Skip to main content
Glama
zzmmgg654321-dev

mcp-han

by zzmmgg654321-dev
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault

No arguments

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
check_textA

检查中文文本的排版、标点、常见错别字和专有名词大小写。

这是只读操作，不会修改任何东西。

Args:
    text: 要检查的文本。Markdown 也行；代码块、行内代码、URL、邮箱、
        HTML 标签和公式会被自动跳过。
    rules: 只跑指定规则，逗号分隔（如 "typo,pangu-space"）；用 "-" 前缀排除
        （如 "-dup-punct"）；留空表示默认规则集（18 条里除 quote-switch 之外的全部）。
    severity: 只看某个级别，逗号分隔，可选 error / warn / style。
    limit: 最多列出多少条问题，默认 30。
fix_textA

自动修复中文文案的排版问题，返回修复后的全文。

默认只套用「安全」规则（不会动代码块、行内代码、URL），
并会告诉你改了哪些地方、还有哪些需要人工确认。

Args:
    text: 要修复的文本。
    rules: 只跑指定规则，逗号分隔；用 "-" 前缀排除。点名某条平时不自动跑的
        规则（例如 "dup-punct"）时它也会被套用。
    quote_style: 引号风格——curly（默认，“”）/ corner（「」）/ keep（不动）。
count_textA

统计字数、段落、句子、预计阅读时长，并检查常见平台的字数限制。

具体平台（小红书、公众号、短信、X）的超限情况会一起返回。

Args:
    text: 要统计的文本。
    platforms: 只看指定平台，逗号分隔，如 "xhs_title,mp_digest"；留空表示全部。
list_rulesA

列出全部校对规则（id、级别、能否自动修复、说明）。

想知道 rules 参数里能写什么，或者想了解某条规则的边界时用这个。

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4.3/5.0

Scored across 4 tools

Disambiguation5/5

Each tool targets a distinct operation: checking reports issues, fixing applies corrections, counting provides statistics, and listing rules exposes metadata. There is no meaningful overlap between them.

Naming Consistency5/5

All tool names follow a consistent verb_noun snake_case pattern: check_text, fix_text, count_text, list_rules. The pattern is uniform and predictable.

Tool Count5/5

Four tools is well-scoped for a text proofreading utility. Each tool fills a clear role with no redundancy or bloat.

Completeness5/5

The set covers the full workflow of text proofreading: inspect, fix, quantify, and learn about available rules. There are no obvious dead ends or missing core operations for this domain.

Maintenance

ActivityMaintained
ResponsivenessNo issues

Resources