Consulting Agents MCP server for AI agents

The ConsultingAgents MCP server enables Claude Code to consult with additional AI agents for code and problem analysis. It provides access to three expert consultants: Darren (OpenAI), Sonny (Anthropic), and Sergey (OpenAI with web search), allowing for multi-model perspectives on coding problems.

Prerequisites

Python 3.8+
OpenAI API key
Anthropic API key
Claude Code CLI (for integration)

Installation

Clone the repository

git clone https://github.com/yourusername/consulting-agents-mcp.git
cd consulting-agents-mcp

Create and activate a virtual environment

python -m venv mcp_venv
source mcp_venv/bin/activate  # On Windows: mcp_venv\Scripts\activate

Install dependencies

pip install -r requirements.txt

Set up API keys

Create a .env file in the project root:

OPENAI_API_KEY=your_openai_api_key_here
ANTHROPIC_API_KEY=your_anthropic_api_key_here

Start the server

chmod +x start_mcp_server.sh
./start_mcp_server.sh

Integration with Claude Code

Register the MCP server

claude mcp add ConsultingAgents /absolute/path/to/consulting-agents-mcp/start_mcp_server.sh

Start Claude Code with MCP integration

claude --mcp-debug

Using the tools

Once configured, you can use consult_with_darren, consult_with_sonny, and consult_with_sergey functions directly in Claude Code.

Available Tools

consult_with_darren

Uses OpenAI's o3-mini model with high reasoning to analyze code and provide recommendations.

Parameters:

consultation_context: Description of the problem (required)
source_code: Optional code to analyze

consult_with_sonny

Uses Claude 3.7 Sonnet with enhanced thinking to provide in-depth code analysis.

Parameters:

consultation_context: Description of the problem (required)
source_code: Optional code to analyze

consult_with_sergey

Uses GPT-4o with web search capabilities to find relevant documentation and examples.

Parameters:

consultation_context: Description of what information or documentation you need (required)
search_query: Optional specific search query to use
source_code: Optional code for context

Advanced Configuration

Environment Variables

MCP_TRANSPORT: Transport protocol (default: "stdio", alternatives: "http", "sse")
HOST: Server host when using HTTP/SSE transport (default: "127.0.0.1")
PORT: Server port when using HTTP/SSE transport (default: 5000)

HTTP API

When running with HTTP transport, the server provides these endpoints:

Health Check

GET /health

Returns server status and available agents.

Model Consultation

POST /consult

Request body for Darren or Sonny:

{
  "agent": "Darren",
  "consultation_context": "I have a bug in my code where...",
  "source_code": "def example():\n    return 'hello'"
}

Request body for Sergey:

{
  "agent": "Sergey",
  "consultation_context": "How do I implement JWT authentication in Express?",
  "search_query": "express.js JWT auth implementation"
}

Troubleshooting

MCP Server Not Found: Verify the absolute path in your claude mcp add command
API Authentication Errors: Check that your API keys are correctly set in the .env file
Connection Issues: Ensure the MCP server is running before starting Claude Code
Debug Logs: Check the terminal where the MCP server is running for detailed logs

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "ConsultingAgents" '{"command":"/absolute/path/to/consulting-agents-mcp/start_mcp_server.sh","args":[]}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "ConsultingAgents": {
            "command": "/absolute/path/to/consulting-agents-mcp/start_mcp_server.sh",
            "args": []
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "ConsultingAgents": {
            "command": "/absolute/path/to/consulting-agents-mcp/start_mcp_server.sh",
            "args": []
        }
    }
}

3. Restart Claude Desktop for the changes to take effect