@alramalho/mcp-guard
npm
v0.2.2
Published by @alramalho — no publish provenance and no public repository, so the publisher could not be verified and the source cannot be independently located.
Simple HTTP proxy that gates MCP servers with block rules
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 − 9.5 = 91. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −9.5 | Untrusted input concatenated into a command sink ×2 MTC-SRC-009 | injection |
2. Client adoption risk — 91 − 8 = 83. 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 |
| −2 | publisher verification (unlinked) — no provenance/repo link, but the shipped source was fully read |
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.
In the server's implementation (`dist/auth.js:6`): 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: ort { exec } from "node:child_process"; const CALLBACK_PORT = 19284; const CALLBACK_PATH = "/oauth/callback"; function s
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 dist/auth.js
In the server's implementation (`dist/index.js:5`): 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: rt { spawn } from "node:child_process"; import { startServer } from "./server.js"; const dim = (s) => `\x1b[2m${s}\x1b[0
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 dist/index.js
In the server's implementation (`src/auth.ts:6`): 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: ort { exec } from "node:child_process"; import type { OAuthClientProvider } from "@modelcontextprotocol/sdk/client/auth.
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 src/auth.ts
In the server's implementation (`src/index.ts:6`): 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: rt { spawn } from "node:child_process"; import { GuardConfig } from "./types.js"; import { startServer } from "./server.
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 src/index.ts
In the server's implementation (`dist/auth.js:62`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: " : "xdg-open"; exec(`${openCmd} "${authorizationUrl.toString()}"`); process.stderr.write(`\x1b[33mauth\
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/auth.js
In the server's implementation (`src/auth.ts:73`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: tart" : "xdg-open"; exec(`${openCmd} "${authorizationUrl.toString()}"`); process.stderr.write(`\x1b[33mauth\x1b[
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 src/auth.ts
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 |
|---|---|---|---|---|
v0.2.2 latest |
B 83/100 | 6 | 1.13.0 | 2026-09-07 |
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.
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 @alramalho/mcp-guard --online
Independent packages implementing the same tool, scanned with the same engine. Compare all 7 side by side →
MCP runtime security proxy — intercepts and enforces security policies on MCP tool calls
Model Context Protocol (MCP) server that scans agent tool calls through Interven before they execute. Drop-in for Claude Desktop, Cursor, Cline, OpenAI Agents SDK, and any MCP-aware client.
AIVory Guard - MCP server for AI-powered compliance scanning. Integrates with Claude Code, Cursor, and other AI coding assistants.
Security MCP server with 20 tools — 12 require local hardware. Wi-Fi/Bluetooth/USB enumeration, ARP LAN discovery, kernel FS events, process introspection, secret scanning, port scanning, TLS inspection, CVE checking.
Secure sandbox with limited permissions to host your MCP servers
MCP server for safe shell, file, database, git, and HTTP access. Every operation validated against per-agent permission rules. Powered by AgentsID.
The Stripe Agent Toolkit enables popular agent frameworks including LangChain and Vercel's AI SDK to integrate with Stripe APIs through function calling.
MCP (Model Context Protocol) server for AgentGate. Enables Claude and other MCP-compatible AI assistants to request approvals.
Scan any website for AI agent readiness, payment protocols, and discovery endpoints
MCP server for aigently security guardrails — reads static catalog-data JSON, zero API dependency
Governed threat modeling, code threat verification, traceability & compliance, as MCP tools.
Governed threat modeling, code threat verification, traceability & compliance, as MCP tools.