Inspector (modelcontextprotocol) MCP Server
@modelcontextprotocol/inspector
npm
v2.5.0
Official
Published by Model Context Protocol — an official vendor package. A brand name in a package name proves nothing; this one is verified by npm scope ownership or publish provenance.
Model Context Protocol inspector
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 − 1.2 = 99. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −1.2 | Package runs install-time scripts MTC-SUP-010 | supply-chain |
2. Client adoption risk — 99 − 6 = 93. 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 6
high Dynamic code execution in server code (clients/web/dist/assets/index-ZYqA4f7P.js)MTC-SRC-001
In the server's implementation (`clients/web/dist/assets/index-ZYqA4f7P.js:130`): 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(g,e));let i=Function(`${r.default.self}`,`${r.default.scope}`,g)(this,this.scope.get());if(this.scope.value(
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 clients/web/dist/assets/index-ZYqA4f7P.js
high Shell/command execution in server code (clients/web/build/index.js)MTC-SRC-002
In the server's implementation (`clients/web/build/index.js:6235`): 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 { spawnSync } from "child_process"; function runViteBuild(webRoot, log) { const result = spawnSync("npm", ["run",
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 clients/web/build/index.js
medium Dynamic module load from a non-literal (clients/web/dist/assets/index-ZYqA4f7P.js)MTC-SRC-005
In the server's implementation (`clients/web/dist/assets/index-ZYqA4f7P.js:376`): 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: s(e)});else{try{r=this.$require(o)}catch{}s(r||t.$loaded[o])}},t.$require=function(e){if(typeof n.require==`function`)re
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 clients/web/dist/assets/index-ZYqA4f7P.js
medium Dynamic module load from a non-literal (clients/web/dist/assets/worker-json-8CDXFfik.js)MTC-SRC-005
In the server's implementation (`clients/web/dist/assets/worker-json-8CDXFfik.js:213`): 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: var clazz = this.require(msg.module)[msg.classname]; main = window.main = new clazz(sender); } }; })(
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 clients/web/dist/assets/worker-json-8CDXFfik.js
low Shell/command execution in packaging/dev tooling (scripts/install-clients.mjs)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/install-clients.mjs:24`): 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: spawnSync } from "node:child_process"; import { existsSync } from "node:fs"; import { dirname, join, resolve, sep } fro
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/install-clients.mjs
low Package runs install-time scripts (postinstall)MTC-SUP-010
"@modelcontextprotocol/inspector" executes postinstall script(s) at install time. An install hook runs at install time; most are routine build/setup, but review what it does before trusting it.
Evidence: node scripts/install-clients.mjs
Fix: Review the scripts; install with --ignore-scripts where possible and vet what they do.
Location: package @modelcontextprotocol/inspector
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 8
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 |
|---|---|---|---|---|
v2.5.0 latest |
A 93/100 | 6 | 1.13.0 | 2026-09-07 |
v2.4.0 |
A 93/100 | 6 | 1.13.0 | 2026-09-01 |
v2.3.0 |
A 93/100 | 4 | 1.13.0 | 2026-08-25 |
v2.2.0 |
A 93/100 | 4 | 1.12.1 | 2026-08-19 |
v2.1.0 |
A 93/100 | 4 | 1.12.1 | 2026-08-12 |
Show 3 more versions ↓
v2.0.0 |
A 93/100 | 4 | 1.12.1 | 2026-08-05 |
v1.0.1 |
A 94/100 | 2 | 1.12.1 | 2026-07-28 |
v1.0.0 |
A 94/100 | 2 | 1.12.1 | 2026-07-27 |
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 @modelcontextprotocol/inspector --onlineOther implementations of Inspector 4
Independent packages implementing the same tool, scanned with the same engine. Compare all 5 side by side →
An MCP client for Node.js
MCP server for domain reputation, website safety, and URL trust analysis powered by GridinSoft Inspector
A minimal Python package for MCP inspection
MCP server for debugging live Node.js processes via Chrome DevTools Protocol
More in Other
A Model Context Protocol server implementation for AdGuard Home that enables AI agents to query and manage DNS records, filtering rules and more
Identity oracle and trust layer for autonomous AI agents. Bidirectional KYA and trust scoring.
MCP server with Airtable integration
A free one-minute reset for people, delivered by AI, with no account or personal data.
Access SEC filings efficiently, save time and tokens, and get cited answers.
A smart [MCP](https://modelcontextprotocol.io) server for [AniList](https://anilist.co) that gets your anime/manga taste - not just API calls.