Gemini CLI
This MCP server provides integration with Google's Gemini CLI, enabling AI assistants to leverage Gemini's massive token window for analyzing large files and codebases using the @ syntax for file references. Built using TypeScript with the Model Context Protocol SDK, it offers tools for general Gemini queries, sandbox-mode code execution for safe testing, and structured response handling with behavioral flags that control AI interaction patterns including context suppression and output formatting. The implementation features proper argument handling for the Gemini CLI, progress monitoring for long-running operations, slash command support for direct user interaction, and specialized sandbox capabilities for executing potentially risky code in an isolated environment, making it valuable for large-scale code analysis, safe script testing, and building AI assistants that need access to Gemini's advanced reasoning capabilities without manual CLI usage.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- monitoring
- Source
- PulseMCP
- Repository
- github.com/jamubc/gemini-mcp-tool
- Author type
- human
- Updated
- 2026-04-30
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.