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.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
๐ง Expert MCP
Equip your AI model with an "on-call" senior expert consultant.
When downstream models encounter complex problems, they can use this MCP tool to forward the query to a pre-configured advanced model (e.g., GPT-5.5, Claude Opus 4.7, etc.) to obtain deep analysis and professional advice, then combine it with their own judgment to provide a final answer.
โจ Features
๐ OpenAI Compatible โ Connects to any upstream endpoint in OpenAI format (OpenAI / DeepSeek / Qwen / vLLM / Ollama, etc.)
โ๏ธ Config-Driven โ All parameters are centrally managed in
config.json, no code changes required๐ก Streamable HTTP โ Compliant with the latest MCP standard for streaming HTTP transport, endpoint
/mcp๐ ๏ธ Rich Tool Prompts โ Carefully designed
descriptionto guide downstream models to call at the right time๐งฉ Three-Part Input โ
question(required),context(background),focus(key areas)๐ Full Logging โ Request logs + Token usage statistics for easy monitoring and troubleshooting
Related MCP server: Consult LLM MCP
๐๏ธ How It Works
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โ ็จๆท (User) โ
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโฌโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โ ๆ้ฎ
โผ
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โ ไธๆธธๆจกๅ (Claude / GPT / Qwen โฆ) โ
โ โ
โ ้ๅฐๅคๆ้ฎ้ข๏ผโ ่ฐ็จ consult_advanced_model ๅทฅๅ
ท โ
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโฌโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โ MCP Streamable HTTP
โผ
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โ Expert MCP Server โ
โ (ๆฌ้กน็ฎ server.py) โ
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโฌโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โ OpenAI API ่ฏทๆฑ
โผ
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โ ไธๆธธ้ซ็บงๆจกๅ (GPT-5.5ใClaude Opus 4.7 โฆ) โ
โ ่ฟๅๆทฑๅบฆๅๆๆ่ง โ
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ๐ฆ Quick Start
1. Clone the repository
git clone https://github.com/MineJPGcraft/Expert-mcp.git
cd Expert-mcp2. Install dependencies
pip install -r requirements.txtPython 3.10+ is recommended; installation within a virtual environment is suggested.
3. Edit the configuration file
Copy and modify 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": "ไฝ ๆฏไธไฝ้กถๅฐ็่ตๆทฑไธๅฎถ้กพ้ฎ๏ผ่ฏทๅฏน้ฎ้ข่ฟ่กๆทฑๅ
ฅใไธฅ่ฐจใๅฏๆง่ก็ๅๆใ"
}
}See โ๏ธ Configuration Reference below for details on configuration items.
4. Start the service
python server.pySuccessful startup is indicated by the following logs:
2025-xx-xx | INFO | mcp-advisor | ไธๆธธๆจกๅ: gpt-4o @ https://api.openai.com/v1
2025-xx-xx | INFO | mcp-advisor | MCP ็ๅฌ: http://0.0.0.0:8765/mcpMCP endpoint address:
http://127.0.0.1:8765/mcp๐ง Client Integration
Add the following configuration in clients that support MCP Streamable HTTP (Cherry Studio, Cline, Claude Code, etc.):
{
"mcpServers": {
"expert-advisor": {
"type": "streamableHttp",
"url": "http://127.0.0.1:8765/mcp"
}
}
}Remote deployment? Replace
127.0.0.1with the actual IP or domain name of the server and ensure the corresponding port is open in the firewall.
โ๏ธ Configuration Reference
Field | Type | Default | Description |
| string |
| Service listening address |
| integer |
| Service listening port |
| string | โ | Base URL of the upstream API (OpenAI compatible format) |
| string | โ | Upstream API Key |
| string | โ | Upstream model name, e.g., |
| float |
| Generation temperature; lower values are recommended for analytical tasks |
| integer |
| Maximum tokens per response |
| float |
| Request timeout in seconds |
| string | Built-in default | System prompt for the advanced model, fully customizable |
Switch configuration files using environment variables
MCP_CONFIG=config.prod.json python server.py๐ ๏ธ Tool Description
Tools available for downstream models to call:
consult_advanced_model
Parameter | Type | Required | Description |
| string | โ | The core question to consult, keep it complete and clear |
| string | โ | Background information, such as code snippets, user requirements, attempted solutions, etc. |
| string | โ | The direction you want the advanced model to focus on |
Recommended scenarios for calling:
Problems where your own confidence is < 80%
User explicitly requests deep thinking / rigorous analysis / best practices
Multi-constraint problems involving complex trade-offs
Mathematics, algorithms, system design, or difficult bugs requiring step-by-step reasoning
Situations where you need to verify your own conclusions
Scenarios not recommended:
Simple greetings or pure information lookups
Basic questions with obvious answers
High-frequency, repetitive simple tasks
๐ Connecting to Upstream Services
Simply modify the upstream section in config.json to connect to different service providers.
๐ Dependencies
mcp>=1.2.0
openai>=1.40.0๐ License
MIT License ยฉ 2026 MCJPG
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogโฆ
Related MCP Servers
- FlicenseNot gradedqualityNot gradedmaintenanceAn OpenAI API-based MCP server that provides deep thinking and analysis capabilities, integrating with AI editor models to deliver comprehensive insights and practical solutions.-
- AlicenseAqualityBmaintenanceAn 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.1148MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI-to-AI consultation for critical thinking and complex reasoning via OpenRouter, allowing one AI to delegate tasks to another AI model.10MIT
- FlicenseNot gradedqualityDmaintenanceEnables two local LLMs (Qwen and Llama) to communicate via MCP, allowing one model to consult the other for second opinions or additional reasoning.1-