slowread-mcp
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@slowread-mcpsearch my reading list for articles about AI agents"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
慢读清单 MCP Server
把 Jun 的「慢读清单」阅读存档(Hatch web artifact space)开放成只读的 MCP 工具,
让 AI agent 可以搜索、浏览、引用这些收藏的文章。这是"给 agent 用的服务"的第一个实验:
agent 成为用户,来读人的精选。
工具(只读)
工具 | 说明 |
| 大小写不敏感的子串搜索(标题/摘要/笔记/标签/主题),标题命中排前面。返回 id、标题、url、来源、主题、标签、创建时间 + 200 字摘要片段。 |
| 按创建时间倒序,可按主题/标签过滤。 |
| 单篇文章的完整记录(标题、url、作者、来源、摘要、笔记、标签、关键词、主题、重要度、阅读时长、创建时间)。 |
| 去重主题及各自文章数。 |
Related MCP server: PubMed MCP Server
快速开始
cd ~/workspace/mcp-slowread
python3 -m venv .venv
.venv/bin/pip install -r requirements.txt
.venv/bin/python test_client.py # 端到端自检stdio(Claude Code / Cursor 本地接入)
Claude Code (~/.claude.json 或项目 .mcp.json):
{
"mcpServers": {
"slowread": {
"command": "/home/hatch/workspace/mcp-slowread/.venv/bin/python",
"args": ["/home/hatch/workspace/mcp-slowread/server.py"]
}
}
}Cursor:Settings → MCP → Add new global MCP server,填同样的 command/args。
SSE(部署给远端 agent)
.venv/bin/python server.py --transport sse --port 8000远端 agent 连 http://<host>:8000/sse。注意:这是只读公开元数据服务,
但仍建议只在可信网络暴露,或前面加一层反向代理做鉴权/限流。
数据刷新
data/articles.json 是静态快照(当前 44 篇,2026-09-06 抓取)。
MCP server 不直连线上 app——这是有意为之:快照简单、可审计、
不怕把线上库拖慢。刷新快照时重新从 artifact 抓取并覆盖该文件即可
(只读抓取,见 artifact.invoke_action 的 listarticles action,
slug=space,args={"limit":200,"status":"all"})。
日志
每次工具调用追加一行 JSON 到 logs/access.log:
{"ts": ..., "tool": ..., "args": {...}}。只记元数据,
不记录文章全文。
隐私说明
只读:没有任何写入、删除、修改线上「慢读清单」的工具。
只暴露文章的公开元数据(标题、链接、来源、摘要、笔记、标签)—— 这些本来就是 Jun 收藏的公开网页,加上他自己的中文点评。
无密钥、无账号体系。
data/articles.json是明文快照, 分享/部署前请确认内容可公开。
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
No tool schema history has been recorded yet.
This server cannot be installed
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Search arXiv and ACL Anthology, retrieve citations and references, and browse web sources to accel…
Search arXiv/Semantic Scholar/OpenAlex + medical evidence (PubMed/Europe PMC) + LaTeX/PDF tools.
Your curated sources (RSS, YouTube, podcasts, Google News) as context for any AI agent. 26 tools.
Read-only access to your Citlyze workspace: AI search visibility, citations, and recommendations.
Related MCP Servers
- AlicenseNot gradedqualityFmaintenanceTurn any AI agent into an academic researcher that can search, read, cite, and write full literature reviews autonomously.14MIT
- AlicenseAqualityCmaintenanceEnables AI agents to search and read PubMed academic literature directly, without requiring an NCBI API key.21MIT
- FlicenseAqualityDmaintenanceEnables agents to search papers across Semantic Scholar and arXiv, read and extract text from arXiv PDFs, align records across sources, and produce structured literature-analysis digests.101-
- FlicenseAqualityBmaintenanceEnables searching and reading of AI/ML papers from conference proceedings and arxiv, with tools for full-text search, table of contents, and content grep.4-
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Papa-Panda/slowread-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server