Skip to main content
Glama
Sign In
noyacg-mcp

noyacg-mcp

by kwkare
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

浏览器登录（自动抓 Cookie）

noy_browser_login

Opens a separate Chrome profile for user sign-in, then saves the NOY_SESSION locally so tools can access noymanga.com without manual cookie copying or restarts.

Instructions

打开一个独立的 Chrome 窗口让用户自己输入账号密码，登录成功后自动读取 NOY_SESSION 并保存到本地，之后所有工具立刻可用（不用重启、不用手动复制 cookie）。 如果这个 profile 之前登录过，会直接复用、不弹窗（约 1 秒完成）——所以可以先无脑调一次 wait 试试。 用法：action=open 只开窗口（马上返回）；action=wait 打开并在 timeout_seconds 内等待保存；action=cancel 关掉窗口。等待超时不会关窗口，用户登完再调一次 wait 即可。 ⚠️ 窗口是本项目专用的独立 profile（~/.noyacg-mcp/browser），不会动用户日常浏览器的登录态。 ⚠️ 只在用户明确要求「帮我登录」时调用，不要自作主张弹窗。

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "noy_browser_login"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionNoopen = 只打开窗口；wait = 打开并等待登录后保存；cancel = 关掉窗口wait
headlessNo无头模式（一般只有 CI / 服务器场景需要）
timeout_secondsNowait 的最长等待时间（秒）；超时不会关窗口，可再次调用

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.6/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations it discloses that a real Chrome window opens, that it uses an isolated project profile at ~/.noyacg-mcp/browser and does not touch the user's daily browser session, that timeouts leave the window open for a re-call, and that a previously logged-in profile reuses silently in about one second. Those are exactly the operational details an agent needs before invoking an openWorld browser tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the core behavior and then the action mapping, with warnings clearly separated. It is slightly repetitive about timeout behavior not closing the window, but overall it stays tight for a tool with this many non-obvious behaviors.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema and an openWorld mutation-like tool, the description covers what the agent must know: what opens, what gets persisted, what happens on timeout, how to cancel, and under what user request to invoke it. Nothing essential for correct invocation is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema already documents action, headless, and timeout_seconds with matching enum descriptions. The description restates action semantics and timeout behavior but adds little beyond what the schema says, so baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

It states a specific verb and resource: open an independent Chrome window, let the user enter credentials, then auto-read and persist NOY_SESSION so all tools become usable. It distinguishes itself from siblings like noy_signin_status and noy_logout by being the only tool that actually captures a session.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives explicit when-to-use guidance: only call when the user explicitly asks to log in, never pop the window up on your own. It also explains the try-wait-first pattern when a profile was logged in before, and maps each action to its behavior.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools