ConsultingAgents MCP Server
An MCP server that interfaces with OpenAI and Anthropic's APIs to give Claude Code "coworkers" to help it on difficult problems.
Overview
ConsultingAgents MCP Server is a Model Context Protocol (MCP) server that allows Claude Code to consult with additional AI agents for code and problem analysis, providing a multi-model perspective on coding challenges.
To use the server, clone the repository, set up a virtual environment, install dependencies, configure API keys, and start the server. Then, register the MCP server with Claude Code to utilize the consulting tools.
- Darren: OpenAI expert coding consultant with high reasoning capabilities. - Sonny: Anthropic expert coding consultant with enhanced thinking. - Sergey: OpenAI web search specialist for finding relevant documentation. - MCP Integration: Seamless integration with Claude Code. - Multiple Transport Options: Supports stdio and HTTP/SSE transport.
- Analyzing complex coding problems with expert AI assistance.
- Finding relevant documentation and examples for coding tasks.
- Enhancing coding efficiency through multi-agent collaboration.
Add to your AI client
Use these steps to connect ConsultingAgents MCP Server in Cursor, Claude, VS Code, and other MCP-compatible apps. The same JSON appears in the Use with menu above for one-click copy.
Cursor
Add this to your .cursor/mcp.json file in your project root, then restart Cursor.
.cursor/mcp.json
{
"mcpServers": {
"consulting-agents-mcp-matthewpdingle": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-consulting-agents-mcp-matthewpdingle"
]
}
}
}Claude Desktop
Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.
~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)
{
"mcpServers": {
"consulting-agents-mcp-matthewpdingle": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-consulting-agents-mcp-matthewpdingle"
]
}
}
}Claude Code
Add this to your project's .mcp.json file. Claude Code will detect it automatically.
.mcp.json (project root)
{
"mcpServers": {
"consulting-agents-mcp-matthewpdingle": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-consulting-agents-mcp-matthewpdingle"
]
}
}
}VS Code (Copilot)
Add this to your .vscode/mcp.json file. Requires the GitHub Copilot extension with MCP support enabled.
.vscode/mcp.json
{
"servers": {
"consulting-agents-mcp-matthewpdingle": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-consulting-agents-mcp-matthewpdingle"
]
}
}
}Windsurf
Add this to your Windsurf MCP config file, then restart Windsurf.
~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"consulting-agents-mcp-matthewpdingle": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-consulting-agents-mcp-matthewpdingle"
]
}
}
}Cline
Open Cline settings, navigate to MCP Servers, and add this server configuration.
Cline MCP Settings (via UI)
{
"mcpServers": {
"consulting-agents-mcp-matthewpdingle": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-consulting-agents-mcp-matthewpdingle"
]
}
}
}FAQ
Can the MCP server consult with multiple agents at once?
Yes! The MCP server allows simultaneous consultations with Darren, Sonny, and Sergey for comprehensive support.
What are the prerequisites for using the MCP server?
You need Python 3.8+, OpenAI and Anthropic API keys, and the Claude Code CLI for integration.
Is the MCP server free to use?
Yes! The MCP server is free to use, but you need valid API keys for OpenAI and Anthropic.7:["$","div",null,{"className":"container mx-auto flex flex-col gap-4","children":["$L26","$L27",["$","$L28",null,{"currentProject":{"id":2742,"uuid":"bc5d6271-c8fa-4910-88e1-adadabdad6a6","name":"consulting-agents-mcp","title":"ConsultingAgents MCP Server","description":"An MCP server that interfaces with OpenAI and Anthropic's APIs to give Claude Code \"coworkers\" to help it on difficult problems.","avatar_url":"https://avatars.githubusercontent.com/u/10378017?v=4","created_at":"2025-03-14T00:55:34.655Z","updated_at":"2025-03-14T01:37:08.212Z","status":"created","author_name":"MatthewPDingle","author_avatar_url":"https://avatars.githubusercontent.com/u/10378017?v=4","tags":"[]","category":"research-and-data","is_featured":false,"sort":1,"url":"https://github.com/MatthewPDingle/consulting-agents-mcp","target":"_self","content":"$29","summary":"$2a","img_url":null,"type":null,"metadata":"{\"star\":\"4\",\"license\":\"MIT license\",\"language\":\"Python\",\"is_official\":false,\"latest_commit_time\":\"2025-04-03 13:49:23\"}","user_uuid":null,"tools":null,"sse_url":null,"sse_provider":null,"sse_params":null,"is_official":false,"server_command":null,"server_params":null,"server_config":null,"allow_call":false,"is_innovation":false,"is_dxt":false,"dxt_manifest":null,"dxt_file_url":null,"is_audit":false},"randomProjects":[],"currentServerKey":"$undefined"}]]}]