Gemini CLI Orchestrator
A pure metaprompting MCP server that teaches AI agents how to collaborate effectively with Google's Gemini CLI through strategic guidance rather than direct execution. Built by Danny Nguyen, this implementation provides no execution logic whatsoever - instead it returns intelligent prompts and frameworks that guide agents through sequential analysis workflows, ReAct loops, and synthesis strategies optimized for Gemini's 1M+ token context window. The server emphasizes Gemini 2.5 Flash model usage for better availability and cost-effectiveness, while teaching agents advanced techniques like complete subsystem aggregation, iterative reasoning patterns, and multi-perspective analysis synthesis for security reviews, architecture analysis, and debugging workflows.
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
- ai-ml
- Source
- PulseMCP
- Repository
- github.com/dnnyngyen/gemini-cli-orchestrator
- Author type
- human
- Updated
- 2026-04-25
Use via MCP
Resolve Gemini CLI Orchestrator 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.