MCP Server MCP

io.github.qmediat/gemini-code-context-mcp

By github 👁 1 views ▲ 0 votes

Gemini 2M context cache for Claude Code — persistent; repeat queries ~8x faster, ~4x cheaper.

Homepage Verified source GitHub

Install

npx -y @qmediat.io/[email protected]

Configuration Example

{
  "remotes": [],
  "packages": [
    {
      "registryType": "npm",
      "identifier": "@qmediat.io/gemini-code-context-mcp",
      "version": "1.16.3",
      "transport": {
        "type": "stdio"
      },
      "environmentVariables": [
        {
          "description": "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.",
          "format": "string",
          "name": "GEMINI_CREDENTIALS_PROFILE"
        },
        {
          "description": "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.",
          "format": "string",
          "isSecret": true,
          "name": "GEMINI_API_KEY"
        },
        {
          "description": "Set to `true` to use Vertex AI backend via Application Default Credentials. Requires GOOGLE_CLOUD_PROJECT.",
          "format": "string",
          "name": "GEMINI_USE_VERTEX"
        },
        {
          "description": "GCP project ID when using Vertex AI backend. Only read when GEMINI_USE_VERTEX=true.",
          "format": "string",
          "name": "GOOGLE_CLOUD_PROJECT"
        },
        {
          "description": "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`.",
          "format": "string",
          "name": "GEMINI_DAILY_BUDGET_USD"
        },
        {
          "description": "Model alias (`latest-pro`, `latest-pro-thinking`, `latest-flash`, `latest-lite`, `latest-vision`) or literal model ID. Default: `latest-pro`.",
          "format": "string",
          "name": "GEMINI_CODE_CONTEXT_DEFAULT_MODEL"
        },
        {
          "description": "Context Cache TTL in seconds. Default: 3600 (1 hour). Hot workspaces (<10 min since last use) auto-refresh via background watcher.",
          "format": "string",
          "name": "GEMINI_CODE_CONTEXT_CACHE_TTL_SECONDS"
        },
        {
          "description": "`debug` | `info` | `warn` | `error`. Default: `info`.",
          "format": "string",
          "name": "GEMINI_CODE_CONTEXT_LOG_LEVEL"
        }
      ]
    }
  ]
}

mcp model-context-protocol npm