Gemini
A TypeScript-based MCP server that provides comprehensive access to Google's Gemini AI models, including the latest 2.5 series with thinking capabilities, vision models for image analysis, and embedding generation. Built by Gurveer, it features advanced functionality like JSON mode with schema validation, Google Search grounding for real-time information, conversation memory, safety settings, and support for system instructions across all major Gemini models. The implementation includes robust error handling, rate limiting, token counting, and extensive validation, making it ideal for developers who need full-featured Gemini integration with Claude Desktop and other MCP-compatible clients for tasks ranging from complex reasoning and coding assistance to image analysis and structured data generation.
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
- media
- Source
- PulseMCP
- Repository
- github.com/gurveeer/mcp-server-gemini-pro
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Gemini 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.