create_upload — Multiplayer Agent MCP Tool Mutating
create_upload
(create upload) is one of 26 tools on the
Multiplayer Agent
MCP server. Connect the server and your client discovers it on the handshake.
by client
How to call create_upload from your client
- Claude Code Multiplayer Agent create_upload run in your project directory
- Claude Desktop Multiplayer Agent create_upload ~/Library/Application Support/Claude/claude_desktop_config.json
- Cursor Multiplayer Agent create_upload ~/.cursor/mcp.json
- VS Code Multiplayer Agent create_upload .vscode/mcp.json
- Zed Multiplayer Agent create_upload ~/.config/zed/settings.json
- Windsurf Multiplayer Agent create_upload ~/.codeium/windsurf/mcp_config.json
- Cline Multiplayer Agent create_upload ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Gemini CLI Multiplayer Agent create_upload ~/.gemini/settings.json
- Grok Multiplayer Agent create_upload .mcp.json (in your project root)
- ChatGPT Multiplayer Agent create_upload Settings → Connectors → Advanced → Developer mode
- Claude.ai Multiplayer Agent create_upload Settings → Connectors → Add custom connector
- LangChain Multiplayer Agent create_upload pip install langchain-mcp-adapters
Fastest route
claude mcp add --transport http multiplayer-agent https://api.multiplayeragent.com/mcp?src=registry
Other tools on this server
- create_game
- list_games
- set_game_name
- define_room_type
- get_connection_info
- get_client_snippet
- deploy_room_logic
- list_room_logic
- rollback_room_logic
- get_room_logs
- get_live_ops
- set_live_config
- schedule_live_event
- cancel_live_event
- set_highlight_webhook
- get_sdk_reference
- set_player_scope
- enable_login_provider
- list_login_providers
- verify_login_token
- publish_game
- list_starters
- remix_game
- connect_account
- claim_studio
This list was read from the server itself, by connecting to it and calling tools/list on 5 November 2026. It is what
the server actually exposes, not what its listing claims.
Mutating and Read-only are read off each tool's name, not its schema — a hint, not a guarantee. The registry stores tool names only; connect the server for its live schemas.