Gemini Collaboration
This MCP server enables Claude Code to collaborate directly with Google's Gemini AI through three specialized tools: general question answering, code review with configurable focus areas (security, performance, etc.), and brainstorming sessions with contextual prompts. Built by Rai Ansar using the google-generativeai Python library and Gemini 2.0 Flash model, it creates an AI pair programming experience where Claude can leverage Gemini's responses directly within its context, with temperature control for balancing factual accuracy versus creativity. The implementation is valuable for developers seeking multi-AI collaboration workflows where different models can complement each other's strengths in code development, review, and problem-solving tasks.
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/raiansar/claude_code-gemini-mcp
- Author type
- human
- Updated
- 2026-04-25
Use via MCP
Resolve Gemini Collaboration 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.