Robin Saige we check the tools AI agents call

Computer-Use Agents API

io.github.hcompai/hai-agents

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

— the operator's own registry description reported

Publisher io.github.hcompai · first seen 2026-08-12 · endpoint https://agp.hcompany.ai/mcp

allow
verdict
mid-slow-solo
cluster
ok_tools
answers
9
tools served

Dependency rating derived

allow — mid-slow-solo — safe to depend on

Cluster mid-slow-solo · distinctiveness 0.553 (moderate). Every figure is a percentile or class within the 11,094-server censussee the whole spectrum.

Reach — can an agent get to it?
answersalive_tools
latency538 ms
vs populationslow
protocolcurrent
authopen
Use — can it use it?
tools9
vs populationmid
capabilities5
harnessB
Trust — can it rely on it?
identitysolo
servers on its host1
verifiabilityunassessed
duplicate inventoryno
drift events0
answers trueno primary

🔏 Signed receipt rr_b8936d9a8ab8d789daaff270 · ed25519 · key rs-rcpt-2026-08 — this rating is tamper-evident; an agent gets the full signature from check_server and can verify it against the published key.

Tools last seen

cancel_session list_agents list_files read_file run_agent send_message share_session wait_for_session write_file

Harness readiness observed

Can an agent's harness pick this tool and call it correctly? Graded on the three things an agent reads — name, description, typed parameters. Band B — usable, with rough edges.

legibility checktools passingok
name is clear & specific9/9
has a description9/9
description is substantive9/9
parameters are typed9/9
parameters are described0/90/9

9 of 9 tools graded · 9 with a captured input schema. RS-008, Tier-1 — no domain knowledge, applies to any tool. “Alive” is not the same as “usable”.

Truth checks observed

Not in the Tier-2 trade lane, or not yet checked. Tier-2 re-derives a server's answers against published primary sources — see truth checks.

Protocol conformance observed

2025-06-18
protocol version
session model
2.14.7
server version hai-agents

Capabilities: experimental prompts resources tasks tools

Drift

No confirmed drift on record. Baseline set 2026-08-14; changes appear here after human review.

History observed

Every probe we made, oldest → newest (2 shown, 2026-08-12 → 2026-08-14). Green answered · amber answered-but-walled · red no useful answer. A gap in our cadence is a gap in coverage, not evidence about the server.

changelog (2 events)
datetypewhat changed
2026-08-14inventorytools 6 → 9
2026-08-12outcomefirst probe: ok_tools
raw probe records
probed (UTC) outcomehttpmsprotocol
2026-08-14T19:59:36Zok_tools2005382025-06-18
2026-08-12T05:34:49Zok_tools2004752025-06-18

Watch or embed this verdict

verdict badge

Operators: put the live verdict in your README — it updates with every census, links back here, and is a dated observation, never a warranty:

[![Robin Saige verdict](https://robinsaige.com/badge/io.github.hcompai/hai-agents.svg)](https://robinsaige.com/s/io.github.hcompai/hai-agents)

Depend on it? Subscribe to its change feed — outcome changes and confirmed drift, no account needed. Building on it? The full dossier as JSON — verdict, rating, truth checks, history — stable enough to gate CI on.

← overview