Penfield
Persistent memory for AI agents. Store decisions, preferences, and context that survive across sessions. Build knowledge graphs that compound over time. Works with Claude, Cursor, Windsurf, Gemini CLI, and any MCP-compatible tool.
接入你的智能体
發布者自己的 URL。不是 PlugMCP 端點。
用我們的金鑰與日誌託管一份副本。
https://mcp.penfield.app/上方的 Claude 按鈕會開啟 Claude,並填好名稱和 URL。你仍需在那裡確認。
claude mcp add --transport http io.github.penfieldlabs-penfield-mcp https://mcp.penfield.app/Run in a terminal.
{ "mcpServers": { "io.github.penfieldlabs-penfield-mcp": { "command": "npx", "args": [ "-y", "mcp-remote", "https://mcp.penfield.app/" ] } }}claude_desktop_config.json
遠端 URL 還是本機指令? 兩種安裝方式的差異
來自發布者
Persistent memory for AI agents. Store decisions, preferences, and context that survive across sessions. Build knowledge graphs that compound over time. Works with Claude, Cursor, Windsurf, Gemini CLI, and any MCP-compatible tool.
Persistent memory and knowledge graphs for AI agents. Hybrid search, context checkpoints, and more.
Add as a custom connector in Settings → Connectors:
Name: Penfield
Remote MCP server URL: https://mcp.penfield.app
claude mcp add --transport http --scope user penfield https://mcp.penfield.app
One-click install:
Install Penfield in Cursor
Cut and paste into your browser:
cursor://anysphere.cursor-deeplink/mcp/install?name=Penfield&config=eyJjb21tYW5kIjoibnB4IiwiYXJncyI6WyIteSIsIm1jcC1yZW1vdGUiLCJodHRwczovL21jcC5wZW5maWVsZC5hcHAvIl19
Or add manually to ~/.cursor/mcp.json:
{
"mcpServers": {
"Penfield": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://mcp.penfield.app/"]
}
}
}
Add to your MCP configuration file:
{
"mcpServers": {
"Penfield": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://mcp.penfield.app/"]
}
}
}
gemini mcp add penfield -- npx -y mcp-remote https://mcp.penfield.app/
Or add to ~/.gemini/settings.json:
{
"mcpServers": {
"Penfield": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://mcp.penfield.app/"]
}
}
}
17 tools for persistent memory:
Hybrid search combining BM25 (keyword), vector (semantic), and graph (connections) for recall that actually finds what you need.
Cross-platform sync — same memory, same knowledge graph, regardless of which tool you connect from.
Every session should start with:
awaken() # Load identity and personality context
reflect() # Orient on recent work (default: last 7 days)
Without these, your agent starts cold with no context.
Personal assistant that remembers
Development workflows
Research and writing
OpenClaw Native Plugin — If you use OpenClaw, the native plugin is 4-5x faster (no MCP proxy layer):
openclaw plugins install openclaw-penfield
openclaw penfield login
API — Direct HTTP access at api.penfield.app for custom integrations.
Copyright © 2025 Penfield™. All rights reserved.
Persistent memory and knowledge graphs for AI agents. Hybrid search, context checkpoints, and more.
{ "mcpServers": { "io.github.penfieldlabs-penfield-mcp": { "url": "https://mcp.penfield.app/", "headers": {} } }}工具
尚無工具清單。遠端伺服器會在首次健康檢查後取得工具清單。
常見問題
在本頁複製適用於 Cursor、Claude Desktop、Claude Code 或 VS Code 的 http 設定。它使用發布者的安裝方式,而不是 PlugMCP 代理伺服器。
這筆記錄未列出必要的環境變數。
Penfield Memory 透過 HTTP 存取。
上次檢查時間:2026-11-10。 Persistent memory and knowledge graphs for AI agents. Hybrid search, context checkpoints, and more.