gemini-code-context-mcp
Gemini 2M context cache for Claude Code — persistent; repeat queries ~8x faster, ~4x cheaper.
Package Details
@qmediat.io/gemini-code-context-mcp
Environment Variables
Profile name in ~/.config/qmediat/credentials (chmod 0600). Created by `npx @qmediat.io/gemini-code-context-mcp init`. Recommended; keeps your API key out of ~/.claude.json.
Fallback Tier 3 auth. Your Gemini API key. Emits a warning at startup recommending you move it to the credentials profile via the init command.
Set to `true` to use Vertex AI backend via Application Default Credentials. Requires GOOGLE_CLOUD_PROJECT.
GCP project ID when using Vertex AI backend. Only read when GEMINI_USE_VERTEX=true.
Hard daily USD cap enforced locally. Server refuses calls after the cap until UTC midnight. Unlimited if unset. Honoured by `ask`, `code`, and per-iteration by `ask_agentic`.
Model alias (`latest-pro`, `latest-pro-thinking`, `latest-flash`, `latest-lite`, `latest-vision`) or literal model ID. Default: `latest-pro`.
Context Cache TTL in seconds. Default: 3600 (1 hour). Hot workspaces (<10 min since last use) auto-refresh via background watcher.
`debug` | `info` | `warn` | `error`. Default: `info`.