Skills/PyPI/visualgen-mcp

visualgen-mcp@0.1.1

VERIFIED· not started

Publisher claims: "MCP server for generating images and short videos via Google's Gemini API (Imagen 4 and Veo 3.1), for use inside Claude Code." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher 1raghavm · publishing for 211 daysInstalls 79Last detonated 11 min ago
$claude mcp add visualgen-mcp -- uvx visualgen-mcp
WatchReport an issue

Coverage

Not started: dependency install failed; the server itself was not observed.
Tested
the dependency install step · every file read, file written and host contacted by what ran
Not tested
server startup · the tool list · tool behavior

What this means for the label: Verified here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
GEMINI_API_KEYConfiguration, not credentials: OUTPUT_DIR
Where it talks to
no vendor host named in the codeAlso google.dev, google.com — not the publisher's domain; check what for before connecting.
What we saw when it ran
no credential files read · no network
What we could not test
server startup · the tool list · tool behavior

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names google.dev, google.com as well as its own vendor. The guard injects GEMINI_API_KEY only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- uvx visualgen-mcp

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-20 and scored it 87/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.2sprocessdependency install exit 1 ·
0.2sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.2sprocessscript backend runs setup only
0.2sprocessno install scripts to re-run

Static findings

MEDIUM
File permission modification commandsrc/visualgen_mcp/wizard.py:244 · File permission modification command — agent changes file ownership/permissionsprint(f"\nSaved to {path} (chmod 600)\n")Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
CRITICAL
Fake instruction boundary tag.claude/skills/visualgen/SKILL.md:31 · Fake instruction boundary tag> About to generate an 8s Veo standard clip at 1080p. Estimated cost: **$3.20**. Prompt: "<prompt>". Confirm to proceed? (yes / change / cancel)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Access to sensitive file pathssrc/visualgen_mcp/config.py:56 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"(e.g. in `.env` or your `.mcp.json` env block)."Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File permission modification commandsrc/visualgen_mcp/profile.py:57 · File permission modification command — agent changes file ownership/permissions"""Write the profile to disk with dir chmod 0700 and file chmod 0600."""Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
LOW
Fake instruction boundary tagdocs/plans/2026-04-22-visualgen-skill.md:230 · Fake instruction boundary tag · informational: not an instruction file> About to generate an 8s Veo standard clip at 1080p. Estimated cost: **$3.20**. Prompt: "<prompt>". Confirm to proceed? (yes / change / cancel)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Fake instruction boundary tagdocs/plans/2026-04-22-visualgen-skill-design.md:160 · Fake instruction boundary tag · informational: not an instruction file> About to generate an 8s Veo standard clip at 1080p. Estimated cost: **$3.20**. Prompt: "<prompt>". Confirm to proceed? (yes / change / cancel)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈1,682 tok
1 file · 80 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

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.