Aurai AI Advisor
MCP Aurai Server - AI顾问服务器
What is Aurai AI Advisor?
Aurai AI Advisor is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp aurai server - ai顾问服务器
MCP Aurai Server - AI顾问服务器
This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- MCP Aurai Server - AI顾问服务器
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx mcp-auraiConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Aurai AI Advisor
Aurai is an AI advisor MCP server that acts as a remote consultant inside Claude Code or any MCP-compatible client. It forwards context (code, documents, notes) to an OpenAI-compatible backend model and returns structured analysis, plans, or next-step instructions—supporting multi-turn consultation loops with persistent conversation history across up to 50 rounds.
Prerequisites
- Python 3.10 or later
- An OpenAI-compatible API key (OpenAI, Azure OpenAI, or any compatible provider)
- uv or pip for Python dependency management
- Claude Code CLI or another MCP-compatible client
- Git to clone the repository
Clone the repository
Clone the mcp-aurai-server repository and enter the project directory.
git clone https://github.com/LZMW/mcp-aurai-server.git
cd mcp-aurai-serverCreate a virtual environment and install the package
Set up a Python virtual environment and install the package in editable mode.
python -m venv venv
# Activate (Linux/macOS)
source venv/bin/activate
# Activate (Windows)
venv\Scripts\activate
pip install -e .Register with Claude Code
Add the server to Claude Code using the mcp add command. Provide your API key, the base URL of your OpenAI-compatible endpoint, and the model identifier you want Aurai to use.
claude mcp add --scope user --transport stdio aurai-advisor \
--env AURAI_API_KEY="sk-your-api-key" \
--env AURAI_BASE_URL="https://api.openai.com/v1" \
--env AURAI_MODEL="gpt-4o" \
-- "/path/to/mcp-aurai-server/venv/bin/python" "-m" "mcp_aurai.server"Verify the connection
Confirm the server registered successfully and is showing as connected.
claude mcp list
# Expected output:
# aurai-advisor: ✓ ConnectedOptional: tune performance environment variables
Adjust generation parameters or history retention via environment variables. These can be added to the --env flags in the mcp add command.
# Optional tuning variables:
# AURAI_TEMPERATURE=0.7 (0.0–2.0, default 0.7)
# AURAI_MAX_TOKENS=32000 (max output tokens per response)
# AURAI_CONTEXT_WINDOW=200000 (total token budget)
# AURAI_MAX_ITERATIONS=50 (max conversation rounds)
# AURAI_ENABLE_PERSISTENCE=true (persist history to disk)
# AURAI_HISTORY_PATH=~/.mcp-aurai/history.json
# AURAI_STDIO_IDLE_TIMEOUT_SECONDS=0 (0 = never auto-exit)Aurai AI Advisor Examples
Client configuration
Claude Desktop claude_desktop_config.json for Aurai Advisor with an OpenAI API key and gpt-4o model.
{
"mcpServers": {
"aurai-advisor": {
"command": "/path/to/mcp-aurai-server/venv/bin/python",
"args": ["-m", "mcp_aurai.server"],
"env": {
"AURAI_API_KEY": "sk-your-api-key",
"AURAI_BASE_URL": "https://api.openai.com/v1",
"AURAI_MODEL": "gpt-4o",
"AURAI_TEMPERATURE": "0.7",
"AURAI_MAX_TOKENS": "32000"
}
}
}
}Prompts to try
Example prompts using the four Aurai tools: sync_context, consult_aurai, report_progress, and get_status.
- "Upload my current codebase context to Aurai and ask it to identify architectural issues"
- "Consult Aurai: what is the best approach to add distributed tracing to this Python service?"
- "Report to Aurai that I finished implementing the database migrations and ask for the next step"
- "Get Aurai session status and show me the current conversation history"
- "Ask Aurai to review my API design and suggest improvements for REST compliance"Troubleshooting Aurai AI Advisor
Server shows as disconnected or fails to start in Claude Code
Ensure the Python path in the command points to the interpreter inside your virtual environment, not the system Python. Run `which python` inside the activated venv to get the correct absolute path. Also confirm `pip install -e .` completed without errors.
API calls fail with authentication errors
Verify AURAI_API_KEY is a valid key for the provider at AURAI_BASE_URL. For Azure OpenAI, the base URL format differs from the standard OpenAI URL—consult your Azure portal for the correct endpoint. For local models via LM Studio or Ollama, set AURAI_BASE_URL to their local API endpoint (e.g., http://localhost:1234/v1).
Conversation history is not persisted between sessions
Set AURAI_ENABLE_PERSISTENCE=true and confirm AURAI_HISTORY_PATH points to a directory where the running user has write permissions. The default path is ~/.mcp-aurai/history.json.
Frequently Asked Questions about Aurai AI Advisor
What is Aurai AI Advisor?
Aurai AI Advisor is a Model Context Protocol (MCP) server that mcp aurai server - ai顾问服务器 It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Aurai AI Advisor?
Follow the installation instructions on the Aurai AI Advisor GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Aurai AI Advisor?
Aurai AI Advisor works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Aurai AI Advisor free to use?
Yes, Aurai AI Advisor is open source and available under the NOASSERTION license. You can use it freely in both personal and commercial projects.
Aurai AI Advisor Alternatives — Similar Coding Agents Servers
Looking for alternatives to Aurai AI Advisor? Here are other popular coding agents servers you can use with Claude, Cursor, and VS Code.
Dify
★ 142.2kProduction-ready platform for agentic workflow development.
Ruflo
★ 54.0k🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, self-learning swarm intelligence, RAG integrat
Goose
★ 45.7kan open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
Antigravity Awesome Skills
★ 38.3kInstallable GitHub library of 1,400+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.
AgentScope
★ 25.5kBuild and run agents you can see, understand and trust.
Serena
★ 24.5kA coding agent toolkit that provides IDE-like semantic code retrieval and editing tools, enabling LLMs to efficiently navigate and modify codebases using symbol-level operations instead of basic file reading and string replacements.
Browse More Coding Agents MCP Servers
Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Aurai AI Advisor in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Aurai AI Advisor?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.