Sign In

@cubiczan/chp-mcp

Package Overview
Dependencies
Maintainers
1
Versions
3
Alerts
File Explorer

Advanced tools

Socket logo

Install Socket

Detect and block malicious and high-risk dependencies

Install

@cubiczan/chp-mcp

Spend approval gate for AI agents — enforce budget limits, per-asset caps and human-in-the-loop thresholds before an agent moves money, with a signed audit hash.

latest
Source
npmnpm
Version
0.1.2
Version published
Maintainers
1
Created
Source

@cubiczan/chp-mcp

icohangar-ops/cubiczan-chp-mcp MCP server

One-command MCP install for CHP Profile B spend / capital gates.

MCP Registry npm Conformance

Wraps @cubiczan/chp so Cursor, Claude Code, or any MCP client can call evaluate_spend_gate without vendoring protocol code. Engine digests match the normative golden vectors (Profile B 30/30).

How the pieces fit

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)
└───────────────────────────┘

For AGENTS.md + skills + Profile A decision_gate / decision_adversary, use agent-conductor instead.

Install

npm install -g @cubiczan/chp-mcp
# or one-shot
npx -y @cubiczan/chp-mcp

Cursor / Claude Desktop

{
  "mcpServers": {
    "chp": {
      "command": "npx",
      "args": ["-y", "@cubiczan/chp-mcp"]
    }
  }
}

Claude Code

claude mcp add chp -- npx -y @cubiczan/chp-mcp

Tools

ToolMaps toPurpose
evaluate_spend_gateevaluateGateLOCKED / HITL_REQUIRED / BLOCKED + claims + content hash
approve_spendapproveHumanHuman lock when HITL_REQUIRED (cannot override hard fails)
chp_content_hashcontentHashFloat-aware canonical SHA-256
chp_versionServer + protocol versions

Example — evaluate a spend

// 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"]
  }
}
Package / repoRole
@cubiczan/chpProfile B library (this server’s dependency)
consensus-hardening-protocolProfile A + normative spec
@cubiczan/agent-conductorFull MCP: contracts, skills, Profile A gates
@cubiczan/governed-mcp-gatewayHTTP MCP control plane
@cubiczan/codesentinel-mcpCodebase health MCP
cubiczan-resilience / @cubiczan/resilienceShared retry / timeout / audit primitives

Licence

MIT.

Keywords

mcp

FAQs

Package last updated on 22 Aug 2026

Related posts