# Gemini Code Context

> Use this tool when you need to accelerate and optimize Claude Code queries with a persistent context cache, solving problems of slow repeat queries and high costs. It takes in API keys, model configurations, and budget caps as inputs, and outputs faster and cheaper query results. Ideal for use cases where speed and cost efficiency are crucial, such as large-scale development and production environments.

Canonical page: https://skillsregistry.net/skills/gemini-code-context-mcp  
JSON: https://api.skillsregistry.net/v1/skills/gemini-code-context-mcp

## Description

Gemini Code Context provides a persistent 2M-token context cache for Claude Code using Google Gemini, enabling repeat queries to run up to 8× faster and 4× cheaper. It supports Gemini Pro, Flash, and Lite models with configurable TTL and daily budget caps. The server integrates with both Google AI Studio API keys and Vertex AI backends.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** api-integration
- **Updated:** 2026-04-25

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/gemini-code-context-mcp)
- **Repository:** <https://github.com/qmediat/gemini-code-context-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "gemini-code-context-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/gemini-code-context-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/gemini-code-context-mcp/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt