Spree Commerce developer docs for AI agents
Spree Commerce docs for AI coding agents: build headless B2B and marketplace ecommerce on its APIs.
Local advisory pre-trade risk gate for agents. Never places orders.
选择你使用的 AI 应用,然后复制设置。
通过 3/3 项检查 · 在你的电脑上运行 · ✓ 命令已检查 2026年11月13日
第一步:你用哪个 AI?
选择你用的应用,步骤会显示在下方。
可连接 Claude,但需要先准备
需要先在电脑上安装 Python (uv)(只需一次) · 仅限电脑上的 Claude 应用(Windows 或 Mac),网页和手机不可用
SettingsDeveloperEdit Config
{
"mcpServers": {
"deadlatch": {
"command": "uvx",
"args": [
"deadlatch",
"--policy",
"your-value",
"--portfolio",
"your-value"
]
}
}
}用 Deadlatch 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Claude 说正在使用 Deadlatch,或回答中出现 Deadlatch 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同
ChatGPT 暂时无法连接 Deadlatch
Deadlatch 需要安装在你的电脑上,而 ChatGPT 只能连接在网上运行的服务器
A · 使用能连接 Deadlatch 的应用
B · 网店与支付 类中能连接 ChatGPT 的其他服务器
从同类中使用较多的里挑选,仅限用地址即可连接、无需密钥的
可连接 Claude Code,但需要先准备
需要先在电脑上安装 Python (uv)(只需一次)
Mac:按 Command+空格,输入 Terminal · Windows:打开 PowerShell
claude mcp add --scope user deadlatch -- uvx deadlatch --policy your-value --portfolio your-value应能看到 Deadlatch 在列表中并显示已连接
用 Deadlatch 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Claude Code 说正在使用 Deadlatch,或回答中出现 Deadlatch 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同
可连接 Cursor,但需要先准备
需要先在电脑上安装 Python (uv)(只需一次) · 没有一键按钮,需要粘贴设置并自行填写
~/.cursor/mcp.json
粘贴这些设置,填写空着的值并保存
{
"mcpServers": {
"deadlatch": {
"command": "uvx",
"args": [
"deadlatch",
"--policy",
"your-value",
"--portfolio",
"your-value"
]
}
}
}用 Deadlatch 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Cursor 说正在使用 Deadlatch,或回答中出现 Deadlatch 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Cursor 帮助页面核实 · 你的界面可能因版本略有不同
可连接 VS Code,但需要先准备
需要先在电脑上安装 Python (uv)(只需一次) · 没有一键按钮,需要粘贴设置并自行填写
MCP: Open User Configuration
粘贴这些设置,填写空着的值并保存
{
"servers": {
"deadlatch": {
"type": "stdio",
"command": "uvx",
"args": [
"deadlatch",
"--policy",
"your-value",
"--portfolio",
"your-value"
]
}
}
}用 Deadlatch 告诉我你能帮我做什么,然后做一件给我看✓ 如果 VS Code 说正在使用 Deadlatch,或回答中出现 Deadlatch 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 VS Code 帮助页面核实 · 你的界面可能因版本略有不同
Claude Code
claude mcp add --scope user deadlatch -- uvx deadlatch --policy your-value --portfolio your-valueClaude Desktop (claude_desktop_config.json)
{
"mcpServers": {
"deadlatch": {
"command": "uvx",
"args": [
"deadlatch",
"--policy",
"your-value",
"--portfolio",
"your-value"
]
}
}
}Cursor (~/.cursor/mcp.json)
{
"mcpServers": {
"deadlatch": {
"command": "uvx",
"args": [
"deadlatch",
"--policy",
"your-value",
"--portfolio",
"your-value"
]
}
}
}VS Code (mcp.json)
{
"servers": {
"deadlatch": {
"type": "stdio",
"command": "uvx",
"args": [
"deadlatch",
"--policy",
"your-value",
"--portfolio",
"your-value"
]
}
}
}这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
依据这个服务器的连接方式和各应用自己的文档,检查于 2026年11月10日。
在你的电脑上运行,适用于
ClaudeGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatRaycast
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月14日
注册名称已通过 GitHub 账户 Diabloluo 验证,该账户拥有此仓库
代码最后更新于29天前
使用 MIT
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
它在你的电脑上运行;我们只能读取互联网端点的工具列表
提问、分享技巧或报告无法使用。按“有帮助”数量排序。
还没有评价
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 3 项适用的基础检查中通过了 3 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
GitHub 仓库最后更新于29天前,最新版本(0.1.2)于2个月前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Python (uv)。
同一分类中有:Spree Commerce developer docs for AI agents, Stripe MCP, Sessy — Amazon SES observability
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:↓ 每周下载量i★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Spree Commerce docs for AI coding agents: build headless B2B and marketplace ecommerce on its APIs.
MCP server integrating with Stripe - tools for customers, products, payments, and more.
Read-only Amazon SES observability: search events, inspect bounces, pull delivery stats.
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
The pre-trade latch for your trading agent. Advisory-only.
Three things you need to know before anything else:
init / append / repair / prune / shadow report) are supported on Linux and macOS only. On Windows the package still imports, and the rule engine / Guard / CLI / MCP still compute decisions; those write paths fail closed with audit_platform_unsupported. Offline verify / read of a stopped snapshot remain available. Windows MCP is a limited integration path, not a full trusted audit chain.Honest boundary (please read): Deadlatch is advisory. It cannot force an agent that never calls it to call it, and it cannot stop an agent that ignores a BLOCK from submitting the order somewhere else. Whether the agent calls the guard and honors the result is the integrator's decision. Do not rely on this tool as a guarantee against loss — it is a gate, not an insurance policy.
The current install path is the verified PyPI deadlatch==0.1.2, published on 2026-09-22. The stable GitHub v0.1.2 Release targets b072e8a4d4b053e1d5a428dbb9c47e06652fbf4c; its wheel/sdist assets match the PyPI originals.
pip install deadlatch==0.1.2
The published MCP Registry name is io.github.Diabloluo/deadlatch at version 0.1.2, verified active/latest on 2026-09-22. The local server.json matches that published version. The command below starts the verified PyPI package directly.
MCP-first start:
uvx --from deadlatch==0.1.2 deadlatch-mcp --policy policy.yaml --portfolio portfolio.json
--policy and --portfolio are required local files. --audit-path and --kill-switch-path are optional. Use fictional or your own simulated inputs only. Deadlatch is advisory-only: it never places orders and cannot stop an agent that never calls it. Option orders must use the broker's unique full contract code as symbol. A historical GitHub pre-release remains at v0.1.0.dev1; it is not the current install path.
Then:
PASS → BLOCK → local audit. Windows can import the package and run rule computation; it is not the audit-write Quick Start.That GitHub issue is public. Do not paste accounts, positions, orders, API keys, tokens, customer names, or private paths. Security defects must go through GitHub Security Advisories, not a public issue.
All three quick starts use fictional data and a temporary audit path. They are executed from the same source scripts by the test suite, so they cannot drift from the documentation. Full audit-write / MCP Quick Start requires Linux or macOS. Windows may import the library and evaluate rules; it will not initialize or append a durable audit collection.
pip install dist/deadlatch-*.whl # or: pip install -e .
python docs/quickstart/python.py
Shows Guard.from_policy(...) → Order / Portfolio → guard.check(...): a valid order returns PASS / 0; an oversized order returns BLOCK / 3 with the hit rules; on BLOCK the example caller stops — no broker call is ever made.
bash docs/quickstart/cli.sh # requires `deadlatch` on PATH
Creates fresh inputs in a temp directory (dynamic timestamps — never goes stale), then runs deadlatch check for PASS (exit 0), BLOCK (exit 3), an input error (exit 4), and a --json check, plus shadow report --json over the audit.
python docs/quickstart/mcp_client.py # requires `deadlatch` installed
Starts deadlatch-mcp as a real subprocess over stdio, lists the five tools, and calls check_order once for PASS and once for BLOCK. policy / portfolio / audit paths are server startup configuration — an agent cannot swap them as tool arguments. BLOCK is a constraint the caller must honor; technically the guard cannot force a fully bypassing agent to call it.
| Deadlatch is | Deadlatch is not |
|---|---|
| A local, deterministic risk gate evaluated before you submit | A signal generator, recommender, or portfolio optimizer |
| A library, a CLI, and a stdio MCP server — no broker connectivity, no policy mutation | A broker adapter, an execution engine, or a market feed |
| An auditable check: every evaluation is written to a local JSONL log | A cloud service, a database, or a telemetry sink |
| USD-only, single-leg orders, one snapshot per check (v0.1) | Multi-leg, multi-currency, Greeks/IV-aware (see limitations) |
Who should not use it: anyone expecting a profit guarantee, a backtest engine, a portfolio manager, or a tool that enforces itself. If the agent never calls the guard, or ignores a BLOCK, nothing in this repository can stop it.
exit 3); input/config errors → exit 4; internal errors → exit 5. An uncertain state is never reported as PASS.symbol must be the broker's unique full contract code; never reuse an underlying ticker across different expiries, strikes, or rights.exit 4); the MCP account-status tool fail-closes on mismatch.Write surface: the tool never modifies policy, portfolio, or kill-switch state, never connects to a broker, and never places an order. Two kinds of intentional local file writes exist:
Guard.check() / check_order append one sanitized v2 record to a UTC day shard next to the logical audit path (30-day retention). Append is a bounded tail write under a shared lock; it does not rewrite history. A new collection needs one explicit deadlatch audit init (or initialize_audit_state) before append; Guard/MCP never auto-migrate. deadlatch shadow report and deadlatch audit prune delete whole shard files that fall outside the 30-calendar-day window. deadlatch audit repair --quarantine still uses lock/tmp files and os.replace when it isolates a truncated tail. Ordinary append is not crash-atomic across files. POSIX locks are cross-process. v0.1.2 durable audit writes are Linux/macOS only; Windows writers receive audit_platform_unsupported and do not skip directory fsync to report success.deadlatch migrate --output writes the migrated document only when you explicitly pass --output.The public contract for these rules, Decimal thresholds, exit codes, and option-symbol requirements is docs/rules-spec.md.
| # | Rule | What it guards |
|---|---|---|
| R1 | kill_switch | Global switch: off / full (block everything) / reduce_only (allow only inferred closing orders) |
| R2 | input_validity | Order passes schema, version gate, currency consistency, finite amounts (violations → exit 4) |
| R3 | max_order_quantity | Single-order quantity limit |
| R4 | max_order_value | Single-order notional limit (options: price × multiplier × quantity) |
| R5 | max_symbol_exposure | Exposure per underlying (options by strike × multiplier × quantity) |
| R6 | max_total_exposure | Portfolio gross exposure ratio |
| R7 | cash_margin_check | Post-trade cash floor and short-option margin |
| R8 | max_daily_loss | Daily loss ratio (PnL / day-start equity) |
| R9 | max_drawdown | Drawdown ratio from peak |
| R10 | order_time_validity | Order age / future timestamps (unparseable → fail-closed BLOCK) |
| R11 | data_freshness | Portfolio snapshot freshness (future snapshot → fail-closed) |
| R12 | missing_data_fail_closed | Missing/null/ill-formed portfolio data → exit 3 (data unusable = risk) |
Optional rules (R3–R7) are toggled by their config keys in policy.yaml; a missing optional key must be declared in acknowledged_disabled or the policy is rejected (exit 4). Mandatory rules (R1, R2, R8–R12) can never be disabled.
| Code | Meaning |
|---|---|
0 | PASS — the order is allowed as given |
2 | WARN — proceed only if your execution policy explicitly allows warnings |
3 | BLOCK — the order must not be submitted (risk rule or fail-closed data) |
4 | Input / configuration error — the caller misused the API, not a risk event |
5 | Internal / rule exception — treated as BLOCK (fail-closed) |
In shadow mode the internal verdict is recorded (shadow_verdict) while the external projection is PASS / 0; kill-switch hits and exit 4/5 are never projected away.
Schemas are versioned JSON Schema 2020-12 files shipped inside the package: order, portfolio, policy, result, audit-record, shadow-report, audit-maintenance-result, audit-prune-result, audit-write-state, audit-state-result. Explicit offline migration is available for legacy documents:
deadlatch migrate --kind order --input order_v1.json [--out