Safari Server Claude MCP Server
mcp-safari-server-claude
npm
v1.0.0
Published by iclaudiumihaila — no publish provenance, so origin is unverified, but the source is public: the repository link below is self-declared yet readable, so you can inspect the code before adopting it.
MCP server for Safari browser control and debugging on macOS
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 − 7 = 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 |
| −1 | publisher verification (public source) — no provenance, but the source is public and inspectable |
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 Tool "execute_script" exposes command/code executionMTC-CAP-001
Tool "execute_script" appears to run shell commands or evaluate code (parameter "script"). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.
Fix: Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.
Location: tool execute_script
high Shell/command execution in server code (dist/index.js)MTC-SRC-002
In the server's implementation (`dist/index.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 { exec } from 'child_process'; import { promisify } from 'util'; const execAsync = promisify(exec); // Tool sch
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/index.js
high Shell/command execution in server code (src/index.ts)MTC-SRC-002
In the server's implementation (`src/index.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: exec, execSync } from 'child_process'; import { promisify } from 'util'; const execAsync = promisify(exec); // Tool s
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/index.ts
medium Untrusted input can drive an external actionMTC-FLOW-005
Untrusted-input tools ([get_page_info]) co-exist with external-action tools ([execute_script]). A prompt injection could cause unwanted external actions, though no direct sensitive-data leak path was found.
Evidence: untrusted [get_page_info] → sinks [execute_script]
Fix: Require confirmation for state-changing/egress actions triggered after processing untrusted content.
Location: flow get_page_info → execute_script
medium Unconstrained command parameter "script" on "execute_script"MTC-CAP-006
Tool "execute_script" takes a command-shaped parameter "script" with no enum/pattern constraint. Free-form, model- or attacker-controlled arguments reaching a shell is the command-injection precondition.
Fix: Constrain the parameter (enum/pattern), or build the command from a fixed template with escaped args.
Location: tool execute_script · inputSchema.properties.script
low Mutating tool "execute_script" declares no destructiveHintMTC-CAP-005
Tool "execute_script" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.
Fix: Declare accurate annotations, and gate destructive tools on user confirmation regardless.
Location: tool execute_script
Tools 16
Each tool and what it can reach — statically extracted from the published source.
execute_scriptruns code / shellget_page_infoingests untrusted inputclick_elementno sensitive capabilityget_console_logsno sensitive capabilityget_element_textno sensitive capabilitygo_backno sensitive capabilitygo_forwardno sensitive capabilitynavigateno sensitive capabilityrefresh_pageno sensitive capabilityscroll_tono sensitive capability
Show 6 more tools ↓
select_optionno sensitive capabilitystart_error_monitoringno sensitive capabilitystop_error_monitoringno sensitive capabilitytake_screenshotno sensitive capabilitytype_textno sensitive capabilitywait_for_elementno sensitive capability
Toxic flows 1
Cross-tool combinations that form a data-exfiltration primitive (untrusted input → sensitive source → external sink).
What this scan could not see
- Tools were statically extracted from the published source (16 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Versions 1
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 |
|---|---|---|---|---|
v1.0.0 latest |
A 93/100 | 6 | 1.13.0 | 2026-09-07 |
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 mcp-safari-server-claude --onlineMore in Browser Automation
Model Context Protocol (MCP) server that integrates AgentQL data extraction capabilities.
Screenshot any URL or HTML as PNG/JPEG/WebP from your AI agent. Full-page, clean, no install.
MCP server for aria51 accessibility scanner
Bridge any browser web app to Claude Code via MCP
Browserbase’s official MCP server: cloud headless browsers for agents, with sessions and screenshots.
MCP server for AI web browser automation using Browserbase and Stagehand