Gemini MCP Server
gemini-mcp-сервер
Реализация TypeScript сервера Model Context Protocol (MCP), который интегрируется с моделью Gemini от Google с помощью прямых вызовов API.
Функции
Использует прямые вызовы API Gemini (без устаревшего SDK)
Поддерживает последнюю модель Gemini 2.0 Flash
Реализует протокол MCP для бесшовной интеграции с Claude
Поддерживает контекст разговора для естественного взаимодействия
Related MCP server: Gemini MCP Server
Инструменты МКП
сгенерировать_текст
С сервера: близнецы
Генерация текста с использованием модели Gemini с настраиваемыми параметрами.
Предпосылки
Node.js 18 или выше
API-ключ Google Gemini
Машинопись
Приложение Клода для ПК
Установка
Клонируйте репозиторий:
git clone https://github.com/YOUR-USERNAME/gemini-mcp-server.git
cd gemini-mcp-serverУстановить зависимости:
npm installСтроить:
npm run buildИнтеграция рабочего стола Клода
Чтобы использовать этот сервер с Claude Desktop:
Открыть рабочий стол Клода
Перейдите в Настройки > Разработчик.
Нажмите «Изменить конфигурацию».
Добавьте следующую конфигурацию:
"gemini": {
"command": "node",
"args": ["path\\to\\dist\\gemini_mcp_server.js"],
"env": {
"GEMINI_API_KEY": "gemini_api_key"
},
"cwd": "path\\to\\gemini-mcp-server"
}Заменять:
/path/to/gemini-mcp-serverна абсолютный путь к вашему репозиториюyour_api_key_hereна ваш реальный ключ API Google Gemini
Теперь сервер будет доступен в списке MCP-серверов Claude Desktop.
Реализация API
Этот сервер использует прямые HTTP-запросы к конечной точке API Gemini. Формат запроса API соответствует официальной документации Google:
curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:generateContent?key=GEMINI_API_KEY" \
-H 'Content-Type: application/json' \
-X POST \
-d '{
"contents": [{
"parts":[{"text": "Explain how AI works"}]
}]
}'Тестирование
Вы можете протестировать прямую реализацию API, используя пример скрипта:
node dist/example_direct_api.js "Your prompt here"Лицензия
Массачусетский технологический институт
Available Tools
1 toolgenerate_textD
| Name | Required | Description | Default |
|---|---|---|---|
| maxOutputTokens | No | ||
| prompt | Yes | ||
| stream | No | ||
| temperature | No | ||
| topK | No | ||
| topP | No |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
1 tool update
v1.0.0- First observed
generate_text
TDQS
Scored across 1 tool
With only one tool, there is no possibility of ambiguity or overlap between tools. The single tool 'generate_text' has a distinct purpose by default.
A single tool inherently has perfect naming consistency, as there are no other tools to compare it against. The name 'generate_text' follows a clear verb_noun pattern.
One tool is too few for a server named 'Gemini MCP Server', which suggests a broader scope like interacting with Gemini AI services. A single text generation tool feels thin and incomplete for such a domain.
The server is severely incomplete for its implied purpose. With only a text generation tool, it lacks essential operations like chat interactions, model selection, or other AI functionalities expected from a Gemini server, leading to significant gaps.
Maintenance
Related MCP Connectors
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
A Model Context Protocol server for Wix AI tools
- QuallaaOAuthcom.quallaa
Talk to your public-facing AI from any MCP client — Claude, ChatGPT, Cursor, Cline, Windsurf.
Hosted Notion MCP server for Claude, ChatGPT and Cursor, with each action switched per account.
Related MCP Servers
- AlicenseAqualityFmaintenanceModel Context Protocol (MCP) server implementation that enables Claude Desktop to interact with Google's Gemini AI models.616 npm259MIT
- AlicenseAqualityDmaintenanceA TypeScript server that integrates Google's Gemini Pro model with Claude Desktop through the Model Context Protocol, allowing Claude users to access Gemini's text generation capabilities.794 npm12MIT
- FlicenseNot gradedqualityDmaintenanceA server implementing the Model Context Protocol that enables AI assistants like Claude to interact with Google's Gemini API for text generation, text analysis, and chat conversations.-
- AlicenseBqualityDmaintenanceA Model Context Protocol server that enables Claude Desktop to interact with Google's Gemini 2.5 Pro Experimental AI model, with features like Google Search integration and token usage reporting.216 npm4Apache 2.0