Expert MCP
Allows using locally hosted or self-managed models via Ollama's OpenAI-compatible endpoint as an upstream expert consultant, providing deep analysis and recommendations.
Forwards complex questions to an advanced OpenAI-compatible model (e.g., GPT-5.5) for deep analysis and professional advice, enabling downstream AI agents to consult high-capability models via an OpenAI API endpoint.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Expert MCPGet expert advice on optimizing this database query."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
🧠 Expert MCP
为你的 AI 模型配备一位"随时可以请教"的高级专家顾问。
当下游模型遇到复杂问题时,可以通过本 MCP 工具将问题转发给预先配置好的高级模型(如 GPT-5.5、Claude Opus 4.7 等), 获取深度分析与专业建议,再结合自身判断给出最终答案。
✨ 功能特性
🔌 OpenAI 兼容 — 对接任何 OpenAI 格式的上游端点(OpenAI / DeepSeek / Qwen / vLLM / Ollama 等)
⚙️ 配置文件驱动 — 所有参数在
config.json中集中管理,无需改动代码📡 Streamable HTTP — 符合 MCP 最新标准的流式 HTTP 传输,端点
/mcp🛠️ 丰富的工具提示 — 精心设计的
description,引导下游模型在正确时机调用🧩 三段式入参 —
question(必填)、context(背景)、focus(重点方向)📊 完整日志 — 请求日志 + Token 用量统计,便于监控与排查
Related MCP server: Consult LLM MCP
🏗️ 工作原理
┌─────────────────────────────────────────────────────────┐
│ 用户 (User) │
└───────────────────────────┬─────────────────────────────┘
│ 提问
▼
┌─────────────────────────────────────────────────────────┐
│ 下游模型 (Claude / GPT / Qwen …) │
│ │
│ 遇到复杂问题?→ 调用 consult_advanced_model 工具 │
└───────────────────────────┬─────────────────────────────┘
│ MCP Streamable HTTP
▼
┌─────────────────────────────────────────────────────────┐
│ Expert MCP Server │
│ (本项目 server.py) │
└───────────────────────────┬─────────────────────────────┘
│ OpenAI API 请求
▼
┌─────────────────────────────────────────────────────────┐
│ 上游高级模型 (GPT-5.5、Claude Opus 4.7 …) │
│ 返回深度分析意见 │
└─────────────────────────────────────────────────────────┘📦 快速开始
1. 克隆仓库
git clone https://github.com/MineJPGcraft/Expert-mcp.git
cd Expert-mcp2. 安装依赖
pip install -r requirements.txt推荐使用 Python 3.10+,建议在虚拟环境中安装。
3. 编辑配置文件
复制并修改 config.json:
{
"host": "0.0.0.0",
"port": 8765,
"upstream": {
"base_url": "https://api.openai.com/v1",
"api_key": "sk-xxxxxxxxxxxxxxxxxxxx",
"model": "gpt-5.5",
"temperature": 0.3,
"max_tokens": 4096,
"timeout": 120,
"system_prompt": "你是一位顶尖的资深专家顾问,请对问题进行深入、严谨、可执行的分析。"
}
}配置项说明见下方 ⚙️ 配置参考。
4. 启动服务
python server.py看到如下日志即表示启动成功:
2025-xx-xx | INFO | mcp-advisor | 上游模型: gpt-4o @ https://api.openai.com/v1
2025-xx-xx | INFO | mcp-advisor | MCP 监听: http://0.0.0.0:8765/mcpMCP 端点地址:
http://127.0.0.1:8765/mcp🔧 客户端接入
在支持 MCP Streamable HTTP 的客户端(Cherry Studio、Cline、Claude Code 等)中添加如下配置:
{
"mcpServers": {
"expert-advisor": {
"type": "streamableHttp",
"url": "http://127.0.0.1:8765/mcp"
}
}
}远程部署? 将
127.0.0.1替换为服务器的实际 IP 或域名,并确保防火墙放行对应端口。
⚙️ 配置参考
字段 | 类型 | 默认值 | 说明 |
| string |
| 服务监听地址 |
| integer |
| 服务监听端口 |
| string | — | 上游 API 的 base URL(OpenAI 兼容格式) |
| string | — | 上游 API Key |
| string | — | 上游模型名称,如 |
| float |
| 生成温度,建议分析类任务保持较低值 |
| integer |
| 单次回复最大 Token 数 |
| float |
| 请求超时秒数 |
| string | 内置默认值 | 高级模型的系统提示词,可完全自定义 |
使用环境变量切换配置文件
MCP_CONFIG=config.prod.json python server.py🛠️ 工具说明
下游模型可以调用的工具:
consult_advanced_model
参数 | 类型 | 必填 | 说明 |
| string | ✅ | 待咨询的核心问题,尽量完整清晰 |
| string | ❌ | 背景信息,如代码片段、用户需求、已尝试方案等 |
| string | ❌ | 希望高级模型重点回答的方向 |
建议调用的场景:
自身把握 < 80% 的问题
用户明确要求深度思考 / 严谨分析 / 最佳方案
涉及复杂权衡的多约束问题
需要逐步推理的数学、算法、系统设计、疑难 Bug
需要二次验证自己结论的情况
不建议调用的场景:
简单问候或纯粹的信息查询
答案显而易见的基础问题
高频重复的简单任务
🌐 对接上游服务
只需修改 config.json 中的 upstream 部分即可对接不同服务商
📋 依赖
mcp>=1.2.0
openai>=1.40.0📄 License
MIT License © 2026 MCJPG
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- Flicense-quality-maintenanceAn OpenAI API-based MCP server that provides deep thinking and analysis capabilities, integrating with AI editor models to deliver comprehensive insights and practical solutions.Last updated
- AlicenseAqualityAmaintenanceAn MCP server that lets Claude Code consult stronger AI models (o3, Gemini 2.5 Pro, DeepSeek Reasoner) when you need deeper analysis on complex problems.Last updated1102124MIT
- Alicense-qualityCmaintenanceEnables AI-to-AI consultation for critical thinking and complex reasoning via OpenRouter, allowing one AI to delegate tasks to another AI model.Last updated10MIT
- Flicense-qualityBmaintenanceMCP server that lets Claude Code consult ChatGPT for a second opinion mid-task, with explicit context passed by the caller.Last updated
Related MCP Connectors
AI Reasoning Cache & Consensus Layer with 11 MCP tools via Streamable HTTP.
A paid remote MCP for OpenAI Codex agent coordination MCP, built to return verdicts, receipts, usage
MCP server for AI dialogue using various LLM models via AceDataCloud
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/MineJPGcraft/Expert-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server