Computer-Use Agents API MCP Server

by hcompai Your server? Claim it

answering

Computer-Use Agents API is answering right now. Last checked 9 min ago. It exposes 9 tools. Last commit 30 Oct 2026.

Run and manage H Company's Computer-Use Agents from any MCP client.

Uptime history 91 days of history · worst day 98%

91 days agonow

100.0%

Uptime 24h

182 of 182 checks

Tools

read from the server

509 ms

Response time

average over 24h

Stars

last commit 30 Oct 2026

What changed 28

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 13 August 2026. No other catalogue keeps this.

29 Oct 3 tool descriptions were rewritten list_files, read_file, write_file

29 Oct a tool changed the parameters it asks for list_files

26 Oct a tool changed version2 times that day

20 Oct a tool changed version2 times that day

16 Oct a tool description was rewritten run_agent

12 Oct a tool changed version2 times that day

5 Oct 9 tools changed the parameters they ask for cancel_session, list_agents, list_files and 6 more

5 Oct a tool changed version2 times that day

15 Sep 3 tool descriptions were rewritten list_files, read_file, write_file

13 Aug 3 tools appeared list_files, read_file, write_file

and 4 more, back to 13 August 2026

What the code does

We read the source, 3 d ago · tools taken from the live server · rules 995398eba69f

Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

Runs an external command src/hai_agents_local/browser.py:93, src/hai_agents_local/runtime/process.py:60, src/hai_agents_local/workstation.py:60 и ещё 2

        process = subprocess.Popen(

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

This code can reach further than it looks

We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 9 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add hai-agents --transport http https://agp.hcompany.ai/mcp

Settings → Connectors → Add custom connector, then paste this address

https://agp.hcompany.ai/mcp

~/.codex/config.toml

[mcp_servers.hai-agents]
url = "https://agp.hcompany.ai/mcp"

.cursor/mcp.json

{
  "mcpServers": {
    "hai-agents": {
      "url": "https://agp.hcompany.ai/mcp"
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "hai-agents": {
      "type": "http",
      "url": "https://agp.hcompany.ai/mcp"
    }
  }
}

This server publishes 1 more address. The block above uses the one we reach during checks; the full list is under Endpoints below, and the author may intend a particular one for your client.

Available tools 9

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

file

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-manager session id.

write_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.

agent

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 revision, or ``name:N`` to run revision N.

agents

list_agents

List agents the caller can run: their org's agents plus the public ``h/`` ones.

cancel

cancel_session

Cancel a session; a no-op if it does not exist or already finished.

files

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 ``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.

send

send_message

Send a follow-up message to a running session.

share_session

Make a session publicly readable and return its absolute share URL.

wait

wait_for_session

Poll a session: with ``wait`` long-poll for the answer, else return the current snapshot.

Endpoints

URL	Transport	State	Latency	Checked
https://agp.hcompany.ai/mcp	streamable-http	answering	762 ms	9 min ago
https://agp.eu.hcompany.ai/mcp	streamable-http	answering	237 ms	10 min ago

Alternatives to Computer-Use Agents API

same job, measured the same way

FrelyMCP

by frely

Use your own computers, cloud tools and AI agents from any MCP client with one Frely login.

5 tools answering

Reason

by reason-machines

Start and manage Reason cloud coding agents, projects and sessions from any MCP client.

answering

Storydoc

by storydoc

Generate and manage Storydoc presentations from any MCP-compatible client.

answering

Google Tasks MCP Server

by ebmurha

Manage Google Tasks from MCP-compatible AI clients.

115 installs/wk local only

Openuptime

by openuptime

Manage uptime monitors, incidents and status pages from any MCP client.

answering

Mio Computer-Use Agent

by mldlbs

Control this Windows desktop from any MCP client: files, windows, keyboard and mouse.

89 installs/wk local only

AgentGo

by nishkalkashyap

Run Codex and Claude Code on your computer from an MCP client, and track or continue their runs.

77 installs/wk local only

Warp Ozbridge

by sena-labs

OzBridge: run Warp Oz agents from any MCP client — Claude Code, Cursor, Codex, VS Code.

310 installs/wk local only

Computer-Use Agents API — questions

Answers built from our own checks of this server.

What can Computer-Use Agents API do?

It exposes 9 tools, read directly from the server on our last check. Among them: cancel_session, list_agents, list_files, read_file, run_agent, send_message and 3 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →

Is Computer-Use Agents API working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 182 of 182 checks got a reply (100.0%), average response time 509 ms. The bar chart above shows every period we have measured.

How do I connect Computer-Use Agents API?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.

Does Computer-Use Agents API need an API key?

No. Computer-Use Agents API completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 9 of them are readable on this page. This is what we observed, not what the docs claim.

How fast is Computer-Use Agents API?

It answers our handshake in 509 ms on average, which is faster than 24% of all working MCP servers we measure. That is on the slow side — worth knowing if the tool sits inside an interactive loop. The comparison comes from our own checks across the whole registry, every 15 minutes.

Is Computer-Use Agents API open source?

The code is open source: it is published under the MIT licence, written in Python, 45 stars on GitHub and 4 open issues. The licence covers the code in the repository, not the hosted service at agp.hcompany.ai, which runs on its operator's own terms.