"PlayStation Portable" matching MCP servers:

A plain-files brain template and MCP server that lets models read owned, portable working memory via list, read, and grep-style search tools.

A portable MCP server enabling AI assistants to operate VS Code, including file management, extension control, and workspace automation.

Gives AI apps a shared, plain-folder memory on your own machine, so whatever you tell one model the others can read, and you can inspect, review and undo every change they make. Memory stays portable across vendors, models and account changes instead of living on a provider's servers.

Provides portable memory for AI agents using plain Markdown files. Enables storing, recalling, and managing memories via MCP tools like recall, remember, forget, list, and get.

Portable AI memory that roams with you across models and harnesses — one shared memory for Claude Code, Codex, Cursor, Gemini CLI and more, stored as plain markdown files you own. Per-project spaces plus a shared layer, vault-wide search; runs locally over stdio/HTTP or hosted with OAuth 2.1 backed by your own GitHub repo.

Enables authenticated web agents to reach a local machine through a portable MCP endpoint, with optional Cloudflare Tunnel or Tailscale Funnel ingress for public access.

Enables any MCP client — Codex, Cursor, Gemini CLI, or a custom agent — to read and write Claude Code's per-project auto memory, retrieving linked Markdown memories within a token budget and optionally saving or deleting them. Keeps memories as plain files in Claude Code's own format, so multiple agents share one portable memory without vectors or a database.

Provides a portable Windows AI workspace with local SQL queries, calculation and statistics, file sandbox, chat, tool debugging, and account/file sharing features.