GMTRENCHOR
NPM · GMTRENCHOR-MCP · SCANNED SEP 20
Arc launch intelligence with a free published track record: first hours, deployers, open calls.
Available components
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security98
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- 32 of 97 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency19
- Repository check failed: no source repository is declared. See how to fix → View diagnostics → Fail
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 0 days ago).Pass
- Security-disclosure policy not yet verified: we couldn't inspect the source repository.Unverified
Schema Quality & AI Usability74
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 618 tokens (~103/item across 6 items; 6 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
- Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
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 6 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
Unverified: 1 category
A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.
How do I install the GMTRENCHOR MCP server?
GMTRENCHOR runs locally as an npm package, launched with npx -y gmtrenchor-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · gmtrenchor-mcp
claude mcp add xyz-honeycheck-gmtrenchor-mcp -- npx -y gmtrenchor-mcp
{
"mcpServers": {
"xyz-honeycheck-gmtrenchor-mcp": {
"command": "npx",
"args": [
"-y",
"gmtrenchor-mcp"
]
}
}
} {
"servers": {
"xyz-honeycheck-gmtrenchor-mcp": {
"command": "npx",
"args": [
"-y",
"gmtrenchor-mcp"
]
}
}
} codex mcp add xyz-honeycheck-gmtrenchor-mcp -- npx -y gmtrenchor-mcp
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"xyz-honeycheck-gmtrenchor-mcp": {
"type": "local",
"command": [
"npx",
"-y",
"gmtrenchor-mcp"
],
"enabled": true
}
}
} openclaw mcp add xyz-honeycheck-gmtrenchor-mcp --command npx --arg -y --arg gmtrenchor-mcp
mcp_servers:
xyz-honeycheck-gmtrenchor-mcp:
command: "npx"
args: ["-y", "gmtrenchor-mcp"] {
"McpServers": {
"xyz-honeycheck-gmtrenchor-mcp": {
"Transport": "stdio",
"Command": "npx",
"Arguments": [
"-y",
"gmtrenchor-mcp"
]
}
}
} assistant mcp add xyz-honeycheck-gmtrenchor-mcp -t stdio -c npx -a -y gmtrenchor-mcp
{
"mcpServers": {
"xyz-honeycheck-gmtrenchor-mcp": {
"command": "npx",
"args": [
"-y",
"gmtrenchor-mcp"
]
}
}
} 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.
- 19 Sept 26 65
First indexed and scored.
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 · Analysed npm/gmtrenchor-mcp@1.0.1
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | npm |
Background: How many MCP packages publish verified provenance →
Dependencies 97 packages
| Packages resolved | 97 |
|---|---|
| Stale | 31 |
| No linked repository | 1 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
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 →
carry_persistence ~129
How long funding spreads between Hyperliquid venues have actually lasted, over every hour sampled since 17 August 2026: the share of hours each pair stood above a level, how long an episode ran in consecutive hours, and how often the spread changed sign inside a day, which is what turns a carry into two fees and no position. This is what makes a spread sizeable rather than merely visible. Call it after hyperliquid_carry_spreads, never instead of it. Paid per call.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | How many pairs, most hours open first. Default 10. |
No output schema declared.
No examples provided.
deployer_history ~107
What one Arc address has launched and what became of it: pools attributed by reading each pool's own creation transaction, the share that anyone traded, the share that died and doubled once their horizons passed, the median size of a first hour and how concentrated it was, and the sell-test verdicts counted by name. Every rate states the denominator it was computed over, because the attribution is partial by design. Paid per call.
| Name | Type | Req | Description |
|---|---|---|---|
| address | string | yes | The deployer address on Arc. |
No output schema declared.
No examples provided.
market_context ~84
The Hyperliquid market now and the same hour a day ago for Bitcoin, Ether, HYPE and Solana: funding, open interest, book imbalance and mark, with the change in each, plus the widest funding gap between venues carrying each asset. The backdrop for a cent. An hour we never sampled is null rather than compared against a nearer one. Paid per call.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
open_calls ~102
Every call the scanner has open on Arc right now, with what was known when each was opened: entry price, score and the reasons the gate fired, the pool's liquidity and age, the return so far, the sell-test verdict already published for the token, and the Hyperliquid market at that moment. A record of what was flagged, not a recommendation. Paid per call.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | How many, newest first. Default 10. |
No output schema declared.
No examples provided.
token_microstructure ~115
One Arc token's first hour of trading, frozen while it still existed: how many trades and distinct buyers, dollars through the pool, the largest single buy, what share of the money was three wallets, and the price at ten, thirty and sixty minutes. The chain's public nodes prune this within days, so it cannot be fetched from anywhere at any price. Also carries what was knowable at the time and the outcome once its horizon passed. Paid per call.
| Name | Type | Req | Description |
|---|---|---|---|
| address | string | yes | The token address on Arc. |
No output schema declared.
No examples provided.
track_record ~81
What this scanner has called and what became of it: closed calls per chain with the share that doubled and rugged, the lift against pools that traded and were never called, the outcome of every score band including the ones that do not separate, and what its research engine has refuted. Free, and published failures included. Read this before acting on anything else here.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
What is the GMTRENCHOR MCP server?
GMTRENCHOR is an MCP server listed in the public MCP registry as xyz.honeycheck/gmtrenchor-mcp. Arc launch intelligence with a free published track record: first hours, deployers, open calls. This page covers its npm package (gmtrenchor-mcp).
Is the GMTRENCHOR MCP server safe to use?
GMTRENCHOR scores 65 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. It declares no install or post-install scripts. 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 GMTRENCHOR MCP server expose?
GMTRENCHOR exposes 6 tools: track_record, open_calls, token_microstructure, deployer_history, market_context, carry_persistence. Their descriptions and schemas cost roughly 618 tokens of context every time the server is loaded.
Is the GMTRENCHOR MCP server still maintained?
GMTRENCHOR 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.
What licence is the GMTRENCHOR MCP server under?
GMTRENCHOR declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.