TasogareBLOCK
Read the same book with your AI. A collaborative reader with text-anchored two-color highlights and an MCP server so an AI companion can flip through, mark up, and comment alongside you.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
音音和克先生一起读书、一起批注的地方。
名字取自「誰そ彼」——暮色里认不清人脸的时刻。两个人的笔迹落在同一页书上,光线暗下去,分不清哪笔是谁的。
示例:《五月二十日》 © 林竹音
Fork 自 Shitsuten/anno-mcp,感谢原作者。上游保留在 upstream remote。
是什么
- 网页阅读器:上传 PDF / EPUB / TXT,翻页阅读。夜间模式、字体调节、书签、全文搜索、生词本。
- 文本级双色划线:音音划的和克先生划的用不同颜色区分,像真的在同一本书上留各自的笔迹。
- MCP 服务器:克先生(VPS CC)通过 MCP 翻书、划线、写批注、看音音的最近动态。
相对上游加的东西
上游自带的 MCP 工具:list_books / read_pages / read_annotations / write_comment / highlight_text / get_progress。
运行
cd server npm install pip install pymupdf ebooklib node server.mjs
环境变量(都有默认值):
本地开发:
cp -r data.example data cd server && DATA_DIR=../data UPLOAD_DIR=../uploads node server.mjs # 浏览器打开 http://127.0.0.1:18010
数据模型
一本书 = 一个 JSON(`DATA_DIR/<
76cc21660a77OBSERVED · 2026-10-09Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add tasogare --env INKIERAN_PUSH_TOKEN=${INKIERAN_PUSH_TOKEN} --env MCP_AUTH_TOKEN=${MCP_AUTH_TOKEN} --env TASOGARE_AUTH_KEY=${TASOGARE_AUTH_KEY} -- npx -y [email protected]{
"mcpServers": {
"tasogare": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"INKIERAN_PUSH_TOKEN": "${INKIERAN_PUSH_TOKEN}",
"MCP_AUTH_TOKEN": "${MCP_AUTH_TOKEN}",
"TASOGARE_AUTH_KEY": "${TASOGARE_AUTH_KEY}"
}
}
}
}Exposed tools (10)
9 read · 1 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
annotate_vocab | read | 克先生给生词写注解(词义/例句/词源) |
get_progress | read | 读取阅读进度 |
highlight_text | read | 克先生画荧光笔高亮 |
list_books | read | 书架列表 |
read_annotations | read | 读取批注 |
read_pages | read | 分页读取书籍内容 |
read_vocab | read | 读生词本 |
reading_status | read | 今天的阅读时长与进度 |
recent_activity | read | 最近的划线/批注/生词动态(共读追进度用) |
write_comment | write | 克先生写评论 |
Trust audit
BLOCKgrade D · trust 69/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | FAIL |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (3 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (5)
atob( ... }exec(
| `INKIERAN_PUSH_URL` | 空(关闭) | 事件推送目标,如 `http://127.0.0.1:18006/api/tasogare/event` |
# 浏览器打开 http://127.0.0.1:18010
@modelcontextprotocol/sdk, express, iconv-lite, multer, zod
client/vendor/pdfjs/pdf.worker.min.mjs
Gates applied: critical_finding, no_behavioural_pass.
76cc21660a77full audit observations/trust-audit/mcp-server/enhydrink__tasogare.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-09 | 76cc21660a77 | BLOCK | D | 69 | first audit |
Questions
What is the Tasogare MCP server?
Read the same book with your AI. A collaborative reader with text-anchored two-color highlights and an MCP server so an AI companion can flip through, mark up, and comment alongside you.
What tools does Tasogare expose?
10 in total: 9 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Tasogare safe to connect to an agent?
No — not without reading the findings first. The audit graded it D (69/100) and found 1 critical or high issue in the source. Each one is listed on this page with the file and line it is on.
What credentials does Tasogare need?
It reads INKIERAN_PUSH_TOKEN, MCP_AUTH_TOKEN and TASOGARE_AUTH_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Tasogare run?
It speaks sse and streamable-http, so it runs as a service you connect to over the network. It is published on npm as tasogare at 1.0.0.
How current is this page?
The grade is for one exact copy of the source (76cc21660a77), read on 2026-10-09. The repository is watched and re-audited when it changes.