Marsnme Gateway MCP Server
@marsnme/mcp-gateway
npm
v0.3.0
Source verified
Published by marsmanleo — publish provenance cryptographically ties this package to that repository. That is proof of origin, not an official vendor package.
Agent-agnostic, LLM-agnostic memory backend for MCP-compatible tools
The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.
1. Threat score — 100 − 0 = 100. What the published surface and source actually contain:
The deterministic scan raised no scored threat in the surface it inspected — the threat score stayed at 100. Capability observations and advisory notes are recorded but never lower it.
2. Client adoption risk — 100 − 6 = 94. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:
| Points | Adoption-risk factor |
|---|---|
| −6 | capability blast radius (high) — client exposure if the model is manipulated |
Capability observations and info notes are shown under Findings but never scored.
Open any row's finding below for the file, line and evidence behind a deduction.
Findings 3
high Shell/command execution in server code (server.mjs)MTC-SRC-002
In the server's implementation (`server.mjs:4`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: ecFileSync } from 'node:child_process'; import { AsyncLocalStorage } from 'node:async_hooks'; import { existsSync, mkdir
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server server.mjs
low Shell/command execution in packaging/dev tooling (scripts/dream_runner.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/dream_runner.py:324`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: tend(args) result = subprocess.run( command, cwd=str(cwd) if cwd else None, capture_output=T
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server scripts/dream_runner.py
low Shell/command execution in packaging/dev tooling (scripts/tests/test_dream_runner_modes.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/tests/test_dream_runner_modes.py:35`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: v) result = subprocess.run( ["python3", str(script)], cwd=str(ROOT),
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server scripts/tests/test_dream_runner_modes.py
What this scan could not see
- No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command "npx -y <package>".
Versions 1
Scan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v0.3.0 latest |
A 94/100 | 3 | 1.13.0 | 2026-09-07 |
Embed this score
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
Verify this score yourself
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan @marsnme/mcp-gateway --onlineOther implementations of Marsnme Gateway 15
Independent packages implementing the same tool, scanned with the same engine. Compare all 16 side by side →
MCP Gateway for exposing VAT agents through Model Context Protocol
NestJS MCP Gateway - Proxy, route, and aggregate multiple MCP servers
The Kirha MCP Gateway provides unified access to Kirha Tool Planning through the Model Context Protocol (MCP), enabling advanced tool composition and execution for LLM interfaces.
MCP Gateway for Blaxel
Policy enforcement, tamper-evident audit trail, and kill switch for any MCP server — a drop-in governance proxy
Personal MCP Gateway - aggregate multiple MCP servers into one stdio interface
More in Lifestyle & Local
MCP server for Australian address search and validation via Addressr
Admissions data & match scores for law, medical, dental, MBA, pharmacy, vet, optometry schools
Live AI data for agents: model releases, regulations (EU AI Act), GenAI glossary, daily news.
AirTreks MCP Server — complex flight routing intelligence for AI agents. Plan multi-city trips, validate alliance routings, get carrier recommendations, and create trip ideas.
Physician-reviewed medical opinions and prescriptions for AI agents.
Thin MCP server + CLI that proxy the atrium /api/v1 observability surface using an oc_live_ Bearer key. Talks HTTP only — no Convex imports.