gemini-embedding-2-mcp
JSON →A powerful Model Context Protocol (MCP) server using gemini embedding 3 that transforms any local directory into an ultrafast, visually-aware spatial search engine for AI agents.
Install
uvx --from Tools · 2
- preview_directory Shows what will be indexed, grouped by modality and skip reason, before the scan runs.
- get_result_context Returns neighboring chunks or pages so agents can inspect exact source material after search.
Environment variables
GEMINI_API_KEY
★ 4 GitHub stars