AI Briefingmemv Launches MCP Server
Key point
The open-source memory layer memv has launched an MCP server, making it available for use in Claude Desktop, Code, and more.
Details
The open-source Python memory layer memv has launched an MCP (Model Context Protocol) server. It enables persistent, structured memory across all MCP clients including Claude Desktop, Claude Code, and Cursor without writing any integration code.
Key features:
- Provides 5 MCP tools:
search_memory,add_memory,add_conversation,list_memories,delete_memory - Optional LLM usage — search/add work without an LLM, only
add_conversationextraction requires an LLM - Per-user isolation and ownership verification
- Merges concurrent extraction jobs for the same user
Technical architecture:
memv uses a predict-calibrate extraction approach inspired by Nemori to prevent storing unnecessary information. It uses a bi-temporal model to expire contradictory information rather than overwriting it, and supports hybrid search combining vector search + BM25 + RRF.
Installation is simple: run pip install "memvee[mcp]" followed by memv-mcp --db-url memory.db --llm-model openai:gpt-4o-mini. Mounting within a Python process is also supported.
This summary was generated automatically by AI. Check the original for the author's claims and context. Copyright belongs to the original author.
Our guide explains how the AI works. Report summary errors, attribution issues, or removal requests via Contact.
Related
Jevper Released: A Jev Classification Wrapper for OpenAI-Compatible Models with Automatic Logprobs DetectionForemerge v0.5.0 Released: Rust-Based Open-Source Tool Detects Intent Conflicts Between Parallel AI Coding Agents
Narae Energy Services Implements Automated Power Plant Equipment Diagnostics Using Strands Agents and Bedrock AgentCore