ArcRift
未认领Persistent local memory layer for AI. ArcRift uses a extension and a native MCP server to sync context and decisions from your browser chats (Claude, ChatGPT, DeepSeek) straight to your local IDE agents (Cursor, Claude Code, Windsurf) powered by a local SQLite knowledge graph.
01 / 选择客户端
03 / 添加配置
claude mcp add --transport stdio 'arcrift' -- 'npx' '-y' 'arcrift-setup'04 / 在客户端中确认
打开客户端的 MCP 设置，确认服务器已连接并列出工具。复制配置不代表连接成功。
更多Databases服务器
浏览完整目录安全概况
已认领和已认证的服务器每周接受一次静态扫描，显示代码能触及的范围（外部服务、环境变量、shell 命令、代理配置目录）以及带有已知公告的依赖。认领此列表即可获得。 安全概况的工作原理
11 个工具中显示 11 个
文档中列出的工具 (11)
内容来自项目文档。服务器握手不会验证每个工具的说明或行为。
Auto-Connect
Once a session is active, ArcRift re-attaches automatically on every page load. No clicking required — just type.
ChromaDB
8000
get_project_summary
Returns a structured knowledge graph summary for a project as readable markdown.
identify_active_project
Matches a folder path against saved project names. Lets the AI agent auto-detect which project it is working on from the CWD.
list_projects
Lists all saved projects with metadata — chunk count, triple count, last updated.
MongoDB
27017
Neo4j
7474 / 7687
prune_memory
Surgically removes facts or chunks matching a description. Corrects outdated information without wiping an entire project.
recall_context
Retrieves the top-N most relevant memory chunks for a prompt, scoped to a project. Includes knowledge graph facts.
search_memory
Cross-project global search. Useful for finding decisions made in a different project that apply to the current one.
store_memory
Saves text or a transcript to ArcRift Memory. Auto-creates the project if it does not exist. Triggers full background indexing.