cs2wt-docs-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
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
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_docsA | 按关键词检索 Counter-Strike 2 Workshop Tools 官方文档的离线全文索引。 何时使用:需要查找 CS2 Workshop Tools 文档中的术语、命令、概念、实体时; 回答任何涉及该工具集用法的技术问题前,应先用本工具定位来源页面。 何时不使用:已知道确切页面标题(或数字 rowid)时,直接调用 get_page 更高效; 与 CS2 Workshop Tools 文档无关的问题不要使用。 返回:JSON,含 count 与 results(每项含 title、url、snippet、score; score 为 bm25,越小越相关)。索引初始化中或刷新失败时返回 status 字段; 后台刷新进行中时额外带 refreshing 字段。 |
| get_pageA | 读取某个文档页面的正文,可按章节只取一部分。 何时使用:已知页面标题(或数字 rowid),需要阅读其内容;或只想读取某章节以控制返回体积。 何时不使用:只知道模糊关键词时,先用 search_docs 定位。 参数:id_or_title 为纯数字时按数字 rowid 查询,否则按页面标题查询; section 为可选的章节标题(不区分大小写,支持部分匹配)。 返回:JSON,含 found、title、url、revid、timestamp、content; 未找到页面或章节时 found 为 false。索引初始化中或刷新失败时返回 status 字段; 后台刷新进行中时额外带 refreshing 字段。 |
| list_pagesA | 列出当前索引收录的全部文档页面。 何时使用:需要了解文档覆盖范围、列举全部页面,或确认某主题是否被收录。 何时不使用:已有明确查询词时,用 search_docs 更合适。 返回:JSON,含 count 与 pages(每项含 title)。索引初始化中或刷新失败时返回 status 字段;后台刷新进行中时额外带 refreshing 字段。 |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 3 tools
Each tool serves a clear, distinct purpose: search_docs for keyword lookup, get_page for retrieving a known page/section, and list_pages for enumerating the index. No overlap or ambiguity between them.
All tools follow the same snake_case verb_noun pattern: search_docs, get_page, list_pages. The naming is perfectly consistent and predictable.
Three tools is an ideal scope for a documentation retrieval server: search, fetch by identifier, and list coverage. Each tool earns its place with no redundancy.
The tool surface fully covers the core workflow for documentation access: discover via search, list available pages, and read page content by title or section. No obvious gaps for the stated purpose.