GemForge-Gemini-Tools-MCP
GemForge(Gemini 工具)
GemForge-Gemini-Tools-MCP :企业级 Gemini 集成,适用于您常用的 MCP 代理。增强 Claude、Roo Code 和 Windsurf 的功能,提供代码库分析、实时搜索、文本/PDF/图像处理等功能。
快速导航
Related MCP server: Vibe Check MCP
为什么选择 GemForge?
GemForge 是 Google Gemini AI 与 MCP 生态系统之间的重要桥梁:
实时网络访问:使用
gemini_search获取突发新闻、市场趋势和当前数据高级推理:通过
gemini_reason逐步思考处理复杂的逻辑问题代码精通:使用
gemini_code分析完整存储库、生成解决方案和调试代码多文件处理:使用
gemini_fileops处理 60 多种文件格式,包括 PDF、图像等智能模型选择:自动为每个任务路由到最佳的 Gemini 模型
企业级:强大的错误处理、速率限制管理和 API 回退机制
快速入门
单行安装
npx @gemforge/mcp-server@latest init手动设置
创建配置文件(
claude_desktop_config.json):
{
"mcpServers": {
"GemForge": {
"command": "node",
"args": ["./dist/index.js"],
"env": {
"GEMINI_API_KEY": "your_api_key_here"
}
}
}
}安装并运行:
npm install gemforge-mcp
npm start重载可靠性
GemForge 专为生产环境而构建:
支持 60 多种文件类型:处理从代码到文档到图像的所有内容
自动模型回退:即使在速率限制或服务中断期间也能继续运行
企业级错误日志:详细的诊断,用于故障排除
API 弹性:指数退避、重试逻辑和无缝模型切换
完整的存储库支持:使用可配置的包含/排除模式分析整个代码库
XML内容处理:针对结构化数据的专门处理
关键工具
工具 | 描述 | 关键能力 |
| 网络连接信息检索 | 实时数据访问 |
| 通过逐步逻辑解决复杂问题 | 透明的推理过程 |
| 深度代码理解和生成 | 完整的存储库分析 |
| 跨 60 多种格式的多文件处理 | 文档比较与转换 |
{
"toolName": "gemini_search",
"toolParams": {
"query": "Latest advancements in quantum computing",
"enable_thinking": true
}
}{
"toolName": "gemini_code",
"toolParams": {
"question": "Identify improvements and new features",
"directory_path": "path/to/project",
"repomix_options": "--include \"**/*.js\" --no-gitignore"
}
}{
"toolName": "gemini_fileops",
"toolParams": {
"file_path": ["contract_v1.pdf", "contract_v2.pdf"],
"operation": "analyze",
"instruction": "Compare these contract versions and extract all significant changes."
}
}配置
GemForge 提供灵活的配置选项:
GEMINI_API_KEY=your_api_key_here # Required: Gemini API key
GEMINI_PAID_TIER=true # Optional: Set to true if using paid tier (better rate limits)
DEFAULT_MODEL_ID=gemini-2.5-pro # Optional: Override default model selection
LOG_LEVEL=info # Optional: Set logging verbosity (debug, info, warn, error){
"mcpServers": {
"GemForge": {
"command": "node",
"args": ["./dist/index.js"],
"env": {
"GEMINI_API_KEY": "your_api_key_here"
}
}
}
}GemForge 为每个任务智能选择最佳模型:
gemini_search:使用gemini-2.5-flash来提高速度并进行搜索集成gemini_reason:使用gemini-2.5-pro实现深度推理能力gemini_code:使用gemini-2.5-pro来理解复杂的代码gemini_fileops:根据文件大小在gemini-2.0-flash-lite或gemini-1.5-pro之间进行选择
在任何工具调用中使用model_id参数覆盖或设置DEFAULT_MODEL_ID环境变量。
部署
Smithery.ai
通过Smithery.ai一键部署
Docker
docker run -e GEMINI_API_KEY=your_api_key ghcr.io/pv-bhat/gemforge:latest自托管
使用我们的MCP.so 目录列表获取集成说明。
GemForge 有何独特之处?
跨生态系统的力量:将谷歌的人工智能与 Claude 和其他 MCP 代理连接起来
多文件分析:比较文档、图像或代码版本
智能路由:根据任务需求自动选择模型
生产就绪:专为企业环境打造

社区与支持
加入我们: MCP Discord | GemForge Discord
贡献: GitHub 讨论
反馈:在 Discord 上提出问题或分享想法
文档
请访问我们的文档网站以获取:
高级使用教程
API 参考
故障排除提示
执照
根据 MIT 许可证授权。详情请参阅许可证。
致谢
由Gemini API提供支持并受到模型上下文协议的启发。
Available Tools
4 toolsgemini_codeC
Analyzes codebases using Repomix and Gemini 2.5 Pro. Answers questions about code structure, logic, and potential improvements.
Inputs: question (required), codebase_path, directory_path, model_id.
gemini_fileopsA
Performs efficient operations on files (text, PDF, images, etc.) using appropriate Gemini models (Flash-Lite or 1.5 Pro for large files). Use for summarization, extraction, or basic analysis.
Inputs: file_path (required), instruction, model_id, operation, +1 more.
gemini_reasonA
Solves complex problems with step-by-step reasoning using Gemini 2.0 Flash Thinking. Best for math and science problems, coding challenges, and tasks requiring transparent reasoning process.
Inputs: problem (required), file_path, model_id, show_steps.
gemini_searchA
Generates responses based on the latest information using Gemini 2.0 Flash and Google Search. Best for general knowledge questions, fact-checking, and information retrieval.
Inputs: query (required), enable_thinking, file_path, model_id.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool has a clearly distinct purpose with no overlap: gemini_code analyzes codebases, gemini_fileops handles file operations, gemini_reason solves complex problems with reasoning, and gemini_search retrieves general information. The descriptions clearly differentiate their domains and use cases, making misselection unlikely.
All tool names follow a consistent 'gemini_' prefix pattern with descriptive suffixes (code, fileops, reason, search). This uniform naming convention makes the tool set predictable and easy to understand, with no deviations in style or structure.
Four tools is a reasonable number for a Gemini-focused server, covering key areas like code analysis, file operations, reasoning, and search. It feels slightly thin but well-scoped, as each tool addresses a distinct domain without unnecessary duplication.
The tool set covers major use cases for Gemini models: code analysis, file handling, reasoning, and information retrieval. Minor gaps might include more specialized operations like image generation or multimodal analysis, but the core functionalities are well-represented for general-purpose tasks.
Maintenance
Related MCP Connectors
Shared memory MCP server for Claude Code, Codex, Gemini CLI and Cursor. Cited, editable.
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceThe ultimate Gemini API interface for MCP hosts, intelligently selecting models for the task at hand—delivering optimal performance, minimal token cost, and seamless integration.32MIT
- AlicenseBqualityDmaintenanceA metacognitive pattern interrupt system that helps prevent AI assistants from overcomplicated reasoning paths by providing external validation, simplification guidance, and learning mechanisms.2325 npm505MIT
- AlicenseBqualityDmaintenanceA lightweight MCP server that enables AI agents to perform deep codebase analysis by leveraging Gemini's massive context window for cross-file analysis and intelligent file selection.428MIT
- AlicenseAqualityDmaintenanceAn MCP server that gives your IDE or agent access to Google Gemini with autonomous codebase exploration, enabling deep code analysis, architectural reviews, and bug hunting.2010MIT
Appeared in Searches
- A real-time voice and text AI assistant with Google Search integration and system control
- A server for searching and finding other MCP servers
- Search for 'dia' (unspecified context)
- Tools or methods for generating academic papers
- A server for finding scientific articles, creating ad ideas, and deploying Facebook ads