tomato-writer-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| TOMATO_COOKIE | Yes | Cookie from the 番茄小说作家后台 (fanqienovel.com) author backend request header. Used together with TOMATO_CSRF_TOKEN for authentication. | |
| TOMATO_CSRF_TOKEN | Yes | X-Secsdk-Csrf-Token from the 番茄小说作家后台 (fanqienovel.com) author backend request header. Used together with TOMATO_COOKIE for authentication. |
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 |
|---|---|
| list_novelsA | 列出当前账号下的所有小说(book_id、书名、字数、总阅读数、连载状态)。多本小说时用它来选择操作目标。 |
| switch_novelA | 切换当前要操作的小说(传 book_id,可先用 list_novels 查)。之后的发布、数据查询默认作用于这本,直到再次切换。 |
| get_current_novelA | 查看当前选中的小说。 |
| get_novel_statsA | 获取小说阅读数据:书级概览(总阅读数 read_count、字数、连载状态)+ 各章阅读/追读明细。不传 book_id 用当前选中的小说。 |
| list_chaptersA | 列出小说各分卷下的章节(含定时待发 / 已发布状态)。不传 book_id 用当前选中的小说。 |
| publish_chapterA | 发布或定时发布一章到当前(或指定)小说。内容二选一:① 直接传 title + content;② 传 file(Markdown 稿件路径)+ chapter_no 自动提取(标题取章节行)。publish_time 传 ISO 时间则定时/预约发布,省略则立即发布。 |
| get_login_qrcodeA | 获取番茄作家后台官方实时扫码登录二维码数据源 (Base64 PNG) 与会话 Token |
| get_account_infoA | 获取当前番茄作家账号信息(昵称、ID、等级等)。用来确认 Cookie 绑的是哪个号。 |
| check_loginA | 检查登录态是否仍然有效(最轻量探针)。Cookie 过期前先用它确认,避免发布到一半失败。 |
| get_author_overviewB | 作者级数据总览(全站维度的创作/收益概览)。 |
| list_noticesA | 站内通知列表(审核结果、平台公告)。发完章节后用它盯是否已过审。 |
| get_banned_infoA | 违规/封禁状态查询。不传 book_id 查账号级;可用于违规自动告警。 |
| get_attend_calendarB | 打卡/全勤日历。start_date / end_date 为 unix 秒;不传默认最近 30 天。 |
| get_checkin_ticketsA | 查询剩余打卡券数量(补卡用)。 |
| get_hot_wordsB | 站内热词榜(起书名 / 蹭流量用)。gender:1=男频,2=女频。 |
| get_douyin_hot_listB | 抖音热点榜,配合站内热词做选题参考。 |
| list_draftsC | 草稿箱列表(未发布的章节)。 |
| get_medal_summaryC | 任务勋章概览(平台活动完成度)。 |
| get_ai_qualificationB | AI 功能资格查询(AI 插画 / AI 命名 / AI 咨询是否对该书开放)。 |
| delete_chapterA | 删除章节(已发布/草稿均可,⚠️ 不可恢复)。必须显式传 confirm=true 才会真正执行。 |
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 20 tools
Most tools have clearly distinct resource/action targets: novel selection, chapter publishing/listing/deleting, account/login, stats, notices, and trend lookup are separable. A few status/account tools such as check_login, get_account_info, and get_login_qrcode are adjacent, but the descriptions make their roles understandable.
All tool names consistently use snake_case and mostly follow a predictable verb_noun pattern such as list_novels, get_novel_stats, publish_chapter, and delete_chapter. Minor variation like check_login and switch_novel is still readable and consistent with the overall convention.
With 20 tools, the server is somewhat heavy but the scope is broad: novel management, chapter publishing, account/login, analytics, notices, check-ins, trends, drafts, and AI qualification. Each tool appears to represent a real operation rather than redundant filler.
The surface covers core writer workflows including listing/switching novels, chapter listing, publishing, drafts, deletion, stats, login, notices, and account checks. Some lifecycle gaps remain, such as editing chapter content or creating a novel, but agents can likely work around these via the web backend.