MemForge
Verified IntegrationClient Configuration
— Connect MemForge to Claude Desktop or Cursor in seconds{
"mcpServers": {
"memforge": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-memforge"
],
"env": {}
}
}
}~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows).System Overview
Provides an open-source memory layer for AI agents, enabling long-term recall, reflection, and learning via the Model Context Protocol (MCP).
7/23/2026
APACHE
stdio / SSE RPC
Frequently Asked Questions
Architecture and operational details for MemForge
MemForge uses a sophisticated read path involving hybrid search (vector similarity, BM25 full-text, knowledge graph traversal), cross-encoder reranking, and a scoring mechanism. It delivers token-budgeted, compiled context documents grouped by type, rather than raw memory lists.
Related MCP Servers
Browse all servers →Empower AI assistants to generate and convert documents, manage templates, and automate document workflows efficiently.
Provides a multi-tenant, AI-native Content Delivery Network deployable on Cloudflare, featuring sub-100ms TTFB, AI agent controllability, and comprehensive accessibility.
Deploy a Model Context Protocol server on Cloudflare Workers without requiring authentication.