Reattend

Name: Reattend
Author: reattend

@reattend

代码仓库

关于 Reattend

Reate

基本信息

分类

其他

传输方式

stdio

发布者

reattend

提交者

Partha

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "reattend": {
      "command": "npx",
      "args": [
        "-y",
        "@reattend/mcp",
        "--token",
        "rat_your_token_here"
      ]
    }
  }
}

工具

未检测到工具

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is Reattend?

Reattend is an MCP server that gives AI assistants like Claude, Cursor, and Windsurf persistent memory across sessions and tools. It connects to a personal memory store built automatically from captured context from meetings, Slack, Gmail, Notion, and other sources via the Reattend Chrome extension.

How to use Reattend?

Install with npx -y @reattend/mcp --token rat_your_token_here. Configure the server in your AI tool’s MCP settings (e.g., Claude Desktop config JSON, Cursor’s .cursor/mcp.json, VS Code Copilot’s .vscode/mcp.json). Restart the tool to begin using persistent memory.

Key features of Reattend

Semantic + keyword search across all captured memories
Automatic capture from tools via Chrome extension
Cross-session and cross-tool memory persistence
Save preferences, decisions, and notes mid-conversation
Synthesized answers from full memory store

Use cases of Reattend

Automatically recall meeting context before a call
Persist architecture decisions and code preferences across sessions
Provide team shared memory for onboarding and decision history
Retrieve action items from past meetings without manual notes

FAQ from Reattend

What are the requirements to use Reattend?

Node.js 18+, a Reattend account (sign up free at reattend.com), and optionally the Chrome extension for automatic capture.

How does Reattend capture memory?

The Chrome extension passively captures from tools you already use (meeting transcripts, Slack threads, emails, docs). Captures are triaged by AI, embedded for semantic search, and stored in your personal memory.

What tools does the MCP server expose?

Four tools: search_memories (semantic+keyword search), ask_memory (AI-synthesized answer), save_memory (save from conversation), and recent_memories (most recent captures).

How is Reattend different from pasting context into prompts?

Automatic and permanent instead of manual per session. Covers everything captured rather than what’s remembered to paste. Provides full semantic search and works across sessions and all MCP-compatible tools.

其他分类下的更多 MCP 服务器

Unity MCP ✨

justinpbarnett

Unity MCP acts as a bridge between AI assistants and your Unity Editor. Give your LLM tools to manage assets, control scenes, edit scripts, and automate tasks within Unity.

12.2K