pleamo
Officialpleamo MCP server
将 pleamo 的 AI 诈骗/钓鱼 URL 检查以 MCP 工具 的形式暴露出来,让任何 MCP 客户端(Claude Desktop、Cursor 或你自己的 agent)都可以在打开或推荐链接之前,向 pleamo 询问"这个链接安全吗?"
它是一个轻量的、经过认证的托管 pleamo API 代理——每次检查都遵循保护服务的相同每用户和全局上限。
工具
工具 | 功能 |
| 判断一个 URL:判定(安全/可疑/危险)、严重程度、置信度、原因 |
| 标记被错误拦截的域名以供审核 |
| 你的套餐 + 今日 AI 检查用量 |
Related MCP server: Verdict
设置
获取一个 pleamo API 密钥(从
https://dash.pleamo.app/keys的仪表板获取可撤销的密钥)。将你的 MCP 客户端指向此服务器。对于 Claude Desktop,添加到
claude_desktop_config.json:
{
"mcpServers": {
"pleamo": {
"command": "npx",
"args": ["-y", "pleamo-mcp"],
"env": {
"PLEAMO_TOKEN": "your-api-key-here"
}
}
}
}重启客户端。然后你就可以说类似 "用 pleamo 检查这个链接:https://paypa1-login.example" 这样的话,agent 就会调用 check_url。
环境变量
变量 | 默认值 | 说明 |
| — | 必填。pleamo API 的 Bearer 令牌。 |
|
| 本地开发时覆盖(例如 |
开发
npm install
npm run verify # lint + format + unit tests
npm start # runs the stdio server (expects an MCP client on stdin)快速 stdio 冒烟测试(列出工具):
printf '%s\n' \
'{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"smoke","version":"0"}}}' \
'{"jsonrpc":"2.0","method":"notifications/initialized"}' \
'{"jsonrpc":"2.0","id":2,"method":"tools/list","params":{}}' \
| node src/server.js远程(托管)替代方案
如果你的客户端支持 远程 MCP 服务器,你根本不需要这个本地进程——直接连接到托管端点:
https://dash.pleamo.app/api/mcp它通过 HTTP 使用 JSON-RPC 通信(同样的三个工具),并使用 pleamo API 密钥作为 Bearer 令牌进行认证。在 https://dash.pleamo.app/keys 创建一个可撤销的密钥。这个本地 stdio 服务器适用于只支持 stdio 的客户端(例如当前的 Claude Desktop)。
备注
认证 / 令牌 — 从仪表板(
/keys)获取一个可撤销的 API 密钥,并将其设置为PLEAMO_TOKEN。(原始会话令牌也可以,但密钥才是正确、可撤销的选择。)传输方式 — 此包使用 stdio;上面的托管
/api/mcp是远程 Streamable-HTTP 变体。另一个 MCP 方向 — 让 扩展 通过用户自己的 agent 路由检查(BYO-via-MCP)已在 pleamo/pleamo-chrome-extension 的扩展源码中跟踪。
Available Tools
3 toolscheck_urlCheck a URL for scams / phishingA
Ask pleamo whether visiting a URL is likely a scam or phishing site. Returns a verdict (safe/suspicious/dangerous), severity, confidence, and a plain-English reason. Use before opening or recommending an unfamiliar link.
Inputs: url (required).
get_statusGet pleamo plan + usageA
Return the signed-in account's plan and today's AI-check usage.
Inputs: no named parameters.
report_false_positiveReport a wrongly-flagged siteA
Tell pleamo a domain was flagged incorrectly, so it can be reviewed and corrected.
Inputs: domain (required), note.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
Each tool serves a clearly distinct purpose: check_url analyzes a URL, report_false_positive submits a correction, and get_status returns account information. There is no meaningful overlap or ambiguity among the three.
All tool names follow the same verb_noun pattern using snake_case: check_url, report_false_positive, get_status. This makes the tool set predictable and easy to navigate.
With only three tools, the server is tightly scoped to its purpose: URL safety checking, correction feedback, and account status. Each tool earns its place and the count is appropriate for such a focused service.
The tool set covers the core workflow: checking URLs, reporting incorrect verdicts, and checking usage/plan status. There are no obvious dead ends or missing operations for the stated domain.
Maintenance
Related MCP Connectors
Unofficial PhishTank MCP — wraps PhishTank API (checkurl.phishtank.com)
Scam and phishing detection for AI agents: safe/warn/danger verdicts for URLs and messages.
URLhaus MCP — wraps abuse.ch URLhaus malware URL database (free, no auth)
URL risk evidence with scoped OAuth/API keys, capped prepaid costs and up to ten URLs per batch.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables checking suspicious URLs for risk without opening them, providing full checkups and lookalike detection.MIT
- AlicenseNot gradedqualityCmaintenanceEnables users to check suspicious text, emails, marketplace listings, job offers, investment pitches, and links through MCP tools, returning an assessment with supporting checks and next-step guidance.Apache 2.0
- AlicenseNot gradedqualityCmaintenanceEnables MCP clients to look up domains, URLs, IPs/ASNs, email addresses, phone numbers, crypto wallets, and business records; run autonomous investigations; collect crawl artifacts; and perform evidence-backed scam checks with traceable provenance.MIT
- AlicenseNot gradedqualityBmaintenanceForwards URL safety scans to a hosted remote MCP endpoint, offering synchronous verdicts, asynchronous task polling, and intent-aware checks that judge whether a page matches the stated reason for visiting. It also enforces the upstream 248-character intent limit locally before sending.63 npmMIT