Claude Desktop (npm) MCP Server

mcp-claude-desktop npm

Published by an unidentified publisher — no publish provenance and no vendor-owned scope, so the publisher could not be verified. The repository link below is self-declared.

View on npm ↗ Raw report (JSON) ↗

Trust grade

100/100

Last scanned 2026-07-22

Trust

A · 100/100

How safe the published surface and source look. Deterministic; every point is auditable.

Capability

Minimal

Blast radius if it went rogue — what the server’s tools could reach. Independent of trust.

Coverage

Metadata

How much the scan could actually inspect. Shallow coverage is stated, never hidden.

A Why this grade

Started at 100 and nothing was deducted: the deterministic scan raised no scored threat in the published surface it inspected (coverage: Metadata — see below for what that scan could and could not see). Capability observations and advisory notes are recorded but never lower the score.

Findings 0

✓ No findings. The scan raised nothing on this surface — see Coverage for how deep it could look.

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>".
The implementation source was not read — this reflects registry metadata only. Add --online to fetch and analyze the published package source.

Versions

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
`—` latest	A 100/100	0	1.5.0	2026-07-22

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.

Markdown (GitHub README)

[![MCP Trust Score](https://mcptrustchecker.com/registry/mcp-claude-desktop/badge.svg)](https://mcptrustchecker.com/registry/mcp-claude-desktop)

HTML

<a href="https://mcptrustchecker.com/registry/mcp-claude-desktop"><img src="https://mcptrustchecker.com/registry/mcp-claude-desktop/badge.svg" alt="MCP Trust Score" height="20"></a>

Prefer shields.io styling? Point it at https://mcptrustchecker.com/registry/mcp-claude-desktop/badge.json via https://img.shields.io/endpoint?url=…

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 mcp-claude-desktop --online

Use the free API → How scoring works

Other implementations of Claude Desktop 1

Independent packages implementing the same tool, scanned with the same engine. Compare all 2 side by side →

Claude Desktop (npm) npm

claude-desktop-mcp

Security scan results for the Claude Desktop (npm) MCP server.

Developer Tools Score 98/100 2 findings Cap. High

More in Productivity & Workflow

0nmcp npm

0nmcp

Security scan results for the 0nmcp MCP server.

Productivity & Workflow Score 100/100 4 findings Cap. High

126 Email npm

126-email-mcp-server

Security scan results for the 126 Email MCP server.

Productivity & Workflow Score 100/100 0 findings Cap. Minimal

5dive npm

@5dive/mcp

Security scan results for the 5dive MCP server.

Productivity & Workflow Score 100/100 1 finding Cap. High

7pace npm

7pace-mcp-server

Security scan results for the 7pace MCP server.

Productivity & Workflow Score 100/100 0 findings Cap. Minimal

Adaptive Cards npm

adaptive-cards-mcp

Security scan results for the Adaptive Cards MCP server.

Productivity & Workflow Score 100/100 4 findings Cap. Moderate

Adb Mcp Tool npm

adb-mcp-tool

Security scan results for the Adb Mcp Tool MCP server.

Productivity & Workflow Score 100/100 2 findings Cap. High