yuelinghuashu/story-cli
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| scan_storiesA | 列出所有故事及元数据（标题/类型/状态/字数/系列）。默认返回精简列表节省 Token；传 verbose=true 获取完整详情 |
| read_chapterA | 读取指定故事的章节内容（支持按章节索引按需加载）。tailLength 可只返回章节末尾 N 字符用于续写衔接，节省 Token |
| write_chapterA | 将正文写入指定故事（原子写入 text.md）。validate=true 时写入后立即执行仓库合规检查并返回结果（不阻断写入） |
| edit_configA | 更新故事 config.json 的元数据字段。可编辑：summary/status/series/seriesOrder/volume/links/author/originalWork/originalAuthor/cover/language/wordCount。字段值传 null 表示移除该可选字段。title/type/created/isMultiChapter 为身份或审计字段，禁止修改。写入前经仓库级 schema 校验，校验失败不写盘。修改后请运行 build 更新 README |
| validateA | 检查仓库合规性（目录命名/必需文件/config schema/编码），等效 CLI |
| buildA | 重建所有 README（等效 story build）。返回构建结果与捕获的输出日志 |
| statsA | 获取故事库写作统计（总字数/章节数/系列分组/健康度/重复短语） |
| import_jsonA | 从结构化 JSON 批量导入故事（与 CLI |
| create_storyA | 创建一个新故事（文件夹 + config.json + text.md 草稿） |
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 9 tools
Each tool targets a distinct operation or resource: creating/importing stories, reading/writing chapters, editing config, validating, building, stats, and scanning. There is no real overlap, and the descriptions clarify boundaries even where purposes are adjacent, such as create_story vs import_json.
Most tools follow a clear verb_noun snake_case pattern (create_story, scan_stories, read_chapter, write_chapter, edit_config, import_json). validate, build, and stats are shorter imperative/noun names but are still intuitive and do not break the overall predictability.
Nine tools is well-scoped for a story authoring workflow. Each tool has a clearly defined role, and none feel redundant or unnecessary for the server's purpose.
The core authoring loop is covered: create, read/write chapters, edit metadata, validate, build, and get stats. However, there is no delete story/chapter operation and no explicit chapter listing tool, leaving lifecycle management incomplete. Agents could work around some gaps, but deletion is a notable missing capability.