Gemini CLI
MCP server that bridges Gemini CLI with Claude Code by using code2prompt to extract codebase content and feeding it to Google's Gemini models for architectural analysis. The implementation provides two core tools: comprehensive codebase review that analyzes entire projects with automatic exclusion of build artifacts and dependencies, and targeted analysis that focuses on specific files or folders for component-level insights. Built with TypeScript and designed to leverage Gemini's large context window, it serves developers who want AI-powered code reviews, architectural assessments, and refactoring recommendations by combining the structured output of code2prompt with Gemini's analytical capabilities for both full-project overviews and focused component analysis.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- ai-ml
- Source
- PulseMCP
- Repository
- github.com/artegy/gemini-cli-mcp
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Gemini CLI from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.