personal-context-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., "@personal-context-mcpcall who_am_i to learn about me"
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.
personal-context-mcp
把你的风格习惯、偏好设置、用过的 skill、人生背景存成 markdown,通过 MCP 暴露给任何支持 MCP 的 AI(Claude Code、Claude Desktop、Cursor…)。 换个 AI、新开一个聊天框,它调用一次工具就「认识你」,不用再重新交代自己是谁。
核心理念
数据一份,插头随时加:你的资料是
context/下的纯 markdown,放在你自己的 git 仓库里。 服务层(这个 MCP server)只是薄薄一层,随时可换、可拔。永久留存、不吃算力:这个项目跟 GPU 无关。数据放 GitHub 永久免费, server 本地 stdio 跑,零托管、断网可用。哪天没有任何服务器,光靠这个 git 仓库你依然拥有全部资料。
分层可见(tier):
public ⊂ recruiter ⊂ friend ⊂ private。同一份资料, 陌生人 / 招聘方 / 朋友 / 自己看到的范围不同。
Related MCP server: Personal Context Manager
目录结构
personal-context-mcp/
├── server.py # MCP server(stdio)
├── context/ # ★ 数据层:你的资料,改这里
│ ├── style.md # 风格习惯
│ ├── preferences.md # 偏好设置
│ ├── skills.md # 用过的 skill
│ └── background.md # 人生背景
├── ingest/import_file.py# 简历/文件 → 纯文本(供 AI 解析)
└── pyproject.toml安装
cd personal-context-mcp
uv sync # 装依赖(mcp / pyyaml / pypdf / python-docx)本地调试
uv run mcp dev server.py # 打开 MCP Inspector,可视化点每个工具接入 Claude Code
uv run mcp install server.py --name personal-context或手动在 Claude Code / Claude Desktop 的 MCP 配置里加:
{
"mcpServers": {
"personal-context": {
"command": "uv",
"args": ["--directory", "/绝对路径/personal-context-mcp", "run", "server.py"]
}
}
}接入后,对 AI 说「调用 who_am_i 了解我」即可。
提供的工具
工具 | 作用 |
| 一次性返回该 tier 下全部可见内容,换新 AI 时用它「一键认识你」 |
| 列出所有板块 |
| 读某个板块全文 |
| 关键词搜索 |
| 写入/更新板块(AI 整理完经历后存回来) |
| 抽取 pdf/docx/txt/md 文本,供 AI 解析简历 |
上传简历 / 文件,自动整理进知识库
不需要写死解析逻辑——让 AI 来做:
让 AI
extract_file("我的简历.pdf")拿到纯文本;AI 解析、优化成结构化内容;
AI
save_context(slug="background", ...)写回context/。
命令行也能单独抽文本:uv run python ingest/import_file.py 我的简历.pdf
留存到 GitHub
cd personal-context-mcp
git init && git add . && git commit -m "init personal-context-mcp"
# 在 GitHub 建仓库后:
git remote add origin <你的仓库URL>
git push -u origin main提示:
context/里若有私密内容,建议用私有仓库,或把私密板块单独放另一个私有仓库、 用PERSONAL_CONTEXT_DIR环境变量指过去。
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
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/KrystalJin1/personal-context-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server