@mcp-use/cli
npm
v4.1.11
Source verified
Published by mcp-use — publish provenance cryptographically ties this package to that repository. That is proof of origin, not an official vendor package.
The mcp-use CLI is a tool for building and deploying MCP servers with support for ChatGPT Apps, Code Mode, OAuth, Notifications, Sampling, Observability and more.
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/commands/dev.js:68`): 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: ode.process(x,d));let B=new Function(`${o.default.self}`,`${o.default.scope}`,x)(this,this.scope.get());if(this.scope.va
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/commands/dev.js
In the server's implementation (`dist/chunk-K5AVW4TV.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: import{spawn as ue}from"child_process";import{readFileSync as le}from"fs";import{chmod as de,mkdir as me}from"fs/promise
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/chunk-K5AVW4TV.js
In the server's implementation (`dist/chunk-S3WHXP7I.js:1`): 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: port{execFile as t}from"child_process";function d(n,e=process.platform){let r;try{r=new URL(n)}catch{return}if(r.protoco
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/chunk-S3WHXP7I.js
In the server's implementation (`dist/commands/deploy.js:1`): 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{execFile as Se}from"child_process";import{createReadStream as Ce}from"fs";import{appendFile as re,lstat as Ie,opendi
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/commands/deploy.js
In the server's implementation (`dist/commands/screenshot.js:1`): 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: ;import{spawn as $}from"child_process";import{access as j,mkdtemp as F,rm as A,writeFile as G}from"fs/promises";import{c
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/commands/screenshot.js
In the server's implementation (`dist/commands/typecheck.js:1`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: ;import{spawn as d}from"child_process";import{createRequire as u}from"module";import{dirname as l,join as m,resolve as y
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/commands/typecheck.js
In the server's implementation (`dist/commands/dev.js:71`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: sync()=>{let ue=await w.import(g),$e=ab(ue),ye=$e.__skillsConfig(),ze=rl(ye,e.cwd,_);$e.__primeSkills(ol(ye,e.cwd,_,{onI
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/commands/dev.js
In a packaging/dev/install script (shipped, but not the server runtime) (`dist/commands/build.js:1`): 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: P_URL=W);let r=(await s.import(i)).default;if(r===null||typeof r!="object")throw new Error("The server entry must defaul
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/commands/build.js
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 |
|---|---|---|---|---|
v4.1.11 latest |
A 94/100 | 8 | 1.13.0 | 2026-09-05 |
v4.1.10 |
A 94/100 | 8 | 1.13.0 | 2026-09-04 |
v4.1.8 |
A 94/100 | 8 | 1.13.0 | 2026-09-01 |
v4.1.7 |
A 94/100 | 8 | 1.13.0 | 2026-08-27 |
v4.1.5 |
A 94/100 | 8 | 1.13.0 | 2026-08-25 |
v4.1.4 |
A 94/100 | 8 | 1.12.1 | 2026-08-14 |
v4.1.2 |
A 94/100 | 8 | 1.12.1 | 2026-08-13 |
v4.1.1 |
A 94/100 | 8 | 1.12.1 | 2026-08-12 |
v4.1.0 |
A 94/100 | 8 | 1.12.1 | 2026-08-10 |
v4.0.1 |
A 94/100 | 7 | 1.12.1 | 2026-08-06 |
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-use/cli --online
Independent packages implementing the same tool, scanned with the same engine. Compare all 2 side by side →
MCP server for 2s.io — 575+ pay-per-call tools for AI agents — ground-truth data, AI gateway, and agent infra (storage, locks, queues, watchers). x402 USDC on Base/Solana, no API keys, upto usage billing, free trials.
ArXiv preprints + Google Scholar papers, with citation counts in one query.
Add MCP servers to your favorite coding agents with a single command.
Help agents automatically write and test stories for your UI components
Model Context Protocol server for AI-Archive platform - enables AI agents to discover, submit, and review research papers
MCP server for Semantic Scholar research workflows with stdio and Streamable HTTP transports.