Skip to main content
Glama
pleamo

pleamo

Official
by pleamo

pleamo 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

check_url

判断一个 URL:判定(安全/可疑/危险)、严重程度、置信度、原因

report_false_positive

标记被错误拦截的域名以供审核

get_status

你的套餐 + 今日 AI 检查用量

Related MCP server: Verdict

设置

  1. 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)。

  2. 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

PLEAMO_TOKEN

—

必填。pleamo API 的 Bearer 令牌。

PLEAMO_API_BASE

https://dash.pleamo.app

本地开发时覆盖(例如 http://localhost:4400)。

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 tools
check_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

    A4.4/5.0

    Scored across 3 tools

    Disambiguation5/5

    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.

    Naming Consistency5/5

    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.

    Tool Count5/5

    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.

    Completeness5/5

    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

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables 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
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables 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
    • A
      license
      Not graded
      quality
      B
      maintenance
      Forwards 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 npm
      MIT