Skip to main content

​
What is it?

MemContext provides a hosted MCP server that gives AI assistants persistent memory through the Model Context Protocol. No local installation or infrastructure required. The server handles input validation, project name normalization, and response formatting for assistant consumption. All business logic - deduplication, classification, hybrid search - runs in the MemContext API. MCP tools intentionally do not expose a free-form scope parameter. AI agents can invent isolation IDs, so app-user and tenant scopes should be controlled by your application through the REST API or TypeScript SDK. MCP remains focused on unscoped assistant memory plus optional project grouping.

​
Connection URL

Authenticate in one of two ways:
  • OAuth: connect without any key. OAuth-capable clients (Claude, ChatGPT, Claude Code, Codex CLI, Cursor, VS Code, OpenCode) discover MemContext’s authorization server automatically, open a sign-in and consent screen, and refresh their access in the background.
  • API key: send your key in the MEMCONTEXT-API-KEY or X-API-Key header. When both are present, the API key is used.
The server speaks the Streamable HTTP transport and supports MCP protocol version 2026-07-28 as well as earlier (2025) clients. See MCP Setup for client-specific configs.

​
Tools

The server exposes five tools:

​
Agent instructions

For best results, add the recommended agent instructions to your client’s preferences file. These tell the assistant when to search, when to save, and how to use categories and projects. The full instructions block and per-client file paths are documented in the MCP Setup guide.