Computer-Use Agents API
Server Details
Run and manage H Company's Computer-Use Agents from any MCP client.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- hcompai/hai-agents-python
- GitHub Stars
- 31
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 9 tools
Each tool has a clearly distinct resource/action: agent discovery, session start/wait/message/cancel/share, and file list/read/write. The only near-overlap is run_agent returning a session handle and wait_for_session polling it, but their descriptions make the boundary clear.
All nine tools follow a consistent snake_case verb_noun pattern: cancel_session, list_agents, list_files, read_file, run_agent, send_message, share_session, wait_for_session, write_file. There are no mixed conventions or vague names.
Nine tools is well-scoped for a computer-use agents API covering agent discovery, session lifecycle, messaging, sharing, and basic file access. No tool appears redundant or unnecessary.
Core lifecycle is covered: list agents, run/wait/message/cancel sessions, share sessions, and list/read/write files. Minor gaps remain, such as no list_sessions/get_session, no unshare_session, and no delete_file, but agents can work around most of these via session handles and returned snapshots.
Available Tools
9 toolscancel_sessionCancel SessionAInspect
Cancel a session; a no-op if it does not exist or already finished.
Inputs: session_id (required). Returns: object
list_agentsList AgentsBInspect
List agents the caller can run: their org's agents plus the public h/ ones.
Inputs: page, size. Returns: object
list_filesList FilesAInspect
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 run_agent returns, or an env-manager session id.
When a listing is truncated, page on the last entry's modified_at (ISO-8601) and name, passed as modified_before and name_after. Send both: modification times are not unique, and a timestamp alone skips the rest of a tied group.
Inputs: session_id (required), path, name_after, max_entries, +1 more. Returns: object
read_fileRead FileAInspect
Read a file from a session's machine; returns base64 content and metadata.
session_id is the id run_agent returns, or an env-manager session id.
Inputs: path (required), session_id (required). Returns: object
run_agentRun AgentAInspect
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 revision, or name:N to run revision N.
Inputs: task (required), agent (required), max_steps, max_time_s, +1 more. Returns: object
send_messageSend MessageBInspect
Send a follow-up message to a running session.
Inputs: message (required), session_id (required). Returns: object
wait_for_sessionWait For SessionAInspect
Poll a session: with wait long-poll for the answer, else return the current snapshot.
Inputs: session_id (required), wait. Returns: object
write_fileWrite FileBInspect
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.
Inputs: path (required), session_id (required), content_base64 (required). Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Start and manage Reason cloud coding agents, projects and sessions from any MCP client.
Remote MCP utilities for agents: structured data, commerce checks, and x402 paid API discovery.
Use a person's computer after they approve it there: files, Terminal, browser, local MCP.
Use a person's computer after they approve it there: files, Terminal, browser, local MCP.
Related MCP Servers
AlicenseNot gradedqualityBmaintenanceEnables MCP clients to provision and control agent computers that provide workspace-scoped file tools, terminal command execution, and optional Playwright browser automation.4,862 npmApache 2.0- AlicenseNot gradedqualityBmaintenanceEnables models to remotely control computers over an MCP link, running commands, managing files, automating desktops and browsers, transferring data, and coordinating durable tasks across sessions.626 npmMIT
- AlicenseAqualityCmaintenanceEnables MCP clients to start and steer persistent terminals and coding agents, run commands and edit files on local or remote machines, and arrange the Herdr desktop window.25MIT
- AlicenseNot gradedqualityBmaintenanceEnables MCP clients to spawn and manage collaboration-style external subagents with persistent sessions, queued messaging, nested delegation limits, and shared budget/concurrency controls, plus a bilingual Windows desktop control UI.MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.