How can an AI agent control OpenScreen?
If you mean an MCP-compatible AI agent operating a live OpenScreen session—not merely explaining a tutorial or generating a one-off script—DCC-MCP can inspect recording sources and run typed bounded record and export operations without desktop UI automation. DCC-MCP performs work through discoverable typed tools, instance routing, and result validation.
What can an AI agent do in OpenScreen?
- inspect available OpenScreen recording sources.
- start one bounded recording through the configured executable.
- export and verify the requested recording artifact.
Capabilities change with the adapter version and loaded Skills. Search and describe tools first instead of guessing current tool names from this page.
Safe operating flow
- Install and follow the public
dcc-mcpSkill. - Inspect the existing CLI, adapter, and live hosts; obtain consent before installing software or changing system state.
- Use
health,dcc-types, andlistto verify the Gateway and target instance. - Search and describe tools for the actual OpenScreen task, then follow every returned
next_step. - Make one bounded change and verify it through host state, files, previews, logs, or rendered output.
dcc-mcp-cli health
dcc-mcp-cli dcc-types
dcc-mcp-cli listCopyable prompt
Use the dcc-mcp Skill to connect to my OpenScreen session. Inspect the existing CLI, adapter, and live instance first; ask before installing software or changing system state. Search for and describe typed tools related to "start one bounded recording through the configured executable", then follow every returned next_step. Do not delete, overwrite, or publish existing work. Make the smallest verifiable change, validate export and verify the requested recording artifact, and report the instance, tool, result, and evidence path.Current availability and official source
Source preview. The 0.1.0 repository has no tag or GitHub Release and is not in the DCC-MCP Core 0.20.25 catalog. Source tests do not establish live Windows recording acceptance; unsupported window selection remains owned by dcc-cua and ui-control.
- OpenScreen adapter repository: source of truth for installation, compatibility, host-specific capabilities, and troubleshooting.
- All AI + DCC control guides: return to every public application and pipeline integration.
- Agent workflow: shared discovery, call, validation, and diagnostic steps.
This page owns the shared Agent workflow and GEO entry point. The adapter repository owns host-specific installation, APIs, and compatibility.

