mcp-proxy
npm
v6.7.14
Source verified
Published by punkpeye — publish provenance cryptographically ties this package to that repository. That is proof of origin, not an official vendor package.
A TypeScript SSE proxy for MCP servers that use stdio transport.
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.
In the server's implementation (`dist/startStdioServer-wlzPR7aW.mjs:9216`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: ame = fn.name; return new Function("fn", "log", "deprecate", "message", "site", "\"use strict\"\nreturn function (" +
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/startStdioServer-wlzPR7aW.mjs
In the server's implementation (`dist/bin/mcp-proxy.mjs:15`): 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 { PassThrough, Transform } from "node:stream"; import { StringDecoder } f
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/bin/mcp-proxy.mjs
In the server's implementation (`src/StdioClientTransport.ts:11`): 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: ype, spawn } from "node:child_process"; import { PassThrough, Stream } from "node:stream"; import { JSONFilterTransform
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/StdioClientTransport.ts
In the server's implementation (`dist/bin/mcp-proxy.mjs:1449`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: } else config = mixin.require(resolvedConfigPath); setConfigObject(config); } catch (ex) { if (ex.name =
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/bin/mcp-proxy.mjs
In a packaging/dev/install script (shipped, but not the server runtime) (`src/StdioClientTransport.test.ts:2`): 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: ildProcess } from "node:child_process"; import { setTimeout as delay } from "node:timers/promises"; import { expect, it
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/StdioClientTransport.test.ts
In a packaging/dev/install script (shipped, but not the server runtime) (`src/startStdioServer.test.ts: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: ess, spawn } from "node:child_process"; import { afterEach, beforeEach, describe, expect, it } from "vitest"; import {
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/startStdioServer.test.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 |
|---|---|---|---|---|
v6.7.14 latest |
A 94/100 | 6 | 1.13.0 | 2026-09-07 |
v6.7.13 |
A 94/100 | 6 | 1.13.0 | 2026-09-05 |
v6.7.11 |
A 94/100 | 6 | 1.13.0 | 2026-08-27 |
v6.7.10 |
A 94/100 | 6 | 1.13.0 | 2026-08-25 |
v6.7.8 |
A 94/100 | 6 | 1.12.1 | 2026-08-18 |
v6.7.4 |
A 94/100 | 6 | 1.12.1 | 2026-08-16 |
v6.7.3 |
A 94/100 | 6 | 1.12.1 | 2026-08-14 |
v6.7.2 |
A 94/100 | 5 | 1.12.1 | 2026-08-13 |
v6.7.1 |
A 94/100 | 5 | 1.12.1 | 2026-08-12 |
v6.7.0 |
A 94/100 | 5 | 1.12.1 | 2026-08-09 |
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 mcp-proxy --online
Independent packages implementing the same tool, scanned with the same engine. Compare all 19 side by side →
A MCP proxy to redirect requests to JetBrains IDEs
Strix MCP Proxy — the distribution wedge for governed agent tool execution. Point your MCP client at the proxy instead of the underlying server; every callTool is intercepted, evaluated against policy, and emits a signed Ed25519 receipt. Designed so Mode
MCP proxy server for SAP ABAP ADT - proxies local requests to cloud-llm-hub with JWT authentication
A tool that proxies MCP servers or merges multiple MCP servers into a single MCP server
A MCP server which proxies requests to a remote MCP server over streamable HTTP or SSE.
An MCP proxy server that aggregates and serves multiple MCP resource servers through a single interface
Adapters for the FrontMCP framework
Transcend MCP Server — Admin tools.
Transcend MCP Server — Assessments tools.
MCP Server for Bling
MCP Server for Blogger API
Official MCP server for Brilliant Directories — manage members, posts, leads, reviews, and more.