The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra
UI-TARS Desktop is part of a multimodal AI agent stack that uses vision and graphical interfaces to operate computers and web browsers. Its desktop application provides local and remote computer and browser operators, while the related Agent TARS project offers terminal and web interfaces for multimodal agents. Catalogue entries connect agent workflows and MCP tools to this stack.
MCP server Claude CodeCodexCursor +2 ✓ vendor
One of 4 in server.json
MCP server for browser use access. Runs locally from the @agent-infra/mcp-server-browser npm package. Needs 1 environment variable to run.
MCP server Claude CodeCodexCursor +2 ✓ vendor
One of 4 in server.json
An MCP server to run arbitrary commands. Runs locally from the @agent-infra/mcp-server-commands npm package.
MCP server Claude CodeCodexCursor +2 ✓ vendor
One of 4 in server.json
MCP server for filesystem access. Runs locally from the @agent-infra/mcp-server-filesystem npm package.
MCP server Claude CodeCodexCursor +2 ✓ vendor
One of 4 in server.json
MCP server for web search operations. Runs locally from the @agent-infra/mcp-server-search npm package.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: