AI Consultant

MCP Server that allows your agent to consult with different models

typescript

1

GitHub Stars

typescript

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "filipkrayem-ai-consultant-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "ai-consultant-mcp"
      ],
      "env": {
        "VERBOSE_LOGGING": "true",
        "OPENROUTER_API_KEY": "your-openrouter-api-key"
      }
    }
  }
}

You can run an AI Consultant MCP Server to let your AI assistant consult multiple AI models through OpenRouter from a single interface. It smartly selects the best model for a task, keeps conversation history, caches responses to save costs, and handles errors gracefully, so your assistant can answer faster and more reliably.

How to use

Use your MCP client to connect to the AI Consultant MCP Server and start asking questions. You can rely on automatic model selection for most tasks, or specify a particular model when you want hands-on control. You can request a model list to discover capabilities and then choose the best option for your current task.

How to install

Prerequisites you need before installing are Node.js (for local development and tooling) and an OpenRouter API key. Install the MCP server package globally so it is accessible to your MCP client.

npm install -g ai-consultant-mcp

Configure your MCP client to use the AI Consultant MCP Server. The following example adds a stdio-based configuration that runs the MCP via npx and passes your OpenRouter API key. You can also run locally after building the project as shown in the development setup.

{
  "mcpServers": {
    "ai_consultant": {
      "command": "npx",
      "args": ["-y", "ai-consultant-mcp"],
      "env": {
        "OPENROUTER_API_KEY": "your-openrouter-api-key"
      }
    }
  }
}

If you prefer to run the server directly from source after development, configure your MCP client to execute the built JavaScript entry point with Node, including the required environment variable.

{
  "mcpServers": {
    "ai_consultant": {
      "command": "node",
      "args": ["/absolute/path/to/ai-consultant-mcp/dist/index.js"],
      "env": {
        "OPENROUTER_API_KEY": "your-openrouter-api-key"
      }
    }
  }
}

Additional setup notes

Environment variables you may use include OPENROUTER_API_KEY (required) to authorize requests to OpenRouter and VERBOSE_LOGGING (optional) to enable detailed logs. Keep your API key secure and do not commit it to source control.

Available tools

consult_ai

Ask questions to AI models with optional automatic model selection and caching. Maintains conversation context across queries.

list_models

List all available models and summarize their capabilities to help you choose the right model for a task.