Categories › AI & Agents › Multi-agent, orchestration & workflows
Run and manage H Company's Computer-Use Agents from any MCP client.
Remote server: your requests and data go to agp.hcompany.ai. Claude Code: claude mcp add --transport http computer-use-agents-api https://agp.hcompany.ai/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
run_agent — Start an agent on a task; return the answer or a session handle to wait on. ``agent`` is a name from list_agents, which runs its latest reviwait_for_session — Poll a session: with ``wait`` long-poll for the answer, else return the current snapshot.list_agents — List agents the caller can run: their org's agents plus the public ``h/`` ones.send_message — Send a follow-up message to a running session.cancel_session — Cancel a session; a no-op if it does not exist or already finished.share_session — Make a session publicly readable and return its absolute share URL.list_files — List files on a session's machine, newest first; by default its environment's own, such as a browser's downloads. ``session_id`` is the id `read_file — Read a file from a session's machine; returns base64 content and metadata. ``session_id`` is the id ``run_agent`` returns, or an env-managerwrite_file — Write base64-encoded content to a file on a session's machine. ``session_id`` is the id ``run_agent`` returns, or an env-manager session id.Not tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.