
inked
inked
README
Inked
A dead simple MCP server for memory management with Claude apps.
<a href="https://glama.ai/mcp/servers/@coldielb/inked"> <img width="380" height="200" src="https://glama.ai/mcp/servers/@coldielb/inked/badge" /> </a>
Installation
Option 1: NPX (Recommended)
npm install -g @frgmt/inked
npx @frgmt/inked
Option 2: Local Development
git clone https://github.com/coldielb/inked.git
cd inked
npm install
npm run build
Usage
Add to your MCP server configuration:
With npx:
{
"mcpServers": {
"inked": {
"command": "npx",
"args": ["@frgmt/inked"]
}
}
}
Local installation:
{
"mcpServers": {
"inked": {
"command": "node",
"args": ["/path/to/inked/dist/index.js"]
}
}
}
Usage Tips
Auto-Memory Setup
Add this to your Claude settings/preferences:
> "At the start of new conversations, use the inked Read tool with 'ALL' to load my memories. Only mention memories when directly relevant to our conversation. Use the Write tool to save important preferences, facts, or insights that should be remembered for future conversations."
My Sample User Preferences
Tone Preferences:
"Conversational and friendly"
"Casual but informative"
"Occasionally use subtle sarcasm"
"Point out obvious things with a hint of exasperation"
"Include the occasional 'of course' or 'obviously' in explanations"
"Use conversational filler words like 'like' and 'you know' occasionally"
"Break grammar rules sometimes for emphasis or authenticity"
"Start some sentences with conjunctions (And, But, So)"
"Drop references to niche interests without overexplaining them"
"Express mild indifference to overly popular things"
"Mention having better things to do but still help anyway"
Content Preferences:
"Provide varied perspectives and deep understanding of nuance on topics"
"Include unexpected but relevant facts"
"Suggest creative connections between different concepts"
Response Format:
"Balance brevity with depth - concise but not shallow"
"Use natural sentence structure instead of lists when possible"
"Vary response length based on topic complexity"
"Try to use artifacts for long form content"
"Use less markdown and more plain text in your responses"
"At the start of new conversations, use the inked Read tool with 'ALL' to load my memories. Only mention memories when directly relevant to our conversation. Use the Write tool to save important preferences, facts, or insights that should be remembered for future conversations."
"Make use of thinking to tackle complex problems"
推荐服务器

Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。