Kaidn

io.kaidn由 kaidn.io 发布v0.4.0更新于 Oct 24, 2026

Explain fraud verdicts with evidence, surface account rings, and see who has burned other operators.

已验证STDIO仅桌面安全与监控数据与分析

概览

AI 生成的概览

Kaidn 的欺诈评分 MCP 服务器,让助手解释欺诈判定、处理审核队列,并调查可疑邮箱、IP 和设备。

可以做什么
  • 读取判定、评分与原因汇总,并按判定或类型筛选已评分事件
  • 解释单个事件触发的每项检查及其原始证据
  • 按分数拉取审核队列,并查看当前租户生效的权重与阈值
  • 调查单个实体(邮箱、IP 或设备)的补充信息、网络信誉与相关事件
  • 检查邮箱、IP 或电话的一次性域名、代理/VPN/Tor、运营商与滥用记录
  • 为新事件评分;仅在开启写入时,把实体加入允许/阻止名单或标注结果
适用场景
适合使用 Kaidn 欺诈评分、希望用自然语言弄清某次注册或支付为何被拦截、某设备或 IP 还关联了什么、以及审核队列里有什么的情况。也适合在调整规则前评估当前会被拦截的事件。
运行要求
通过 npm 包 @kaidn/mcp 以 stdio 在本地运行,需要 Node.js 18 或更高版本。需要 Kaidn 账户和 API 密钥,且只能通过 KAIDN_API_KEY 环境变量提供。可选配置包括 KAIDN_API_URL、KAIDN_MCP_ALLOW_WRITES、KAIDN_MCP_MAX_QUOTA_CALLS 以及 HTTP 传输相关变量。需要能访问 Kaidn API 的网络。
安装前请注意
服务器持有你的 Kaidn API 密钥,能访问它的人即可消耗你的配额;请保持仅监听本机,或在绑定更广接口前设置 KAIDN_MCP_HTTP_TOKEN。部分工具每次调用会消耗配额,受 KAIDN_MCP_MAX_QUOTA_CALLS 限制。写入默认关闭;启用 KAIDN_MCP_ALLOW_WRITES 会开放 add_to_list 和 label_outcome,它们会修改租户数据。被调查的邮箱、IP 和设备会发送到 Kaidn 的 API。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Kaidn,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Desktop only,通过 STDIO。 STDIO 服务会启动本地进程,因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

README

[Kaidn]

[npm version] [MCP registry] [license MIT] [docs]

Kaidn MCP

Model Context Protocol server for the Kaidn fraud-scoring API.

Investigate fraud in plain English — "why was this signup blocked?", "what else has this device touched?", "what's in the review queue this morning?"

  • Evidence, not just a score. Every reason carries the raw numbers behind it, so a model can explain a verdict rather than guess at it.
  • Read-only by default. Nothing changes your tenant unless you opt in.
  • Quota-guarded. An agent in a loop cannot spend your month in ten minutes.
  • Any client. MCP is an open protocol — stdio locally, Streamable HTTP for remote and hosted agents.

Requirements

Node.js 18 or newer, and an API key from your Kaidn dashboard.


Getting started

First, install the Kaidn MCP server with your client. Standard config works in most of the tools:

json
{  "mcpServers": {    "kaidn": {      "command": "npx",      "args": ["@kaidn/mcp@latest"],      "env": { "KAIDN_API_KEY": "your_key" }    }  }}
Claude Code
bash
claude mcp add kaidn --env KAIDN_API_KEY=your_key -- npx @kaidn/mcp@latest
Claude Desktop

Add the standard config to claude_desktop_config.json, then restart Claude. Settings → Developer → Edit Config opens the file.

Cursor

Settings → MCP → Add new MCP Server, or add the standard config to .cursor/mcp.json in your project (or ~/.cursor/mcp.json for every project).

VS Code
bash
code --add-mcp '{"name":"kaidn","command":"npx","args":["@kaidn/mcp@latest"],"env":{"KAIDN_API_KEY":"your_key"}}'
Windsurf

Add the standard config to ~/.codeium/windsurf/mcp_config.json.

Cline

Add the standard config to cline_mcp_settings.json via the MCP Servers icon → Configure MCP Servers.

Zed

Add to settings.json under context_servers, using the same command, args and env as the standard config.

Anything else

Any MCP client takes a command, args and an env block. Use the standard config above. If the client can only reach the server over the network rather than spawning a process, see Streamable HTTP.


Configuration

OptionEnvironment variableDefaultPurpose
KAIDN_API_KEYrequiredYour secret key. Environment only — never a flag, never a tool argument.
KAIDN_API_URLhttps://api.kaidn.ioAPI base URL
--allow-writesKAIDN_MCP_ALLOW_WRITES=1offRegister the mutating tools
KAIDN_MCP_MAX_QUOTA_CALLS100Quota ceiling per process
--httpKAIDN_MCP_TRANSPORT=httpstdioServe Streamable HTTP
--host <addr>KAIDN_MCP_HOST127.0.0.1HTTP bind address
--port <n>KAIDN_MCP_PORT8765HTTP port
KAIDN_MCP_HTTP_TOKENunsetRequire Authorization: Bearer on HTTP
--helpShow usage
--versionShow the version

Precedence: CLI flags override environment variables.

The API key is deliberately env-only. A key passed as a flag leaks into process listings and shell history.


Transports

TransportUse it forEndpoint
stdio (default)local clients that spawn a subprocess—
Streamable HTTPremote agents, containers, anything off-machinePOST /mcp

HTTP+SSE is deliberately absent: deprecated in the 2025-03-26 spec and sunset in June 2026.

Streamable HTTP

bash
npx @kaidn/mcp@latest --http --port 8765

Stateless — a fresh server per request, nothing shared between callers — so it sits behind a load balancer without surprises. GET /health is unauthenticated so an orchestrator can check liveness without holding the token.


Docker

bash
docker build -t kaidn-mcp .
bash
# stdio — behaves like the npx invocationdocker run -i --rm -e KAIDN_API_KEY=your_key kaidn-mcp
# HTTP — for remote agentsdocker run --rm -p 8765:8765 \  -e KAIDN_API_KEY=your_key \  -e KAIDN_MCP_TRANSPORT=http \  -e KAIDN_MCP_HOST=0.0.0.0 \  -e KAIDN_MCP_HTTP_TOKEN=your_token \  kaidn-mcp

Multi-stage build, runs as the unprivileged node user, with a healthcheck.


Security

The server holds your API key. Whoever can reach it can spend your quota, so the defaults are conservative and the guards fail closed rather than warning.

  • Binds 127.0.0.1, and refuses to start on a wider interface unless KAIDN_MCP_HTTP_TOKEN is set. It stops with an explanation rather than quietly exposing your account.
  • Read-only by default. add_to_list and label_outcome exist only with --allow-writes.
  • set_config and forget_subject are never exposed, in any mode. One silently changes the verdict on every future event; the other is irreversible GDPR erasure. Both belong in the dashboard, in front of a human.
  • Quota ceiling per process, with remaining budget reported on every costing response. A reservation that would overshoot is refused outright rather than partially spent.
  • The key never crosses the tool boundary — not as a parameter, not in output, not in an error.

Tools

Two things govern every tool: whether it spends quota, and whether it changes anything.

Read-only — available by default

ToolCostWhat it does
get_statsfreeVerdict, score and reason rollups over a rolling window. Start here.
list_eventsfreeScored events, newest first, filterable by verdict or type, searchable by fingerprint or user id
explain_eventfreeEvery check that fired on one event, with the raw evidence
triage_queuefreeEverything on review, highest score first
get_configfreeEffective weights and thresholds for this tenant
investigate_entity1 row¹Enrichment, network reputation and related events for one entity
check_email1 rowDisposable domain, deliverability, fraud score, abuse history
check_ip1 rowProxy, VPN, Tor, datacenter ASN, geo, abuse history
check_phone1 rowValidity, line type, carrier, fraud score
score_event1 rowScore a new event (also records it)

¹ Free when the entity is a device_id; enrichment only costs on email or IP.

Mutating — require --allow-writes

ToolWhat it does
add_to_listAdd an entity to the allow or block list
label_outcomeReport a confirmed fraud / chargeback / legit outcome

Worked examples

The tools are designed to be chained. These are the flows they were built for.

Morning triage

You: What happened overnight, and what needs me?

The model calls get_stats for the shape of the last 24 hours, then triage_queue for the events sitting on review, then explain_event on the worst one. You get a ranked list with the reasoning attached, rather than a dashboard you still have to read.

"Why was this customer blocked?"

You: Event evt_8f21c — a customer says they were wrongly blocked.

explain_event returns every check that fired with its raw evidence — the datacenter ASN it matched, how many accounts shared the device, the velocity count. Enough to answer the customer, or to conclude the rule was wrong and needs tuning.

Working outward from one signal

You: Is 194.x.x.x a one-off or part of a ring?

investigate_entity returns enrichment and network reputation for the IP plus every recent event it appears in. If the same device ids keep recurring, that is a ring rather than a coincidence.

Checking a rule change before making it

You: If I dropped the velocity weight, what would stop being blocked?

get_config reads the current weights; list_events with verdict: "block" shows what is currently caught. The model can tell you which of those hang on the check you are about to weaken.


Error handling

Failures come back as tool errors with a readable message, not exceptions — the model can act on them.

You seeMeaningFix
KAIDN_API_KEY is not setServer started without a keySet it in the client's env block
Kaidn error: 401 …Key rejectedRotate or re-copy it from the dashboard
Kaidn error: 429 …Rate limitedSlow down; per-key throttling is by the minute
Session quota ceiling reached (100/100 …)The guard stopped an expensive runRaise KAIDN_MCP_MAX_QUOTA_CALLS deliberately, or restart
No event <id> in the most recent 200 eventsEvent is older than the scan windowPage back with list_events using offset
Supply exactly one of email, ip or device_idAmbiguous investigationAsk about one entity at a time
Refusing to bind <host> without authenticationNon-loopback HTTP with no tokenSet KAIDN_MCP_HTTP_TOKEN, or bind 127.0.0.1

Errors never contain your API key.


Troubleshooting

The client shows no tools. Check the client's MCP log for the startup line. kaidn-mcp: ready (stdio, …) on stderr means the server is up and the problem is on the client side. Nothing at all usually means npx could not resolve the package or Node is older than 18.

It starts, then exits immediately. Almost always a missing KAIDN_API_KEY. The message says so on stderr; some clients hide stderr, so run it in a terminal to see it.

add_to_list and label_outcome are missing. Working as designed. They need --allow-writes.

set_config and forget_subject are missing. Also by design, and they are not available in any mode. See SECURITY.md.

HTTP mode refuses to start. You bound something other than loopback without a bearer token. That is the guard working — the process holds your API key.

Everything is slow. The enrichment checks make live upstream calls. get_stats, list_events, explain_event and triage_queue are free and fast; prefer them when reading history.

Check the server independently of the client:

bash
node dist/index.js --help                 # no key requiredKAIDN_API_KEY=your_key npm start          # should print a ready line

Support


Run from source

bash
git clone https://github.com/Kaidn-io/kaidn-mcp.gitcd kaidn-mcpnpm installnpm run buildnpm test
bash
claude mcp add kaidn --env KAIDN_API_KEY=your_key -- node /absolute/path/to/kaidn-mcp/dist/index.js

To check it starts without a client:

bash
KAIDN_API_KEY=your_key npm start

It prints kaidn-mcp: ready (stdio, read-only, quota ceiling 100) to stderr and then waits on stdin — that is the MCP transport, so the silence is correct.


Why the evidence matters

Kaidn's engine is rules-first and explainable: every reason carries the raw numbers behind it. A bare score gives a model nothing to reason about, while checks[] with evidence attached gives it something to explain. That is the difference between explain_event being useful and being decorative.

Rules decide. The model narrates.


Project

Licence

MIT

来源:README.md,提交 d3cc1bc

工具

0
SourceWeft 尚未在沙箱中启动过该软件包,因此其工具未知。

版本历史

1
  1. v0.4.0最新Sep 16, 2026

评分

已满足适用检查项的 50%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通25 分

    请保持端点能够响应 MCP 握手;SourceWeft 每 30 天探测一次。

  • 已声明认证方式10 分

    请在注册中心条目中声明凭据请求头,或保持端点能够响应探测,以便判定其认证方式。

  • 已列出工具15 分

    请让服务器在无凭据时响应 tools/list,或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分