@cubiczan/chp-mcp
@cubiczan/chp-mcp
用于 CHP Profile B 支出/资本门槛的一键式 MCP 安装。
封装了 @cubiczan/chp,使 Cursor、Claude Code 或任何 MCP 客户端都能调用 evaluate_spend_gate,而无需内置协议代码。引擎摘要与规范性黄金向量(Profile B 30/30)匹配。
各部分如何配合
MCP client (Cursor / Claude / …)
│ tools/call
▼
┌───────────────────────────┐
│ MCP server (transport) │ ← you are here (@cubiczan/chp-mcp)
│ evaluate_spend_gate │
│ approve_spend │
│ chp_content_hash │
└─────────────┬─────────────┘
│ depends on
▼
┌───────────────────────────┐
│ Published CHP packages │
│ npm: @cubiczan/chp (Profile B)
│ PyPI: consensus-hardening-protocol (Profile A)
└───────────────────────────┘如需 AGENTS.md + skills + Profile A 的 decision_gate / decision_adversary,请改用 agent-conductor。
Related MCP server: Datashift MCP Server
安装
npm install -g @cubiczan/chp-mcp
# or one-shot
npx -y @cubiczan/chp-mcpCursor / Claude Desktop
{
"mcpServers": {
"chp": {
"command": "npx",
"args": ["-y", "@cubiczan/chp-mcp"]
}
}
}Claude Code
claude mcp add chp -- npx -y @cubiczan/chp-mcp工具
工具 | 映射到 | 用途 |
|
| LOCKED / HITL_REQUIRED / BLOCKED + claims + content hash |
|
| 当 HITL_REQUIRED 时的人工锁定(无法覆盖硬失败) |
|
| 浮点感知的规范 SHA-256 |
| — | 服务器与协议版本 |
示例 — 评估一笔支出
// tools/call evaluate_spend_gate
{
"action": { "action": "LONG", "asset": "ETH", "notional": 300, "confidence": 0.9 },
"policy": {
"max_notional": 500,
"daily_cap": 2500,
"hitl_threshold": 250,
"min_confidence": 0.55,
"allowed_actions": ["LONG", "SHORT"]
}
}相关
包 / 仓库 | 作用 |
Profile B 库(此服务器的依赖) | |
Profile A + 规范说明 | |
完整 MCP:合约、技能、Profile A 门槛 | |
|
许可证
MIT.
Related MCP Servers
- FlicenseAqualityAmaintenanceGovernance/control plane for MCP-enabled coding-agent workflows with validation, findings, approvals, budgets, and proof bundles.5511

Datashift MCP Serverofficial
AlicenseNot gradedqualityDmaintenanceEnables AI agents to submit tasks for human or AI review and receive decisions via MCP tools, adding human review checkpoints to workflows.MIT- FlicenseNot gradedqualityDmaintenanceManages agentic workflow spend through budget quotes, policy gates, approvals, receipts, and cost evidence exports.
- FlicenseNot gradedqualityCmaintenanceProvides MCP tools to enforce spend policies (allow, deny, step-up, allowlist) on agent wallets with an immutable audit trail.
Related MCP Connectors
Paid remote MCP for AI Studio Workspace approval gate MCP, structured receipts, audit logs, and revi
Paid remote MCP for Veo 4 credit waste gate MCP, structured receipts, audit logs, and reviewer-ready
Remote MCP for AI Studio Android release gate MCP, structured receipts, audit logs, and reviewer-rea
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/icohangar-ops/cubiczan-chp-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server