Skills/npm/ayphic-mcp-server

ayphic-mcp-server@3.0.1

VERIFIED

Publisher claims: "Model Context Protocol (MCP) Server for Ayphic AI Video Editor" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher vshukla7 · joined 10 days agoInstalls 2,547Last detonated 1 h ago
$claude mcp add ayphic-mcp-server -- npx -y ayphic-mcp-server
WatchReport an issue

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-11-05 and scored it 90/100 (Verified). It did what it claims and nothing else we could detect: no undeclared network egress, no credential reads, no persistent instruction writes. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 1 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.7sprocessexec /usr/bin/date
0.7sprocessexec /usr/bin/timeout
0.7sclaimed53 tools: getProjectCode, getProjectOutline, applyCodeOps, insertCodeNode, updateCodeNode, deleteCodeNode, replaceProjectCode, validateProjectCode, insertLinesInCode, replaceLinesInCode, deleteLinesInCode, searchCode, patchCode, createFile, readFile, updateFile, deleteFile, listFiles, searchFile, insertLinesInFile, replaceLinesInFile, deleteLinesInFile, patchFile, getTimeline, browseMedia
0.7sprocessscript backend runs setup only

Static findings

No findings across 2,062 lines in 4 files.

Cost to the agent

Instructions loaded
≈54 tok
1 file · 4 in bundle
Tool list per prompt
≈8,302 tok
53 tools · 157 per tool
Handshake
636 ms
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 162

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

Not checked against OSV yet; the weekly check has not reached this version.