Gemini Thinking Server
模型上下文协议 - Gemini Thinking Server
这是模型上下文协议 (MCP) 的实现,它与 Google 的 Gemini API 集成,无需代码生成即可提供分析思维能力。
概述
Gemini Thinking Server 是一款专用的 MCP 服务器,它利用 Google 的 Gemini 模型来提供顺序思考和问题解决能力。它能够实现以下功能:
将复杂问题分解成几个步骤
规划和设计留有修改空间
可能需要修正路线的分析
最初可能不清楚全部范围的问题
Related MCP server: gpal
特征
双子座思维:利用双子座的分析能力来产生深思熟虑的回应
元评论:提供对推理过程的见解
置信水平:表明 Gemini 对其分析的信心程度
替代路径:建议解决问题的不同方法
分支思维:允许探索不同的思维路径
修改能力:支持修改以前的想法
会话持久性:保存并恢复分析会话
安装
# Clone the repository
git clone <repository-url>
# Install dependencies
npm install
# Build the project
npm run build用法
环境设置
在运行服务器之前,您需要设置您的 Gemini API 密钥:
export GEMINI_API_KEY=your_api_key_here运行服务器
node dist/gemini-index.js工具参数
geminithinking工具接受以下参数:
query(必需):要分析的问题context(可选):附加上下文信息approach(可选):建议解决问题的方法previousThoughts(可选):上下文中先前想法的数组thought(可选):您当前的思考步骤(如果为空,将由 Gemini 生成)nextThoughtNeeded(必需):是否需要另一个思考步骤thoughtNumber(必填):当前的想法数totalThoughts(必填):估计需要的想法总数isRevision(可选):这是否改变了以前的想法revisesThought(可选):正在重新考虑哪些想法branchFromThought(可选):分支点思想编号branchId(可选):分支标识符needsMoreThoughts(可选):如果需要更多想法
会话管理
该工具还支持会话管理命令:
sessionCommand:管理会话的命令('save'、'load'、'getState')sessionPath:保存或加载会话文件的路径(“保存”和“加载”命令所需)
示例:保存会话
{
"sessionCommand": "save",
"sessionPath": "/path/to/save/session.json",
"query": "dummy",
"thoughtNumber": 1,
"totalThoughts": 1,
"nextThoughtNeeded": false
}示例:加载会话
{
"sessionCommand": "load",
"sessionPath": "/path/to/load/session.json",
"query": "dummy",
"thoughtNumber": 1,
"totalThoughts": 1,
"nextThoughtNeeded": false
}示例:获取会话状态
{
"sessionCommand": "getState",
"query": "dummy",
"thoughtNumber": 1,
"totalThoughts": 1,
"nextThoughtNeeded": false
}例子
以下是如何使用该工具的示例:
{
"query": "How might we design a sustainable urban transportation system?",
"context": "The city has 500,000 residents and currently relies heavily on personal vehicles.",
"approach": "Consider environmental, economic, and social factors.",
"thoughtNumber": 1,
"totalThoughts": 5,
"nextThoughtNeeded": true
}响应格式
服务器响应:
{
"thought": "The generated thought from Gemini",
"thoughtNumber": 1,
"totalThoughts": 5,
"nextThoughtNeeded": true,
"branches": [],
"thoughtHistoryLength": 1,
"metaComments": "Meta-commentary about the reasoning",
"confidenceLevel": 0.85,
"alternativePaths": ["Alternative approach 1", "Alternative approach 2"]
}示例客户端
提供了几个示例客户端来演示不同的用例:
sample-client.js:基本客户端示例example-usage.js:具体使用示例codebase-analysis-example.js:代码库分析示例session-example.js:演示会话持久性的示例advanced-filtering-example.js:演示高级语义过滤的示例
运行会话示例:
node dist/session-example.js运行高级过滤示例:
node dist/advanced-filtering-example.js执照
麻省理工学院
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Tools
Related MCP Servers
- AlicenseAqualityDmaintenanceA MCP server that implements sequential thinking protocols, provides structured problem-solving methods, decomposes complex problems into manageable steps, and supports iterative optimization and alternative reasoning paths.12Apache 2.0
- AlicenseAqualityCmaintenanceAn 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
- AlicenseAqualityCmaintenanceAn advanced MCP server that provides an agentic interface to Google's Gemini 3.1 models via Vertex AI, combining real-time Google Search, URL analysis, and Python code execution to solve complex multi-step research and data tasks.1MIT
- AlicenseAqualityCmaintenanceGemini-powered MCP server for automated code review, analysis, and documentation.1361MIT
Related MCP Connectors
MCP server for generating rough-draft project plans from natural-language prompts.
MCP server for AI dialogue using various LLM models via AceDataCloud
Hosted MCP server connecting claude.ai, ChatGPT and other AI apps to your own computer
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/bartekke8it56w2/new-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server