Claude To Gemini Cli — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Claude To Gemini Cli (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
An MCP (Model Context Protocol) server that lets Claude query Google's Gemini CLI as a sub-agent. Get second opinions, verify information, and cross-reference answers between AI models.
| Tool | Description |
|---|---|
ask_gemini | Ask Gemini any question directly |
verify_with_gemini | Fact-check a claim using Gemini |
gemini_second_opinion | Get Gemini's review of a proposed solution or code |
gemini_compare | Compare Claude's answer with Gemini's perspective |
npm install
npm run buildAdd to your ~/.claude/settings.json:
{
"mcpServers": {
"gemini": {
"command": "node",
"args": ["/absolute/path/to/claude-to-gemini-cli-mcp/dist/index.js"]
}
}
}Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
{
"mcpServers": {
"gemini": {
"command": "node",
"args": ["/absolute/path/to/claude-to-gemini-cli-mcp/dist/index.js"]
}
}
}| Variable | Default | Description |
|---|---|---|
GEMINI_CLI_PATH | gemini | Path to the Gemini CLI binary |
GEMINI_TIMEOUT | 120000 | Default timeout in ms |
GEMINI_MODEL | (CLI default) | Default Gemini model to use |
Once configured, Claude can use these tools automatically:
MIT
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.