# Google Gemini

> Use this tool when you need to integrate Google Gemini AI capabilities into your applications, solving complex problems that require advanced reasoning and thinking capabilities. It provides a standardized interface for accessing Gemini's features, accepting input parameters such as effort levels and model selection, and outputting streaming or non-streaming responses. Ideal for use cases where programmatic access to AI-powered reasoning is necessary, such as building intelligent assistants or automating decision-making processes.

Canonical page: https://skillsregistry.net/skills/lucky-dersan-gemini  
JSON: https://api.skillsregistry.net/v1/skills/lucky-dersan-gemini

## Description

This MCP server provides Google Gemini AI integration through Google's OpenAI-compatible API endpoint, offering four distinct interaction modes: streaming and non-streaming responses, each with optional reasoning/thinking capabilities. Built using FastMCP and the OpenAI Python client with proxy support for network configurations, it enables AI assistants to leverage Gemini's reasoning capabilities with configurable effort levels (low/medium/high) and includes utility tools for connection testing and configuration management. The implementation supports Docker deployment with environment-based configuration for API keys, model selection, base URLs, and proxy settings, making it valuable for users who need programmatic access to Gemini's advanced reasoning features through a standardized MCP interface without direct API integration complexity.

## Trust

- **Trust score (0–1):** 0.91
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** cloud-infra
- **Updated:** 2026-09-19

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/lucky-dersan-gemini)
- **Repository:** <https://github.com/lucky-dersan/gemini-mcp-server>

## 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": "lucky-dersan-gemini"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/lucky-dersan-gemini` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/lucky-dersan-gemini/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