Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Opus 4.8 Agent

REMOTE · FARM.LLMOTIONS.COM · SCANNED SEP 21

Authenticated async Opus 4.8 Agent agent with status polling and artifact results.

0 this week 79 Trust /100

Recent critical change

Authorization (21 Sept 2026). See the changelog before you install this server.

Trust breakdown (7 categories)

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
Transport & Reachability100
Schema Quality & AI Usability79
  • AI-judged instruction clarity (excellent).Pass
  • Tool/resource definitions use about 270 tokens (~54/item across 5 items; 5 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management97
  • Stability observed for 29 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 5 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 6 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
Install

How do I install the Opus 4.8 Agent MCP server?

Opus 4.8 Agent is a hosted endpoint at https://farm.llmotions.com/mcp/agents/opus-4-8-agent, 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 · farm.llmotions.com

# add to Claude Code
claude mcp add --transport http com-llmotions-farm-opus-4-8-agent 'https://farm.llmotions.com/mcp/agents/opus-4-8-agent'
// .cursor/mcp.json
{
  "mcpServers": {
    "com-llmotions-farm-opus-4-8-agent": {
      "url": "https://farm.llmotions.com/mcp/agents/opus-4-8-agent"
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "com-llmotions-farm-opus-4-8-agent": {
      "type": "http",
      "url": "https://farm.llmotions.com/mcp/agents/opus-4-8-agent"
    }
  }
}
# ~/.codex/config.toml
[mcp_servers.com-llmotions-farm-opus-4-8-agent]
url = "https://farm.llmotions.com/mcp/agents/opus-4-8-agent"
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-llmotions-farm-opus-4-8-agent": {
      "type": "remote",
      "url": "https://farm.llmotions.com/mcp/agents/opus-4-8-agent",
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add com-llmotions-farm-opus-4-8-agent --url 'https://farm.llmotions.com/mcp/agents/opus-4-8-agent' --transport streamable-http
# ~/.hermes/config.yaml
mcp_servers:
  com-llmotions-farm-opus-4-8-agent:
    url: "https://farm.llmotions.com/mcp/agents/opus-4-8-agent"
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "com-llmotions-farm-opus-4-8-agent": {
      "Transport": "http",
      "Url": "https://farm.llmotions.com/mcp/agents/opus-4-8-agent"
    }
  }
}
# add to Vellum
assistant mcp add com-llmotions-farm-opus-4-8-agent -t streamable-http -u 'https://farm.llmotions.com/mcp/agents/opus-4-8-agent'
// mcp.json
{
  "mcpServers": {
    "com-llmotions-farm-opus-4-8-agent": {
      "type": "http",
      "url": "https://farm.llmotions.com/mcp/agents/opus-4-8-agent"
    }
  }
}

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

Changelog

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.

  • 21 Sept 26 +1
    • Authorization: unverified → fail critical
  • 20 Sept 26 −1
    • Stability: pass → 0.93 functional
  • 19 Sept 26 +46
    • Injection markers: unverified → pass security
    • Stability: unverified → pass security
    • Authorization: Authorisation not fully verified: this server exposes a tool marked destructive (agentfarm_cancel_run) and its handshake is open, but we could not confirm whether a tool call is gated, so we do not assert it is callable unauthenticated. security
    • Endpoint reachability: not serving MCP → reachable functional
    • Tool coverage: unverified → 100 functional
    • MCP protocol: unverified → pass functional
  • 17 Sept 26 +10
    • Transport: fail → pass security
  • 16 Sept 26 −56
    • Endpoint reachability: reachable → not serving MCP security
    • Authorization: fail → unverified security
    • Tool safety: pass → unverified security
    • Stability: 0.97 → unverified security
    • Transport: pass → fail security
    • Capabilities: pass → unverified functional
    • Tool coverage: 100 → unverified functional
  • 15 Sept 26 0
    • Stability: pass → 0.97 functional
  • 12 Sept 26 +46
    • Authorization: unverified → fail critical
    • Injection markers: unverified → pass security
    • Stability: unverified → pass security
    • Endpoint reachability: not serving MCP → reachable functional
    • Tool coverage: unverified → 100 functional
    • MCP protocol: unverified → pass functional
  • 11 Sept 26 −46
    • Endpoint reachability: reachable → not serving MCP security
    • Stability: pass → unverified security
    • Tool safety: pass → unverified security
    • Authorization: Authorisation not fully verified: no authorisation is required to connect, but we couldn't read the tool list to see what that exposes. security
    • Capabilities: pass → unverified functional
    • Tool coverage: 100 → unverified functional
Diagnostics

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 21 Sept 2026 · Probed https://farm.llmotions.com/mcp/agents/opus-4-8-agent

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=farm.llmotions.com CN=YE1,O=Let's Encrypt,C=US 15 Aug 2026 13 Nov 2026 ECDSA 256 ECDSA-SHA384 5ddb781bf971ca577255c1ba45d28485888
SANs: farm.llmotions.com
CN=YE1,O=Let's Encrypt,C=US (CA) CN=Root YE,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 ECDSA 384 ECDSA-SHA384 5ddd70dd31f801c85c186a7a04b80afe
CN=Root YE,O=ISRG,C=US (CA) CN=ISRG Root X2,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 ECDSA-SHA384 872165fc34b6e5fba8add5b3705fb53a
CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 SHA256-RSA 6c8f1dc727c7117f7baf853ac980f9cd

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of farm.llmotions.com. Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
com. present 19718 13 Verified
llmotions.com. 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://farm.llmotions.com/mcp/agents/opus-4-8-agent Verified 200
http (plaintext) http://farm.llmotions.com/mcp/agents/opus-4-8-agent HTTPS enforced 301 https://farm.llmotions.com/mcp/agents/opus-4-8-agent
MCP tools · 5 exposed · ~241 tokens

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 →

Tool Tokens
agentfarm_agent_info ~44

Returns this agent's identity, listed per-task price, MCP endpoint, and access URL. This metadata call does not run the model and does not require a bearer token.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

agentfarm_cancel_run ~31

Cancels an authenticated queued or running run.

NameTypeReqDescription
run_idstringyesAgentFarm run identifier.

No output schema declared.

No examples provided.

agentfarm_create_run ~92

Queues an authenticated asynchronous task. This can consume paid model capacity. Poll with agentfarm_get_run_status, then read agentfarm_get_run_result.

NameTypeReqDescription
idempotency_keystringOptional retry key; the same key and input return the original run.
taskstringyesTask for the agent to complete.
task_inputOptional JSON-compatible context or input data for the task.

No output schema declared.

No examples provided.

agentfarm_get_run_result ~36

Returns the final summary and artifact download URLs for an authenticated run.

NameTypeReqDescription
run_idstringyesAgentFarm run identifier.

No output schema declared.

No examples provided.

agentfarm_get_run_status ~38

Returns queued, running, succeeded, or failed status for an authenticated run.

NameTypeReqDescription
run_idstringyesAgentFarm run identifier.

No output schema declared.

No examples provided.

Common questions

What is the Opus 4.8 Agent MCP server?

Opus 4.8 Agent is an MCP server listed in the public MCP registry as com.llmotions.farm/opus-4-8-agent. Authenticated async Opus 4.8 Agent agent with status polling and artifact results. This page covers its hosted endpoint (https://farm.llmotions.com/mcp/agents/opus-4-8-agent).

Is the Opus 4.8 Agent MCP server safe to use?

Opus 4.8 Agent scores 79 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 Opus 4.8 Agent MCP server expose?

Opus 4.8 Agent exposes 5 tools: agentfarm_agent_info, agentfarm_create_run, agentfarm_get_run_status, agentfarm_get_run_result, agentfarm_cancel_run. Their descriptions and schemas cost roughly 241 tokens of context every time the server is loaded.

Does the Opus 4.8 Agent MCP server require authentication?

No. We connected to Opus 4.8 Agent without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the Opus 4.8 Agent MCP server still maintained?

Opus 4.8 Agent is still listed as active in the MCP registry. We last reached this channel on 21 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.