Azure MCP Server
@azure/mcp
npm
v3.0.0-beta.41
Official
Published by Microsoft Azure — an official vendor package. A brand name in a package name proves nothing; this one is verified by npm scope ownership or publish provenance.
Azure MCP Server - Model Context Protocol implementation for Azure
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 − 7.5 = 93. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −6.3 | Untrusted input concatenated into a command sink MTC-SRC-009 | injection |
| −1.2 | Package runs install-time scripts MTC-SUP-010 | supply-chain |
2. Client adoption risk — 93 − 6 = 87. 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 4
high Shell/command execution in server code (index.js)MTC-SRC-002
In the server's implementation (`index.js:43`): 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: { execSync } = require('child_process') console.error(`Installing missing platform package: ${platformPackageName}`
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 index.js
medium Untrusted input concatenated into a command sink (index.js)MTC-SRC-009
In the server's implementation (`index.js:49`): 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: package try { execSync(`npm install ${platformPackageName}@${packageVersion}`, { stdio: ['inherit', 'i
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 index.js
medium Dynamic module load from a non-literal (index.js)MTC-SRC-005
In the server's implementation (`index.js:37`): 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: }`) platformPackage = require(platformPackageName) } catch (err) { debugLog(`Failed to require ${platformPackageName
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 index.js
low Package runs install-time scripts (postinstall)MTC-SUP-010
"@azure/mcp" 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/post-install-script.js
Fix: Review the scripts; install with --ignore-scripts where possible and vet what they do.
Location: package @azure/mcp
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 10
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 |
|---|---|---|---|---|
v3.0.0-beta.41 latest |
B 87/100 | 4 | 1.13.0 | 2026-09-04 |
v3.0.0-beta.39 |
B 87/100 | 4 | 1.13.0 | 2026-08-28 |
v3.0.0-beta.38 |
B 87/100 | 4 | 1.13.0 | 2026-08-27 |
v3.0.0-beta.37 |
B 87/100 | 4 | 1.13.0 | 2026-08-25 |
v3.0.0-beta.36 |
B 87/100 | 4 | 1.12.1 | 2026-08-19 |
Show 5 more versions ↓
v3.0.0-beta.35 |
B 87/100 | 4 | 1.12.1 | 2026-08-14 |
v3.0.0-beta.34 |
B 87/100 | 4 | 1.12.1 | 2026-08-12 |
v3.0.0-beta.33 |
B 87/100 | 4 | 1.12.1 | 2026-08-09 |
v3.0.0-beta.32 |
B 87/100 | 4 | 1.12.1 | 2026-08-06 |
v3.0.0-beta.31 |
B 87/100 | 4 | 1.12.1 | 2026-08-01 |
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 @azure/mcp --onlineOther implementations of Azure 3
Independent packages implementing the same tool, scanned with the same engine. Compare all 4 side by side →
[](https://smithery.ai/server/@Streen9/azure-mcp)
Azure DevOps server with robust error handling, .mcp.json support, and concurrent attachment handling.
Security scan results for the Azure (npm) MCP server.
More in Data Science & ML
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.