gemini-understanding
A minimal MCP server that exposes Gemini's web and multimodal understanding (video, audio, document, image) through five dedicated tools.
README
gemini-understanding
A minimal MCP server for one-shot Gemini requests. Each tool call sends one prompt and at most one source, returns one answer, and does not link calls into a continuing conversation.
The server exposes three independent tools:
webremote_filelocal_file
Clients and MCP gateways may expose any subset of the tools. This is useful for remote or isolated deployments where filesystem access is unavailable or undesirable: local_file can be hidden without changing the contract of the remaining tools.
web
Performs one-shot web research with both Gemini server tools enabled:
- Google Search
- URL Context
Input:
{
"prompt": "Research the topic and read https://example.com/page"
}
Ordinary webpage URLs may be included directly in the prompt.
remote_file
Analyzes one public HTTP(S) file URL. The caller must declare the source type; the server does not inspect the URL or reclassify the source.
Input:
{
"url": "https://example.com/report.pdf",
"type": "document",
"prompt": "Summarize the conclusions",
"mimeType": "application/pdf"
}
type is required and must be one of:
imagevideoaudiodocument
mimeType is optional, but it is preferred for direct remote files when known because origin servers may return missing, generic, malformed, or parameterized MIME metadata. Public YouTube URLs are supplied with type: "video" and normally omit mimeType.
Examples:
{
"url": "https://www.youtube.com/watch?v=...",
"type": "video",
"prompt": "Summarize this video"
}
{
"url": "https://example.com/audio.mp3",
"type": "audio",
"prompt": "Transcribe the speech",
"mimeType": "audio/mpeg"
}
The URL is passed directly to Gemini as a typed URI. The server performs no HTTP header probing, MIME sniffing, extension-based routing, downloading, conversion, or cross-type fallback.
local_file
Analyzes one file available on the MCP server filesystem. The caller must declare the source type; the server does not inspect the content or reclassify the source.
Input:
{
"path": "/workspace/report.pdf",
"type": "document",
"prompt": "Summarize the conclusions"
}
type is required and must be one of:
imagevideoaudiodocument
mimeType is optional. The Gemini SDK normally infers it from a recognized file extension. It may be supplied as an override when inference is unavailable or incorrect.
The server:
- resolves relative paths against its working directory;
- uploads the file through the Gemini Files API;
- waits until processing is complete;
- sends the uploaded URI using the declared source type;
- deletes the temporary upload.
The path refers to the filesystem visible to the MCP server process. In a remote, containerized, or isolated deployment, it does not refer to the MCP client's filesystem unless that storage is explicitly mounted or shared.
Configuration
GEMINI_API_KEY required
GEMINI_MODEL default: gemini-3.5-flash-lite
GEMINI_THINKING_LEVEL default: high
Custom model and thinking-level strings are passed through without compatibility validation.
Install from GitHub
claude mcp add gemini-understanding -s user -- \
env GEMINI_API_KEY=YOUR_KEY \
npx -y github:sandlong/gemini-understanding
With explicit optional settings:
claude mcp add gemini-understanding -s user -- \
env GEMINI_API_KEY=YOUR_KEY \
GEMINI_MODEL=gemini-3.5-flash-lite \
GEMINI_THINKING_LEVEL=high \
npx -y github:sandlong/gemini-understanding
Local development
npm install
npm test
npm run build
Run the stdio server:
GEMINI_API_KEY=YOUR_KEY npm start
The stdio implementation can also be placed behind an MCP gateway that exposes it through Streamable HTTP. Tool filtering remains a client or gateway concern.
Error behavior
The server does not silently correct or reroute failed requests. Tool errors include the tool name, processing stage, configured model, thinking level, source, and the original Gemini status, code, and message when available.
A nonexistent server-side path fails at the filesystem stage because no API request can be constructed. Temporary-upload cleanup failures are non-fatal and are reported as warnings.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。