Computer-Use Agents API
REMOTE · AGP.HCOMPANY.AI · 2 COMPONENTS · SCANNED SEP 20
Run and manage H Company's Computer-Use Agents from any MCP client.
Available components
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security57
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation not fully verified: no authorisation is required to call this server, and 9 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe. See how to fix → View diagnostics → Unverified
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability63
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 536 tokens (~59/item across 9 items; 9 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage71
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 0% of tool parameters carry a description.Fail
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety75
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "send_message" implies "send" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
- An AI judge read all 9 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
How do I install the Computer-Use Agents API MCP server?
Computer-Use Agents API is a hosted endpoint at https://agp.hcompany.ai/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · agp.hcompany.ai
claude mcp add --transport http hcompai-hai-agents 'https://agp.hcompany.ai/mcp'
{
"mcpServers": {
"hcompai-hai-agents": {
"url": "https://agp.hcompany.ai/mcp"
}
}
} {
"servers": {
"hcompai-hai-agents": {
"type": "http",
"url": "https://agp.hcompany.ai/mcp"
}
}
} [mcp_servers.hcompai-hai-agents] url = "https://agp.hcompany.ai/mcp"
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"hcompai-hai-agents": {
"type": "remote",
"url": "https://agp.hcompany.ai/mcp",
"enabled": true
}
}
} openclaw mcp add hcompai-hai-agents --url 'https://agp.hcompany.ai/mcp' --transport streamable-http
mcp_servers:
hcompai-hai-agents:
url: "https://agp.hcompany.ai/mcp" {
"McpServers": {
"hcompai-hai-agents": {
"Transport": "http",
"Url": "https://agp.hcompany.ai/mcp"
}
}
} assistant mcp add hcompai-hai-agents -t streamable-http -u 'https://agp.hcompany.ai/mcp'
{
"mcpServers": {
"hcompai-hai-agents": {
"type": "http",
"url": "https://agp.hcompany.ai/mcp"
}
}
} The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 16 Sept 26 −1
- Tool “write_file” rewrote its description, which is the text the model reads security
- Tool “read_file” rewrote its description, which is the text the model reads security
- Tool “list_files” rewrote its description, which is the text the model reads security
- Schema quality: 49 → 59 ▼ functional
- 26 Aug 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 25 Aug 26 0
- Stability: 0.97 → pass security
- 24 Aug 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.
- 14 Aug 26 0
- Schema quality: 41 → 49 ▼ functional
- New tool “write_file” functional
- New tool “read_file” functional
- New tool “list_files” functional
- 11 Aug 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 7 Aug 26 0
- The server no longer declares the “experimental” capability functional
- 31 Jul 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 20 Sept 2026 · Probed https://agp.hcompany.ai/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=agp.hcompany.ai | CN=Amazon RSA 2048 M01,O=Amazon,C=US | 3 Sept 2026 | 19 Mar 2027 | RSA 2048 | SHA256-RSA | e05f085a1ae97b7ad8d04696fb52729 |
| SANs: agp.hcompany.ai | ||||||
| CN=Amazon RSA 2048 M01,O=Amazon,C=US (CA) | CN=Amazon Root CA 1,O=Amazon,C=US | 23 Aug 2022 | 23 Aug 2030 | RSA 2048 | SHA256-RSA | 77312380b9d6688a33b1ed9bf9ccda68e0e0f |
| CN=Amazon Root CA 1,O=Amazon,C=US (CA) | CN=Starfield Services Root Certificate Authority - G2,O=Starfield Technologies\, Inc.,L=Scottsdale,ST=Arizona,C=US | 25 May 2015 | 31 Dec 2037 | RSA 2048 | SHA256-RSA | 67f944a2a27cdf3fac2ae2b01f908eeb9c4c6 |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of agp.hcompany.ai. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| ai. | present | 3799 | 8 | Verified |
| hcompany.ai. | absent | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://agp.hcompany.ai/mcp | Verified | 200 | |
| http (plaintext) | http://agp.hcompany.ai/mcp | HTTPS enforced | 301 | https://agp.hcompany.ai/mcp |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
cancel_session ~32
Cancel a session; a no-op if it does not exist or already finished.
| Name | Type | Req | Description |
|---|---|---|---|
| session_id | string | yes | – |
Structured output declared, but exposes no named fields.
No examples provided.
list_agents ~42
List agents the caller can run: their org's agents plus the public ``h/`` ones.
| Name | Type | Req | Description |
|---|---|---|---|
| page | integer | – | – |
| size | integer | – | – |
Structured output declared, but exposes no named fields.
No examples provided.
list_files ~142
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.
| Name | Type | Req | Description |
|---|---|---|---|
| max_entries | integer | – | – |
| modified_before | – | – | – |
| name_after | – | – | – |
| path | string | – | – |
| session_id | string | yes | – |
Structured output declared, but exposes no named fields.
No examples provided.
read_file ~69
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.
| Name | Type | Req | Description |
|---|---|---|---|
| path | string | yes | – |
| session_id | string | yes | – |
Structured output declared, but exposes no named fields.
No examples provided.
run_agent ~68
Start an agent on a task; return the answer or a session handle to wait on. ``agent`` from list_agents.
| Name | Type | Req | Description |
|---|---|---|---|
| agent | string | yes | – |
| idempotency_key | – | – | – |
| max_steps | – | – | – |
| max_time_s | – | – | – |
| task | string | yes | – |
Structured output declared, but exposes no named fields.
No examples provided.
send_message ~33
Send a follow-up message to a running session.
| Name | Type | Req | Description |
|---|---|---|---|
| message | string | yes | – |
| session_id | string | yes | – |
Structured output declared, but exposes no named fields.
No examples provided.
share_session ~28
Make a session publicly readable and return its absolute share URL.
| Name | Type | Req | Description |
|---|---|---|---|
| session_id | string | yes | – |
Structured output declared, but exposes no named fields.
No examples provided.
wait_for_session ~45
Poll a session: with ``wait`` long-poll for the answer, else return the current snapshot.
| Name | Type | Req | Description |
|---|---|---|---|
| session_id | string | yes | – |
| wait | boolean | – | – |
Structured output declared, but exposes no named fields.
No examples provided.
write_file ~77
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.
| Name | Type | Req | Description |
|---|---|---|---|
| content_base64 | string | yes | – |
| path | string | yes | – |
| session_id | string | yes | – |
Structured output declared, but exposes no named fields.
No examples provided.
What is the Computer-Use Agents API MCP server?
Computer-Use Agents API is an MCP server listed in the public MCP registry as io.github.hcompai/hai-agents. Run and manage H Company's Computer-Use Agents from any MCP client. This page covers its hosted endpoint (https://agp.hcompany.ai/mcp).
Is the Computer-Use Agents API MCP server safe to use?
Computer-Use Agents API scores 72 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Computer-Use Agents API MCP server expose?
Computer-Use Agents API exposes 9 tools: run_agent, wait_for_session, list_agents, send_message, cancel_session, and 4 more. Their descriptions and schemas cost roughly 536 tokens of context every time the server is loaded.
Does the Computer-Use Agents API MCP server require authentication?
No. We connected to Computer-Use Agents API without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the Computer-Use Agents API MCP server still maintained?
Computer-Use Agents API is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.