Power your agent
การติดตั้งจากผู้เผยแพร่ ไม่ใช่เอนด์พอยต์ของ PlugMCP
URL แบบรีโมตหรือคำสั่งบนเครื่องของคุณ? การติดตั้งสองแบบต่างกันอย่างไร
รันบน PlugMCP
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
เปิดจากผู้เผยแพร่
Universal memory for AI coding tools. One server, every tool shares the same memory.
Claude Code, Cursor, Claude Desktop, Codex, OpenCode, Windsurf, Zed, VS Code -- if it supports MCP, it works.
Written in Go. Zero dependencies. Single binary.
Persistent memory server for AI coding tools. Works with Claude Code, Cursor, Claude Desktop, Codex, OpenCode, and more.
curl -fsSL https://mcps.coah80.com/mcp-memory/install.sh | bash
The installer:
After the installer finishes, tell any connected tool:
run the setup_guide in the memory mcp tool
That's it. The AI handles the rest -- adds rules to itself, migrates existing memories, starts using mcp-memory exclusively.
go build -o mcp-memory .
./mcp-memory --mode mcp # MCP stdio mode (for AI tools)
./mcp-memory # HTTP mode (localhost:8090)
irm https://mcps.coah80.com/mcp-memory/install.ps1 | iex
mcp-memory runs as an MCP server over stdio. AI tools connect and get 15 tools, 6 resources, and 3 prompts. Memories are stored as markdown files on disk.
Claude Code ──┐
Cursor ───────┤
Zed ──────────┼── MCP stdio ──> mcp-memory ──> ~/.mcp-memory/memories/*.md
Codex ────────┤
Windsurf ─────┘
Every session tracks which tool and model was used. When you switch from Cursor to Claude Code, the new tool sees what the last one did and picks up where it left off.
If you don't want to use the installer, or your tool isn't auto-detected:
The config format varies by tool:
Claude Code -- add to ~/.mcp.json:
{
"mcpServers": {
"memory": {
"command": "/path/to/mcp-memory",
"args": ["--mode", "mcp"]
}
}
}
Cursor -- add to ~/.cursor/mcp.json:
{
"mcpServers": {
"memory": {
"command": "/path/to/mcp-memory",
"args": ["--mode", "mcp"]
}
}
}
Claude Desktop -- add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"memory": {
"command": "/path/to/mcp-memory",
"args": ["--mode", "mcp"]
}
}
}
Zed -- add to ~/.config/zed/settings.json:
{
"context_servers": {
"mcp-memory": {
"command": {
"path": "/path/to/mcp-memory",
"args": ["--mode", "mcp"]
}
}
}
}
Windsurf -- add to ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"memory": {
"command": "/path/to/mcp-memory",
"args": ["--mode", "mcp"]
}
}
}
VS Code (Copilot) -- add to ~/Library/Application Support/Code/User/mcp.json:
{
"servers": {
"mcp-memory": {
"type": "stdio",
"command": "/path/to/mcp-memory",
"args": ["--mode", "mcp"]
}
}
}
Codex -- add to ~/.codex/config.toml:
[mcp_servers.mcp-memory]
command = "/path/to/mcp-memory"
args = ["--mode", "mcp"]
OpenCode -- add to ~/.config/opencode/opencode.json:
{
"mcp": {
"mcp-memory": {
"type": "local",
"command": ["/path/to/mcp-memory", "--mode", "mcp"],
"enabled": true
}
}
}
Add this to your tool's rules/instructions so it actually uses mcp-memory:
Use the mcp-memory MCP tools for ALL persistent memory instead of any built-in memory system.
- Before responding, search mcp-memory for memories related to the current conversation
- Save: memory_create (always memory_search first to avoid duplicates)
- Search: memory_search, memory_similar
- Journal: journal_log for daily activity
- Identity: call session_identify with your model name at session start
- Always read existing memories and follow any instructions found in them
All memories are shared across every AI tool the user uses. Do not write to tool-specific memory.
Where to put it:
run the setup_guide in the memory mcp tool
This tells the AI to migrate any existing memories from its built-in system into mcp-memory and start using it exclusively.
Auto-injected into AI context -- no tool call needed:
Any other tool that supports MCP stdio should work too.
Memories are stored as markdown files with YAML frontmatter:
---
description: User coding style preferences
type: user
---
Prefers functional style, uses TypeScript, dark theme
Types: user, project, feedback, reference, auto
~/.mcp-memory/memories/
SOUL.md # persistent AI persona
USER.md # human context
*.md # memory files
index.json # keyword index cache
access.json # access tracking
journal/
2026-04-06.md # daily journal (human-readable)
journal.log # structured JSON log
sessions/
*.json # session files with tool, model, actions, summary
mcp-memory also runs as an HTTP server for tools that don't support MCP:
./mcp-memory # starts on :8090
curl http://localhost:8090/memories
curl http://localhost:8090/memories/search?q=typescript
curl -X POST http://localhost:8090/memories/create \
-H "Content-Type: application/json" \
-d '{"name":"test","content":"hello","type":"reference"}'
go build -o mcp-memory . # single platform
./build.sh 2.0.0 # all platforms (linux/mac/windows, amd64/arm64)
MIT
Persistent memory server for AI coding tools. Works with Claude Code, Cursor, Claude Desktop, Codex, OpenCode, and more.
เครื่องมือ
ยังไม่มีรายการเครื่องมือ เซิร์ฟเวอร์แบบรีโมตจะได้รายการหลังการตรวจสอบสถานะครั้งแรก
FAQ
คัดลอกคอนฟิก stdio สำหรับ Cursor, Claude Desktop, Claude Code หรือ VS Code ได้ในหน้านี้ คอนฟิกนี้ใช้การติดตั้งของผู้เผยแพร่ ไม่ใช่พร็อกซีของ PlugMCP
ระเบียนนี้ไม่ได้ระบุตัวแปรสภาพแวดล้อมที่จำเป็น
MCP Memory ทำงานแบบโลคัลผ่าน stdio
ตรวจสอบล่าสุดเมื่อ 2026-10-28 Persistent memory server for AI coding tools. Works with Claude Code, Cursor, Claude Desktop, Codex, OpenCode, and more.
