MCP CPG Human in the Loop (HITL)
REMOTE · MCP.CPGHUMANINTHELOOP.AI · SCANNED SEP 22
Navigator for BPC Agentic Procurement
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 Security60
- 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 4 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 is configured correctly; the domain's records validate against the full chain to the root. View diagnostics → Pass
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability79
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 512 tokens (~128/item across 4 items; 4 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- 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 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 4 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 4 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 MCP CPG Human in the Loop (HITL) server?
MCP CPG Human in the Loop (HITL) is a hosted endpoint at https://mcp.cpghumanintheloop.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 · mcp.cpghumanintheloop.ai
claude mcp add --transport http greencore-solutions-cpg-human-in-the-loop 'https://mcp.cpghumanintheloop.ai/mcp'
{
"mcpServers": {
"greencore-solutions-cpg-human-in-the-loop": {
"url": "https://mcp.cpghumanintheloop.ai/mcp"
}
}
} {
"servers": {
"greencore-solutions-cpg-human-in-the-loop": {
"type": "http",
"url": "https://mcp.cpghumanintheloop.ai/mcp"
}
}
} [mcp_servers.greencore-solutions-cpg-human-in-the-loop] url = "https://mcp.cpghumanintheloop.ai/mcp"
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"greencore-solutions-cpg-human-in-the-loop": {
"type": "remote",
"url": "https://mcp.cpghumanintheloop.ai/mcp",
"enabled": true
}
}
} openclaw mcp add greencore-solutions-cpg-human-in-the-loop --url 'https://mcp.cpghumanintheloop.ai/mcp' --transport streamable-http
mcp_servers:
greencore-solutions-cpg-human-in-the-loop:
url: "https://mcp.cpghumanintheloop.ai/mcp" {
"McpServers": {
"greencore-solutions-cpg-human-in-the-loop": {
"Transport": "http",
"Url": "https://mcp.cpghumanintheloop.ai/mcp"
}
}
} assistant mcp add greencore-solutions-cpg-human-in-the-loop -t streamable-http -u 'https://mcp.cpghumanintheloop.ai/mcp'
{
"mcpServers": {
"greencore-solutions-cpg-human-in-the-loop": {
"type": "http",
"url": "https://mcp.cpghumanintheloop.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.
- 17 Sept 26 0
- Server version: 1.0.2 → 1.0.3 functional
- 10 Sept 26 −1
- Tool “escalate” rewrote its description, which is the text the model reads security
- Server version: 1.0.0 → 1.0.2 functional
- Tool “escalate” changed its title: Escalate to a human (CPG-451) → Escalate to a human (ACM-451) cosmetic
- 29 Aug 26 +1
- Tool “escalate” rewrote its description, which is the text the model reads security
- Tool “escalate” changed its title: Escalate to a human (ACM-451) → Escalate to a human (CPG-451) cosmetic
- 28 Aug 26 +1
- Schema quality: 164 → 128 ▲ functional
- Server version: 1.2.0 → 1.0.0 functional
- “escalate” dropped the optional parameter “agent_card” cosmetic
- “request_terms” dropped the optional parameter “agent_card” cosmetic
- “submit_rfq” dropped the optional parameter “agent_card” cosmetic
- 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 +1
- DNSSEC: fail → pass ▲ security
- Stability: 0.97 → pass security
- Schema quality: 128 → 164 ▼ functional
- Server version: 1.0.0 → 1.2.0 functional
- “escalate” added an optional parameter “agent_card” cosmetic
- “request_terms” added an optional parameter “agent_card” cosmetic
- “submit_rfq” added an optional parameter “agent_card” cosmetic
- 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
- 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 22 Sept 2026 · Probed https://mcp.cpghumanintheloop.ai/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=cpghumanintheloop.ai | CN=WE1,O=Google Trust Services,C=US | 16 Sept 2026 | 15 Dec 2026 | ECDSA 256 | ECDSA-SHA256 | 6e318a2df9e8fda30ecff2b1716b594f |
| SANs: cpghumanintheloop.ai, *.cpghumanintheloop.ai | ||||||
| CN=WE1,O=Google Trust Services,C=US (CA) | CN=GTS Root R4,O=Google Trust Services LLC,C=US | 13 Dec 2023 | 20 Feb 2029 | ECDSA 256 | ECDSA-SHA384 | 7ff31977972c224a76155d13b6d685e3 |
| CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) | CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE | 15 Nov 2023 | 28 Jan 2028 | ECDSA 384 | SHA256-RSA | 7fe530bf331343bedd821610493d8a1b |
Background: What to check on a remote MCP endpoint →
DNSSEC secure
Validation of mcp.cpghumanintheloop.ai. — Secure
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| ai. | present | 3799 | 8 | Verified |
| cpghumanintheloop.ai. | present | 2371 | 13 | Verified |
| mcp.cpghumanintheloop.ai. | Verified address RRset verified with the apex keys |
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://mcp.cpghumanintheloop.ai/mcp | Verified | 200 | |
| http (plaintext) | http://mcp.cpghumanintheloop.ai/mcp | HTTPS enforced | 301 | https://mcp.cpghumanintheloop.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 →
check_rfq_status Check ticket status ~71
Poll a ticket previously lodged on this MCP (RFQ, terms request, or escalation). Returns current status and, once a human has answered, the answer.
| Name | Type | Req | Description |
|---|---|---|---|
| ticket_id | string | yes | Ticket ID returned at submission, e.g. HITL-20260719-A1B2C3 |
No output schema declared.
No examples provided.
escalate Escalate to a human (ACM-451) ~122
Hand a matter that cannot be resolved deterministically to GSC Navigator human review. Emits ACM-451 ESCALATE. Returns a ticket ID for polling via check_rfq_status.
| Name | Type | Req | Description |
|---|---|---|---|
| context | string | yes | What was attempted, what could not be resolved, and why |
| related_ticket | string | – | Optional earlier ticket this relates to |
| requester_contact | string | yes | Reply channel: email or URL a human can answer to |
| requester_name | string | yes | Requesting organization or agent operator |
| subject | string | yes | One-line summary of the matter |
No output schema declared.
No examples provided.
request_terms Request terms ~122
Ask a commercial or procedural question — terms, conditions, eligibility context, process. The question is lodged as a ticket and a human answers it. Returns a ticket ID for polling via check_rfq_status.
| Name | Type | Req | Description |
|---|---|---|---|
| question | string | yes | The question a human should answer |
| related_ticket | string | – | Optional earlier ticket this relates to |
| requester_contact | string | yes | Reply channel: email or URL a human can answer to |
| requester_name | string | yes | Requesting organization or agent operator |
| subject | string | yes | One-line summary of the question |
No output schema declared.
No examples provided.
submit_rfq Submit RFQ ~197
Lodge a request-for-quotation with GreenCore Solutions Corp. A human reviews and answers every ticket — no order is decided by this tool. Returns a ticket ID for polling via check_rfq_status. Optionally reference a GTIN resolved on mcp.cpgknowledgegraph.ai and an SM-ECO-10060 market code.
| Name | Type | Req | Description |
|---|---|---|---|
| details | string | yes | Full request: product, volumes, timing, destination |
| gtin | string | – | Optional GTIN reference (as resolved on the CPG Knowledge Graph) |
| market | string | – | Optional SM-ECO-10060 member code, e.g. FR, AU, MX |
| quantity | string | – | Optional quantity / volume expression |
| requester_contact | string | yes | Reply channel: email or URL a human can answer to |
| requester_name | string | yes | Requesting organization or agent operator |
| subject | string | yes | One-line summary of the RFQ |
No output schema declared.
No examples provided.
What is the MCP CPG Human in the Loop (HITL) server?
MCP CPG Human in the Loop (HITL) is listed in the public MCP registry as io.github.greencore-solutions/cpg-human-in-the-loop. Navigator for BPC Agentic Procurement. This page covers its hosted endpoint (https://mcp.cpghumanintheloop.ai/mcp).
Is the MCP CPG Human in the Loop (HITL) server safe to use?
MCP CPG Human in the Loop (HITL) scores 80 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 MCP CPG Human in the Loop (HITL) server expose?
MCP CPG Human in the Loop (HITL) exposes 4 tools: submit_rfq, check_rfq_status, request_terms, escalate. Their descriptions and schemas cost roughly 512 tokens of context every time the server is loaded.
Does the MCP CPG Human in the Loop (HITL) server require authentication?
No. We connected to MCP CPG Human in the Loop (HITL) without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the MCP CPG Human in the Loop (HITL) server still maintained?
MCP CPG Human in the Loop (HITL) is still listed as active in the MCP registry. We last reached this channel on 22 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.