MemoV Now Supports MCP: Connect to Any AI Coding Agent
MemoV now includes native support for the Model Context Protocol (MCP), making it easy to capture AI coding sessions from any compatible agent or editor.
What is MCP?
The Model Context Protocol is an open standard that allows AI tools to communicate with external services. By implementing MCP, MemoV can automatically track sessions from:
- Claude Code — Anthropic's official CLI for Claude
- Codex — OpenAI's code completion tool
- VS Code — With the MCP extension
- Cursor — The AI-first code editor
How It Works
When you add MemoV as an MCP server, it runs alongside your AI agent and captures:
- Prompts — Every question or instruction you give the AI
- Responses — The AI's complete answers and explanations
- Code Diffs — Exactly what changed in your files
All of this is stored in a shadow
directory, completely separate from your maincode.mem
history.code.git
Quick Setup
For Claude Code
bashclaude mcp add mem-mcp --scope project -- uvx --from git+https://github.com/memovai/memov.git mem-mcp-launcher stdio $(pwd)
For Codex
bashcodex mcp add mem-mcp -- uvx --from git+https://github.com/memovai/memov.git mem-mcp-launcher stdio $(pwd)
For VS Code
Create
:code.vscode/mcp.json
json{ "servers": { "mem-mcp": { "type": "stdio", "command": "uvx", "args": [ "--from", "git+https://github.com/memovai/memov.git", "mem-mcp-launcher", "stdio", "${workspaceFolder}" ] } } }
For Cursor
Go to Cursor Settings > MCP and add the same configuration.
Benefits
- Zero configuration — Works out of the box with default settings
- Automatic tracking — No manual commands needed during sessions
- Privacy-first — Everything stays on your local machine
- Git-compatible — Uses Git's storage format for reliability
Learn More
Ready to get started? Follow our quickstart guide to set up MemoV in your project today.