MCP.so
Sign In

Reattend

@reattend

Repository

About Reattend

Reate

Config

Add this server to your MCP-compatible client using the configuration below.

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

Tools

4

Search the user's Reattend memory for relevant information. Use this proactively when the user asks about anything they may have captured — meetings, decisions, notes, Slack messages, emails, or any saved context. Also use it before answering questions that might have relevant past context.

Ask a question and get an AI-generated answer synthesised from the user's saved memories. Best when the user needs a direct answer that may span multiple memories. Use search_memories when you just need to find or list specific items.

Save something to the user's Reattend memory. Use this when the user explicitly says to remember, save, note, or capture something. Also use it to record decisions made during this conversation if the user asks.

Get the user's most recently saved memories. Use this when the user asks what they've been working on, what was recently captured, or wants a summary of recent activity.

Overview

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.

Frequently asked questions

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.

Comments

Basic information

Category

Other

Transports

stdio

Author

reattend

Submitted by

Partha

More Other MCP servers

MCP Go 🚀

mark3labs

A Go implementation of the Model Context Protocol (MCP), enabling seamless integration between LLM applications and external data sources and tools.

8.9K

Inbox Zero AI MCP

elie222

The world's best AI personal assistant for email. Open source app to help you reach inbox zero fast.

11.6K

IDA Pro MCP

mrexodia

AI-powered reverse engineering assistant that bridges IDA Pro with language models through MCP.

9.9K

Maestro

mobile-dev-inc

Painless E2E Automation for Mobile and Web

14.8K

Activepieces

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

23.2K