MCP.Market

Computer-Use Agents API MCP server

online · 100% uptime
by hcompai·io.github.hcompai/hai-agents·v1.0.0·35 stars
No reviews yet

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

A89/100grade A
Write a reviewRun it
What users say
No reviews yet
Be the first
Safety scan
A89/100

full report

Adoption
Growing

35 stars

Reviews

Write one

Nobody has reviewed Computer-Use Agents API yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Computer-Use Agents API tools (9, 4 write)

write = sends, deletes, buys or posts
  • cancel_sessionwrite actionFree

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

  • list_agentsFree

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

  • list_filesFree

    List files on a browser session's machine (e.g. downloads), newest first. ``session_id`` is the browser session id issued by env-manager when the session was created, not the id ``run_agent`` returns. 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.

  • read_fileFree

    Read a file from a browser session's machine; returns base64 content and metadata. ``session_id`` is the browser session id issued by env-manager when the session was created, not the id ``run_agent`` returns.

  • run_agentwrite actionFree

    Start an agent on a task; return the answer or a session handle to wait on. ``agent`` from list_agents.

  • send_messagewrite actionFree

    Send a follow-up message to a running session.

  • share_sessionFree

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

  • wait_for_sessionFree

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

  • write_filewrite actionFree

    Write base64-encoded content to a file on a browser session's machine. ``session_id`` is the browser session id issued by env-manager when the session was created, not the id ``run_agent`` returns.

Public scan report

scanner v0.1.9 · 2026-09-26 · same rubric, same numbers if you re-run it

no findings
  • –Code scanremote-only server, no package to scann/a
  • Live reliabilityremote reachable in 1210ms20/20
  • Tool poisoning9 tool descriptions checked15/15
  • Auth qualityAPI key sent as a header8/15
  • Maintenancelast push 1 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year9/10
Overall 89/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Computer-Use Agents API compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
89/100
higher than 80% of 48,255 servers
Tools
9
the typical server has 7
Tools that change things
44%
typical: 0%. Fewer write tools means less an agent can break
Uptime
100%
of our recent checks; the typical remote server answers 100%
Response time
836 ms
faster than 15% of 30,031 servers
GitHub stars
35
more than 92% of 28,688 servers

What its tools let an agent do: 4 read · 1 create · 1 delete · 2 send or post · 1 run or deploy

Install Computer-Use Agents API in Claude Code, Cursor or VS Code

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

What the publisher says

From the Computer-Use Agents API repository's README, as published. We do not edit it. Read it on GitHub

Python SDK for H Company's Agents API.

Documentation  ·  Get an API key  ·  PyPI  ·  TypeScript SDK  ·  H Company

Installation

pip install hai-agents

Add the optional command-line tools with the cli extra:

pip install "hai-agents[cli]"

Python 3.10 or newer is required. Get an API key at platform.hcompany.ai/settings/api-keys and export it:

export HAI_API_KEY=hk-...

Quickstart

Launch the built-in h/web-surfer-pro agent, which ships with its own browser, and describe the task in plain language. run_session polls until the agent finishes and returns the final answer.

from hai_agents import Client

client = Client()

result = client.run_session(
    agent="h/web-surfer-pro",
    messages="What are the top 3 stories on Hacker News right now?",
)

print(result.status)
print(result.answer)

Client() reads HAIAPIKEY from the environment.

result is a SessionRunResult: id, status, answer, the accumulated events, and final_changes.

How a session works

A session is one run of an agent against a task. It moves through a small set of states: pending, running, and then a settled state such as completed, idle, failed, timed_out, or interrupted.

You drive a session two ways. runsession creates it and blocks until it settles, which suits one-shot tasks. startsession creates it and returns a handle right away, so you can read and steer the agent while it works.

session = client.start_session(
    agent="h/web-surfer-pro",
    messages="Find the top story on Hacker News",
)

print(session.id)
result = session.wait_for_completion()
print(result.status, result.answer)

Watch and steer a running session

A handle bound to the session id exposes the full lifecycle. Read the agent's progress at three levels of detail:

session.status()
session.changes(from_index=0)
session.get()

status() is a cheap snapshot with the state, step count, and token usage. changes(from_index=0) long-polls for new events and the final answer. get() returns the full Session resource.

While the session is not in a terminal state, you can intervene:

session.send_message({"type": "user_message", "message": "Only consider the last 24 hours"})
session.pause()
session.resume()
session.force_answer()
session.cancel()

sendmessage redirects the agent on its next step and wakes an idle session. pause halts with state preserved until resume. forceanswer makes the agent stop exploring and answer from what it has. cancel ends the session as interrupted.

Multi-turn sessions

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Computer-Use Agents API: common questions

Is Computer-Use Agents API MCP server safe?
Yes, by our scan: it is graded A (89/100). Read the Computer-Use Agents API safety report
How do I install Computer-Use Agents API?
It runs remotely at agp.hcompany.ai. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
Does Computer-Use Agents API need an API key?
Yes. The registry entry asks for Authorization.
Is Computer-Use Agents API maintained?
The last commit was 40 days ago (2026-09-25). The latest release is v1.0.0.
Is Computer-Use Agents API up?
100% of our last 28 checks got an answer. We check remote servers about four times a day.
How does Computer-Use Agents API compare with other MCP servers?
safety score 89/100 (higher than 80% of 48,255 servers); tools 9 (the typical server has 7); tools that change things 44% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.