License

Skip to content

You signed in with another tab or window. Reload
to refresh your session. You signed out in another tab or window. Reload
to refresh your session. You switched accounts on another tab or window. Reload
to refresh your session. Dismiss alert

MatthewPDingle / consulting-agents-mcp Public

• Notifications
  You must be signed in to change notification settings

• Fork 1

• Star 4

An MCP server that interfaces with OpenAI and Anthropic's APIs to give Claude Code "coworkers" to help it on difficult problems.

License

MIT license

4 stars
1 fork
Branches
Tags
Activity

Star

Notifications
You must be signed in to change notification settings

MatthewPDingle/consulting-agents-mcp

master

1 Branch
0 Tags

Go to file

Code

Folders and files

| Name | | Name | Last commit message | Last commit date |
| --- | --- | --- | --- |
| Latest commit
-------------


MatthewPDingle

Improve Sergey's search prioritization

Mar 15, 2025

f596a2b
 · Mar 15, 2025

History
-------

5 Commits

| | |
| .env.example | | .env.example | Initial commit | Mar 13, 2025 |
| .gitignore | | .gitignore | Initial commit | Mar 13, 2025 |
| CLAUDE.md | | CLAUDE.md | Enhance agent consulting capabilities and documentation | Mar 15, 2025 |
| CONTRIBUTING.md | | CONTRIBUTING.md | Initial commit | Mar 13, 2025 |
| LICENSE | | LICENSE | Initial commit | Mar 13, 2025 |
| README.md | | README.md | Add Sergey agent with web search capabilities | Mar 13, 2025 |
| mcp_consul_server.py | | mcp_consul_server.py | Improve Sergey's search prioritization | Mar 15, 2025 |
| start_mcp_server.sh | | start_mcp_server.sh | Initial commit | Mar 13, 2025 |
| View all files | | |

Repository files navigation

ConsultingAgents MCP Server

A Model Context Protocol (MCP) server that allows Claude Code to consult with additional AI agents for code and problem analysis. This server provides access to Darren (OpenAI), Sonny (Anthropic), and Sergey (OpenAI with web search) as expert consultants, enabling multi-model perspective on coding problems.

Features

• Darren: OpenAI expert coding consultant powered by o3-mini model with high reasoning capabilities
• Sonny: Anthropic expert coding consultant powered by Claude 3.7 Sonnet with enhanced thinking
• Sergey: OpenAI web search specialist powered by GPT-4o for finding relevant documentation and examples
• MCP Integration: Seamless integration with Claude Code via MCP protocol
• Multiple Transport Options: Supports stdio (for direct Claude Code integration) and HTTP/SSE transport

Prerequisites

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

Quick Start

1. Clone the repository:

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

2. Create and activate a virtual environment:

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

3. Install dependencies:

   shell pip install -r requirements.txt

4. 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
   

5. Start the server:

   shell chmod +x start_mcp_server.sh ./start_mcp_server.sh

Integration with Claude Code

1. Register the MCP server with Claude Code:

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

2. Start Claude Code with MCP integration:

   shell claude --mcp-debug

3. Use the tools in Claude Code:

   Now you can use consult_with_darren, consult_with_sonny, and consult_with_sergey functions in Claude Code.
   

Available Tools

The MCP server provides three consulting 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 Using HTTP Transport)

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

Development

Running in Development Mode

1. Start the server with debug output:

   shell DEBUG=true ./start_mcp_server.sh

2. Test HTTP endpoints (when using HTTP transport):

   ```shell

   Test Darren

   curl -X POST http://localhost:5000/consult \
   -H "Content-Type: application/json" \
   -d '{"agent":"Darren","consultation_context":"Test message"}'

   Test Sonny

   curl -X POST http://localhost:5000/consult \
   -H "Content-Type: application/json" \
   -d '{"agent":"Sonny","consultation_context":"Test message"}'

   Test Sergey

   curl -X POST http://localhost:5000/consult \
   -H "Content-Type: application/json" \
   -d '{"agent":"Sergey","consultation_context":"Test message","search_query":"example"}'
   ```

Project Structure

• mcp_consul_server.py: Main MCP server implementation
• start_mcp_server.sh: Script to start the server with proper environment
• requirements.txt: Python dependencies

License

MIT

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

About

An MCP server that interfaces with OpenAI and Anthropic's APIs to give Claude Code "coworkers" to help it on difficult problems.

Resources

Readme

License

MIT license

Activity

Stars

4 stars

Watchers

1 watching

Forks

1 fork

Report repository

Releases

No releases published

Packages 0

No packages published

Languages

• Python 96.6%

• Shell 3.4%

You can’t perform that action at this time.