The full upstream README, mirrored here for reference. Install config, tool schemas, adoption signals, and an original overview live on the MCP Server listing page.
PandaNpc MCP Server — expose PandaNote, workspaces, AI models, scheduled tasks, and Agent connection management to Codex, Claude Code, Cursor, Windsurf, and other MCP clients.
Homepage: https://pandanpc.com · npm: @pandanpc/mcp-server
The postinstall script downloads the matching prebuilt binary for your platform (Linux x64, macOS x64/arm64, Windows x64).
Or in config JSON:
~/.codex/config.toml:
Add an MCP server with command pandanpc-mcp (stdio). HTTP/SSE mode: pandanpc-mcp --http --port 3100.
note_login — log in to your PandaNpc accountlist_workspaces / create_workspace / update_workspace / delete_workspacelist_notes / create_note / read_note / update_note / delete_note / search_notes (full-text + semantic) / generate_note_titlelist_models / create_model / list_providers / create_provider / …list_agent_connections / create_agent_connection — manage Claude Code / Codex / PandaCode remote connectionslist_scheduled_tasks / create_scheduled_task / toggle_scheduled_task / …sync_rules — sync .claude/rules/ and .claude/skills/ Markdown to PandaNoteCall note_login first to authenticate.
This repository hosts documentation and issue tracking for the PandaNpc MCP server. The server ships as prebuilt binaries via the npm installer above (installer is MIT-licensed; the binary is proprietary freeware). Learn more at pandanpc.com.