Compare two

Compare two AI tools side by side

Put any two skills or MCP servers next to each other: risk grade, what each can access, how popular it is, and how to install it.

Try: Chrome DevTools MCP vs Context7 · n8n MCP vs Figma Context MCP · Claude-Mem vs MCPorter

Whatcodelocal@browserstack/mcp-server
Risk gradeCC · Moderate risk signals Based on public adoption and transparency signals as of Oct 23, 2026. Our opinion, not a code audit or security guarantee.BB · Some risk signals Based on public adoption and transparency signals as of Oct 24, 2026. Our opinion, not a code audit or security guarantee.
TypeApp connectorApp connector
Est. context load~500 tokens / turn (~3 tool schemas, 0.25% of 200k context)~650 tokens / turn (~4 tool schemas, 0.33% of 200k context)
GitHub stars89155
Weekly npm downloads32629.7k
Local filesNo local folder access notedNo local folder access noted
Command executionRuns shell or system commandsNo shell command runner noted
Network reachConnects to outside service APIFetches arbitrary web URLs
CredentialsNo API token requiredRequires API key or token
Package sourcenpm (codelocal)npm (@browserstack/mcp-server)
Install commandnpx -y codelocalnpx -y @browserstack/mcp-server
Bottom linecodelocal is distributed via npm (codelocal); review its source code, dependencies, and requested permissions before use.This connector is safe if you trust BrowserStack and keep your API credentials private, but it can drain your testing budget if misused and may expose sensitive data from test screenshots.

Based on public adoption and transparency signals as of Oct 28, 2026. Our opinion, not a code audit or security guarantee.

Go deeper

Want to inspect exact published files, install hooks and network hosts?

Run a pre-install check on any package, MCP config or SKILL.md, or open a full report with PDF export.