Relayshield Firewall

io.github.nzdsf2-gif由 GitHub 账号 nzdsf2-gif 发布v0.3.0更新于 Nov 22, 2026

RelayShield MCP Proxy Firewall. Screens every MCP tool call. 50 free calls, then $49/month.

已验证Streamable HTTP可网页运行金融安全与监控

概览

AI 生成的概览

RelayShield 把泄露查询、SIM 卡调换、仿冒域名、恶意软件扫描和凭据暴露等威胁情报检查作为 MCP 工具提供给助手。

可以做什么
  • 查询邮箱泄露记录、SIM 卡调换与 eSIM 状态、仿冒域名及 OAuth 应用暴露情况
  • 检查信息窃取日志、被盗会话、非人类身份凭据以及公开 GitHub 仓库中的密钥
  • 通过多个引擎扫描网址和文件,并轮询获取判定结果
  • 评估 MCP 服务器注册表风险与供应商供应链暴露
  • 检查 EVM 钱包的链上风险
适用场景
当助手需要核查邮箱、电话号码、域名、网址、文件、钱包地址或 MCP 服务器是否存在欺诈、钓鱼或凭据暴露风险,或审计某个代理与供应商所持有的权限时适用。
运行要求
远程端点 tnt-demo.proxy.relayshield.net,要求 OAuth 认证。README 另提供本地 Python 包(pip 或 uvx),需配置 RELAYSHIELD_API_URL,并设置 RELAYSHIELD_API_KEY(订阅)或 RELAYSHIELD_X_PAYMENT(按次付费)之一。
安装前请注意
多数工具按次计费:按次付费通过 Base 链上的 USDC 每次收取约 0.05–0.50 美元,订阅在免费额度用完后需付费。RELAYSHIELD_API_KEY 与 RELAYSHIELD_X_PAYMENT 属于机密,只应设置其中一个。查询会把邮箱、电话号码、钱包地址等个人数据发送到 RelayShield 的 API。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Relayshield Firewall,将其添加到工作区。
  2. 连接 所需的 凭据。它们会被私密存储,绝不会在公开页面上展示。
  3. 为需要使用其工具的对话启用该服务。

Web executable,通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体,或 SourceWeft 对话中。智能体会读取该服务器的安装指南,先向你展示发布者、端点和登录方式,经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/io.github.nzdsf2-gif%2Frelayshield-firewall/install.md,并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前,先告诉我它的发布者、端点和登录方式,等我确认。不要把 API 密钥写进命令或我会提交的文件;问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。 客户端会在首次连接时完成 OAuth 登录。

{
  "mcpServers": {
    "relayshield-firewall": {
      "type": "http",
      "url": "https://tnt-demo.proxy.relayshield.net/mcp"
    }
  }
}

README

relayshield-mcp

mcp-name: io.github.nzdsf2-gif/relayshield-mcp

RelayShield security intelligence as an MCP server — plug breach detection, SIM swap detection, domain lookalike monitoring, OAuth supply chain watchlist, and URL/file scanning directly into Claude and any MCP-compatible AI agent.

Tools

ToolWhat it doesPAYG price
check_breachEmail breach lookup — 13 billion+ compromised-account records$0.10 USDC
check_sim_swapSIM swap / eSIM detection via live carrier data$0.25 USDC
check_domain_lookalikesTyposquat and lookalike domain detection with cert transparency$0.50 USDC
check_oauth_watchlistOAuth-app breach + stolen-token exposure from the stealer-log corpus$0.30 USDC
check_infostealerInfostealer malware log lookup — credentials harvested from infected devices$0.15 USDC
scan_walletEVM wallet on-chain risk check$0.10 USDC
scan_urlURL malware/phishing scan across 70+ engines (async)$0.05 USDC
scan_fileBinary malware scan across 70+ AV engines (async)$0.10 USDC
check_scan_resultPoll for verdict after scan_url / scan_filefree
check_mcp_registry_riskTyposquat/IOC/registration-age check for MCP servers$0.35 USDC
check_prompt_injection_breachBreach exposure sourced from AI-agent prompt-injection attacks$0.35 USDC
check_supply_chainUp to 10 vendor domains checked for breach/infostealer exposure$0.10 USDC
check_session_riskActive/reusable stolen session (cookie/token) exposure check$0.30 USDC
check_nhi_exposureNon-human-identity credential exposure — API keys, service tokens, PATs$0.40 USDC
check_secret_scanSecrets exposed in public GitHub repositories$0.35 USDC

check_oauth_watchlist, check_supply_chain, check_session_risk, check_nhi_exposure, and check_secret_scan cover related ground — connected-app, session, and machine-credential exposure for an identity or its supply chain — and are a natural set to use together when vetting an agent's current authority, not just a login.

Access modes

Subscription — API key from api.relayshield.net/developers. All 15 tools available. Free tier: 100 calls/month. Paid tiers from $29/month.

Pay-as-you-go — No API key needed. Pay per check in USDC on Base (x402 protocol). Set RELAYSHIELD_X_PAYMENT with your payment proof. All 15 tools available ($0.05–$0.50/check, check_scan_result free). Call a tool with no payment set to receive pricing and payment instructions.

Discovery — Set neither key nor payment. Tool calls return payment requirements and a subscription link.

Install

bash
pip install relayshield-mcp

Or run without installing:

bash
uvx relayshield-mcp

Configure Claude Desktop

Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

Subscription (RelayShield API key):

json
{  "mcpServers": {    "relayshield": {      "command": "relayshield-mcp",      "env": {        "RELAYSHIELD_API_URL": "https://api.relayshield.net",        "RELAYSHIELD_API_KEY": "your-relayshield-api-key-here"      }    }  }}

Pay-as-you-go (x402 USDC on Base):

json
{  "mcpServers": {    "relayshield": {      "command": "relayshield-mcp",      "env": {        "RELAYSHIELD_API_URL": "https://api.relayshield.net",        "RELAYSHIELD_X_PAYMENT": "your-x402-payment-proof-here"      }    }  }}

Quit and relaunch Claude Desktop after editing.

Configure Claude Code (CLI)

bash
claude mcp add relayshield \  --command relayshield-mcp \  --env RELAYSHIELD_API_URL=https://api.relayshield.net \  --env RELAYSHIELD_API_KEY=your-relayshield-api-key-here

Free checks server (no key, no signup)

relayshield-free-mcp ships in the same package and exposes RelayShield's free, keyless threat-intel checks as four MCP tools. It is the funnel into the paid server above: every summary links the deeper paid checks where they apply.

ToolWhat it doesKey needed
check_linkScreen 1–25 URLs for phishing/malware (IOC corpus + threat feeds + domain age)no
check_walletScreen a crypto wallet before paying it (chain auto-detected)no
check_emailScore a suspicious email for phishing signals; checks its links toono
check_breachEmail vs 13B+ breached accountspartner key only
bash
pip install relayshield-mcp# or: uvx relayshield-mcprelayshield-free-mcp

Claude Desktop — add to claude_desktop_config.json:

json
{  "mcpServers": {    "relayshield-free": {      "command": "relayshield-free-mcp",      "env": {        "RELAYSHIELD_API_URL": "https://api.relayshield.net",        "RS_SOURCE_TAG": "mcp-free-claude"      }    }  }}

ChatGPT — ChatGPT connects to MCP servers through Developer Mode connectors, which require a remote HTTP endpoint; it does not launch a local stdio server. A hosted RelayShield MCP endpoint is planned — until then, use Claude Desktop, Claude Code, Cursor, or any other stdio-capable MCP client. Set RS_SOURCE_TAG=mcp-free-chatgpt once the hosted endpoint is live so usage is attributed to the ChatGPT channel. check_breach stays disabled until a partner key is set via RELAYSHIELD_API_KEY.

Partner keys — distributors (Claude, ChatGPT, registries) each get their own RelayShield partner key with a per-key daily call cap, set via RELAYSHIELD_API_KEY. Separate keys per channel mean one channel's abuse never takes down the others, and RS_SOURCE_TAG attributes usage per channel. The server runs fine without any key — link, wallet, and email checks stay keyless on the free tier.

Usage examples

Once configured, ask Claude:

Check whether [email protected] has been breached.
Has there been a SIM swap on +14155551234?
Check acme.com for lookalike domains.
Are any OAuth apps connected to [email protected] in a recent breach?
Scan this URL for malware: https://suspicious-link.example.com

For URL and file scans, Claude automatically polls check_scan_result every 5 seconds until the verdict is ready.

Environment variables

VariableDescription
RELAYSHIELD_API_URLAPI Gateway base URL (required)
RELAYSHIELD_API_KEYRelayShield subscription key (subscription mode) — get one at api.relayshield.net/developers
RELAYSHIELD_X_PAYMENTx402 payment proof — USDC on Base (pay-as-you-go mode)

Set RELAYSHIELD_API_KEY or RELAYSHIELD_X_PAYMENT — not both. API key takes priority if both are set.

Links

来源:README.md,提交 ca6400c

工具

0
该服务器需要 API 密钥等凭据,因此 SourceWeft 无法在没有凭据的情况下读取其工具,也未收录。

版本历史

1
  1. v0.3.0最新Nov 22, 2026

评分

已满足适用检查项的 75%

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 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 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

    请在仓库或注册中心条目中声明许可证。