About ArcRift
ArcRift is an MCP server in the RAG category: persistent local memory layer for AI. ArcRift uses a Chrome 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.
Install
git clone https://github.com/Eshaan-Nair/ArcRiftThis server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Tools (7)
get_project_summaryReturns a structured knowledge graph summary for a project as readable markdown.
Parameters not published.
identify_active_projectMatches a folder path against saved project names. Lets the AI agent auto-detect which project it is working on from the CWD.
Parameters not published.
list_projectsLists all saved projects with metadata — chunk count, triple count, last updated.
Parameters not published.
prune_memorySurgically removes facts or chunks matching a description. Corrects outdated information without wiping an entire project.
Parameters not published.
recall_contextRetrieves the top-N most relevant memory chunks for a prompt, scoped to a project. Includes knowledge graph facts.
Parameters not published.
search_memoryCross-project global search. Useful for finding decisions made in a different project that apply to the current one.
Parameters not published.
store_memorySaves text or a transcript to ArcRift Memory. Auto-creates the project if it does not exist. Triggers full background indexing.
Parameters not published.
Ask AI
Ask AI about ArcRift
Powered by Claude · Grounded in docs
Security checks
6 checks have not been run yet.