MCP Sift

Name: MCP Sift
Author: codespar

作者：codespar版本 0.2.0-alpha.3i★ –i在你的电脑上运行

注册名称io.github.codespar/mcp-sift

安装

概览

作者提供的说明（英文原文）

MCP server for Sift — global ML fraud detection: real-time risk scoring, decisions, event ingestion

PopNx MCP 的三大支柱

这三项永远不会合并成一个分数：意见、测量和人气是不同的东西。

用户评价i暂无评价评价功能将在后续阶段与账户功能一起开放
我们的基础检查i1 项中通过 1 项依据公开信息检查；尚未扫描代码
使用情况i非常新↓ 44/周 · ★ –

它能帮你做什么

我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。

连接方式: 在你的电脑上运行
传输方式: stdio
分类: 网络安全
你需要填写：SIFT_API_KEY, SIFT_ACCOUNT_ID

安装

选择你使用的 AI 应用，然后复制设置。

安装之前

基础检查：1 项中通过 1 项
在你的电脑上运行，拥有你的用户账户的权限（文件、网络、应用）。
需要你自己填写： SIFT_API_KEY, SIFT_ACCOUNT_ID, SIFT_BASE_URL

标为机密的值是你账户的钥匙。千万不要分享给别人，也不要粘贴到聊天里。

你需要

npm已安装 Node.js（用于 npx 命令）

你用的是哪个应用？

ClaudeClaude CodeCursorVS CodeChatGPT

在上方选择你的应用。我们会记住它，下次按钮会显示“安装到 …”。

打开 Claude Desktop → Settings → Developer → Edit Config，把下面的内容粘贴到 claude_desktop_config.json

{
  "mcpServers": {
    "sift": {
      "command": "npx",
      "args": [
        "-y",
        "@codespar/mcp-sift"
      ],
      "env": {
        "SIFT_API_KEY": "your-value",
        "SIFT_ACCOUNT_ID": "your-value",
        "SIFT_BASE_URL": "your-value"
      }
    }
  }
}

在终端中运行这条命令

claude mcp add sift --env SIFT_API_KEY=your-value --env SIFT_ACCOUNT_ID=your-value --env SIFT_BASE_URL=your-value -- npx -y @codespar/mcp-sift

运行前请先填写空着的值。

在 Cursor 中打开

或者自己复制设置

粘贴到项目中的 .cursor/mcp.json，或 ~/.cursor/mcp.json

{
  "mcpServers": {
    "sift": {
      "command": "npx",
      "args": [
        "-y",
        "@codespar/mcp-sift"
      ],
      "env": {
        "SIFT_API_KEY": "your-value",
        "SIFT_ACCOUNT_ID": "your-value",
        "SIFT_BASE_URL": "your-value"
      }
    }
  }
}

浏览器会先询问是否打开应用，然后应用会显示设置并请你确认。密钥的值会留空，由你自己填写。

在 VS Code 中打开

或者自己复制设置

粘贴到项目中的 .vscode/mcp.json

{
  "servers": {
    "sift": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@codespar/mcp-sift"
      ],
      "env": {
        "SIFT_API_KEY": "your-value",
        "SIFT_ACCOUNT_ID": "your-value",
        "SIFT_BASE_URL": "your-value"
      }
    }
  }
}

浏览器会先询问是否打开应用，然后应用会显示设置并请你确认。密钥的值会留空，由你自己填写。

这个服务器在你的电脑上运行，而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。

你的选择通过 Cookie 保存在这台设备上，无需账户。

需要你填写的值

SIFT_API_KEY 机密必填 env
Sift API key. Used in the Events API request body ($api_key) and as the HTTP Basic auth username (empty password) for Score + Decisions APIs.
SIFT_ACCOUNT_ID 必填 env
Sift Account ID. Required for all Decisions API v3 endpoints (path segment /v3/accounts/{account_id}/...).
SIFT_BASE_URL env
Sift API base URL. Defaults to https://api.sift.com.

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。

它能做什么

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。

基础检查i

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8日

✓ 通过
作者与仓库一致
注册名称已通过 GitHub 账户 codespar 验证，该账户拥有此仓库
… 尚未检查
仍在维护
我们还没有从 GitHub 读取这个仓库
… 尚未检查
有许可证
我们还没有从 GitHub 读取这个仓库
– 不适用
端点有响应
它在你的电脑上运行，没有互联网端点
– 不适用
使用 OAuth 登录
在你的电脑上运行，改用本地设置
… 尚未检查
工具描述中没有隐藏指令
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

与“网络安全”中的其他服务器比较i

星标数多于此分类中其他 1004 个服务器的 0%
发布到注册中心的时间比此分类中其他 1004 个服务器的 22% 更新
基础检查结果等于或优于此分类中其他 1004 个服务器的 100%

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。

常见问题

MCP Sift 安全吗？

它在 1 项适用的基础检查中通过了 1 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。

它需要哪些密钥或代码？

你需要填写：SIFT_API_KEY, SIFT_ACCOUNT_ID

它在我的电脑上运行还是在云端？

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）。

它还在维护吗？

GitHub 仓库最后更新于–，最新版本（0.2.0-alpha.3）于5个月前进入注册中心。

哪些应用可以使用它？

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 Node.js。

有什么可以替代它？

同一分类中有：Draugr, Zeqqat, MCP Safety Warden

替代选择

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

Draugr

Security scanning for AI agents: SAST, SCA, secrets, IaC, DAST, ranked by real risk.

作者：draugr-dev非常新今天更新

在你的电脑上运行✓ draugr.dev

安装

Zeqqat

The safe MCP for Dokploy: agents deploy and fix apps without holding keys or seeing secrets.

作者：zeqqat非常新今天更新

在云端运行

安装

MCP Safety Warden

MCP proxy adding security scanning, behavioral profiling, risk gating, and safe tool call execution.

作者：gautamvarmadatla非常新↓ 307/周今天更新

在你的电脑上运行

安装

作者的 README

打开 README

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。

@codespar/mcp-sift

MCP server for Sift — global enterprise ML-based fraud detection.

Third entry in the CodeSpar fraud category after @codespar/mcp-clearsale and @codespar/mcp-konduto. Sift is the global / enterprise counterpart to the two BR-native antifraud servers.

Positioning

	ClearSale	Konduto	Sift
Geography	Brazil	Brazil	Global (US-HQ, ~30 countries)
Founded	2001	2014	2011
Strength	Chargeback history db	Behavioral device intelligence	Multi-abuse-type ML + workflow decisions
Shape	Score + manual review	API-first, tight surface	Event stream in, scores + decisions out
Scope	Order fraud	Order fraud	Payment, account, content, promotion abuse

Also distinct from @codespar/mcp-jumio, which is global KYC / identity verification — a different layer than fraud scoring.

Sift's API shape

Sift is built around three APIs that work together:

Events API (/v205/events) — you POST every interesting signal (account creation, login, order, chargeback, ...) as a $-prefixed event.
Score API (/v205/users/{user_id}/score) — you GET the latest ML score for a user, or POST to force a rescore. Scores are floats in [0, 1] per abuse type (payment_abuse, account_abuse, content_abuse, promotion_abuse).
Decisions API v3 (/v3/accounts/{account_id}/...) — workflows in the Sift console turn scores into Decisions (block_user_payment_abuse, approve_order_payment_abuse, etc). You can apply a decision directly, read the current decisions on a user/order, or fetch the status of a workflow run.

Tools (20)

Tool	Purpose
`send_event`	Send a fraud signal to Sift's Events API (POST /v205/events).
`get_user_score`	Fetch the latest Sift score(s) for a user (GET /v205/users/{user_id}/score).
`rescore_user`	Force Sift to recompute a user's score right now (POST /v205/users/{user_id}/score).
`label_user`	Label a user as fraud or not-fraud via the legacy Labels API (POST /v205/users/{user_id}/labels).
`unlabel_user`	Remove any existing label on a user (DELETE /v205/users/{user_id}/labels).
`apply_decision_to_user`	Apply a workflow Decision to a user (POST /v3/accounts/{account_id}/users/{user_id}/decisions).
`apply_decision_to_order`	Apply a workflow Decision to a specific order (POST /v3/accounts/{account_id}/users/{user_id}/orders/{order...
`get_user_decisions`	Fetch the decisions currently applied to a user (GET /v3/accounts/{account_id}/users/{user_id}/decisions).
`get_order_decisions`	Fetch the decisions currently applied to an order (GET /v3/accounts/{account_id}/orders/{order_id}/decisions).
`get_workflow_run`	Fetch the status of a Sift Workflow run (GET /v3/accounts/{account_id}/workflows/runs/{run_id}).
`send_chargeback`	Send a $chargeback event to Sift's Events API (POST /v205/events).
`send_login`	Send a $login event to Sift's Events API (POST /v205/events).
`send_logout`	Send a $logout event to Sift's Events API (POST /v205/events).
`send_content_status`	Send a $content_status event to Sift's Events API (POST /v205/events).
`link_session_to_user`	Send a $link_session_to_user event to Sift's Events API (POST /v205/events).
`send_custom_event`	Send a custom (merchant-defined) event to Sift's Events API (POST /v205/events).
`apply_decision_to_session`	Apply a workflow Decision to a session (POST /v3/accounts/{account_id}/users/{user_id}/sessions/{session_id...
`apply_decision_to_content`	Apply a workflow Decision to a content item (POST /v3/accounts/{account_id}/users/{user_id}/content/{conten...
`get_session_decisions`	Fetch the decisions currently applied to a session (GET /v3/accounts/{account_id}/users/{user_id}/sessions/...
`get_content_decisions`	Fetch the decisions currently applied to a content item (GET /v3/accounts/{account_id}/users/{user_id}/cont...

Install

npm install @codespar/mcp-sift@alpha

Environment

SIFT_API_KEY="..."         # required, secret

SIFT_ACCOUNT_ID="..." # required for all Decisions API v3 calls SIFT_BASE_URL="..." # optional; defaults to https://api.sift.com

Authentication

Events API — $api_key is injected into the JSON body. The server handles this automatically.
Score API + Decisions API v3 — HTTP Basic, API key as username, empty password. The server handles the base64 encoding.

Pass the raw key in SIFT_API_KEY.

Typical flow

Instrument your app: every signup, login, profile update, order, and chargeback becomes a send_event call with the right $type.
On high-stakes moments (checkout, withdrawal), call send_event with return_score: true to get an inline decision.
Or poll get_user_score / get_order_decisions asynchronously after a workflow run completes.
For manual review outcomes, call apply_decision_to_user or apply_decision_to_order with a Decision ID configured in the Sift console and source: "MANUAL_REVIEW".
When a chargeback is confirmed, send a $chargeback event AND either apply_decision_to_user with a Block decision or label_user with is_bad: true, abuse_type: "payment_abuse". Decisions are preferred for new integrations; Labels are kept for backward compatibility.

Alpha note

Shipped as 0.1.0-alpha.1. All endpoint paths are verified against Sift's official Ruby SDK (SiftScience/sift-ruby): rest_api_path, user_score_api_path, users_label_api_path, user_decisions_api_path, order_decisions_api_path, workflow_status_path, and the Decision ApplyTo path builder.

Scope vs. the original brief:

Shipped & verified: send_event, get_user_score, rescore_user, label_user, unlabel_user, apply_decision_to_user, apply_decision_to_order, get_user_decisions, get_order_decisions, get_workflow_run.
Dropped — not in the public SDK:
get_session_score (/v205/sessions/{session_id}/score) — no equivalent helper in the Ruby SDK; session-level scoring in Sift flows through session-level Decisions and Workflow runs, not a dedicated score endpoint.
list_workflow_runs (GET /v3/accounts/{account_id}/workflows/runs) — only GET /{run_id} is implemented in the public SDK. In practice, Sift surfaces run_ids in event responses rather than via a list endpoint.
get_psychology_score — no such endpoint in the public SDK.

The developers.sift.com reference pages gate deep-link URLs (403 on several paths), so we used the official SDK as the source of truth. Promote to 0.1.0 once a customer confirms (or denies) the dropped endpoints against the full Decisions / Score API reference in Sift's admin console.

Run

# stdio (default — for Claude Desktop, Cursor, etc)

npx @codespar/mcp-sift

HTTP (for server-to-server testing)

MCP_HTTP=true MCP_PORT=3000 npx @codespar/mcp-sift

Enterprise

Need governance, budget limits, and audit trails for agent payments? CodeSpar Enterprise adds policy engine, payment routing, and compliance templates on top of these MCP servers.

License

MIT