 | 客户端可追踪(存在 clientInfo) | 不可追踪 → 被拒绝 |
完整性 | 请求完整且非空 | 损坏 → 被拒绝 |
快速开始
安装
git clone https://github.com/Correctover/correctover-mcp-server.git
cd correctover-mcp-server
npm install运行
# Development
npm run dev
# Production
npm run build
npm start配置
# Environment variables
export MCP_PORT=3000 # Default: 3000
export MCP_HOST=127.0.0.1 # Default: 127.0.0.1
export CCS_AUDIT=true # Enable audit loggingMCP 协议合规性
此服务器实现 MCP 2026-07-28(仅现代):
✅
server/discover— 广播协议版本、能力和 CCS 身份✅ Streamable HTTP 传输(POST /mcp)
✅
_meta每请求版本协商(无 initialize 握手)✅
resultType在所有响应上(complete/input_required)✅ MRTR 模式用于人机回环(InputRequiredResult)
✅
subscriptions/listen用于变更通知✅ 带有
ttlMs+cacheScope的CacheableResult✅ 标准头部(
Mcp-Method、Mcp-Name、MCP-Protocol-Version)❌ 无
initialize握手(仅现代,无双时代)❌ 无 HTTP+SSE 传输(已弃用)
可用工具
ccs_verify
对代理操作运行 6 维运行时验证。
{
"agent_id": "agent-123",
"action_type": "tool_call",
"tool_name": "search_web",
"tool_input": { "query": "test" }
}ccs_evidence_hash
生成用于审计链封存的完整性证据哈希。
{
"action_id": "action-456",
"result": { "output": "verified" },
"verifier_id": "ccs"
}ccs_status
获取 CCS 运行时状态和性能统计。
可用资源
ccs://policy/default— 默认验证策略配置ccs://status/runtime— 实时运行时统计ccs://config/verifier— 验证器配置(延迟预算、成本限制)
CCS 扩展
此服务器通过 server/discover 通告 CCS 扩展:
{
"extensions": {
"io.modelcontextprotocol/ccs": {
"version": "1.0.0",
"dimensions": ["structure", "schema", "latency", "cost", "identity", "integrity"],
"failClosed": true,
"maxOverheadUs": 25
}
}
}与 Halo 的集成
ccs_evidence_hash 工具生成与 Halo 的 verification 块(v0.2.30+)兼容的哈希,从而支持密封审计链:
{
"verification": {
"status": "verified",
"verifier": "ccs",
"policy_ref": "default",
"checked_at": "2026-08-03T12:00:00Z",
"evidence_hash": "0x..."
}
}性能
P50 验证延迟:< 10μs
P99 验证延迟:< 25μs
故障关闭保证:如果任何维度失败,操作将被阻止
开发
# Build
npm run build
# Test
npm test
# Lint
npm run lint
# Format
npm run format许可证
MIT
参考
This server cannot be deployed
Maintenance
Related MCP Connectors
Deterministic runtime safety for AI agents: scan PII, gate tool actions, verify LLM output.
Runtime permission, approval, and audit layer for AI agent tool execution.
Zero-trust gateway for AI agents: score tool calls, verify agent cards, enforce policy, audit.
Pre-execution governance for AI agents. Deterministic PASS/FAIL/REVIEW verdicts, replayable proof.
Related MCP Servers
- AlicenseCqualityBmaintenanceA fail-closed preflight, approval, evidence, and verification runtime for agents, preventing unsupported output from being treated as verified completion.3MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to securely invoke tools by enforcing identity proof, capability verification, and risk scoring on every request, blocking unsafe calls before they execute.MIT

ERDL Guardofficial
AlicenseNot gradedqualityAmaintenanceEnforces deterministic policy decisions on AI agent tool calls, supporting allow, deny, correct, escalate, and human review actions with verifiable audit receipts.9 npmMIT- AlicenseCqualityCmaintenanceEnables an AI agent to preflight concrete tool calls by recording principal, destination, scope, authority evidence, and relations, allowing only formed actions to execute and producing inspectable evidence receipts.1MIT